Reliable robotic manipulation requires both semantic understanding and precise control in three-dimensional space. However, vision-language-action (VLA) foundations largely inherit visual representations from 2D vision-language pre-training, while spatial supervision is often introduced only during task-specific adaptation. Developing spatial understanding as a transferable foundation-model capability therefore calls for learning from broader robot experience. We present SLA, a Spatial-Language-Action Model that scales implicit spatial alignment to continual pre-training and maintains it during downstream post-training. Initialized from a pretrained pi05 policy, SLA jointly optimizes action prediction and alignment between intermediate visual embeddings and spatial representations from a frozen 3D perception model. We curate and unify heterogeneous robot datasets to support spatial learning across diverse embodiments, tasks, and scenes. To accommodate this diversity, we introduce feature-dependent gates that adaptively aggregate visual embeddings from multiple VLA layers for spatial supervision. The teacher further exploits partially available depth and camera calibration alongside RGB observations, enabling effective use of heterogeneous geometric annotations. Probabilistic state dropout encourages reliance on visual cues and mitigates overfitting to demonstration trajectories. All auxiliary components are used only during training, allowing direct reuse of pretrained VLA weights and preserving the original inference architecture.
We ask whether a model needs to hear the audio directly at all, and present SleuthVLM, an agent harness built on a VLM that never hears the audio directly: speech will be transcribed into text, and the VLM will sleuth the video on its own without any predefined workflow.
All ablations use SleuthVLM (Qwen3.8-27B) at medium effort (A0: the medium row of Table 1). Table 5 removes the transcript (A1: only the muted video and the question remain) or only its word times (A2)
Table 13 gives the audio_caption tool of Section 4.3 on the 448 questions about the music itself: the questions a benchmark labels as music tasks, and those whose text asks about music, melody, rhythm or instruments rather than lyrics. The model calls the tool on 84% of them, and accuracy rises from 48.9% to 58.7%
原文节选自动核对 · 2026-11-11 · 原论文与实验表 ↗ 自动核对论文 HTML 节选中的作者报告与原文引句；未独立复现。
原文完整摘要
Omni models answer questions about videos by jointly processing sampled frames and audio in one turn, with progress driven largely by scaling model size and omni training data. We ask whether a model needs to hear the audio directly at all, and present SleuthVLM, an agent harness built on a VLM that never hears the audio directly: speech will be transcribed into text, and the VLM will sleuth the video on its own without any predefined workflow. On four omni benchmarks with videos up to 90 minutes, SleuthVLM achieves the best average accuracy: \textbf{75.0%}, 2.6 points above Gemini 3.8 Flash, and it also tops the Video-MME-v2 leaderboard with \textbf{77.8%}; with an open-source 27B VLM, it beats all open-source omni models. We draw three findings: SleuthVLM beats a model that glances; hearing is not the bottleneck, agentic ability is; omni understanding needs better agentic ability, not just more omni data for modality alignment. So we provide a simple but effective starting point for doing omni video understanding. Omni understanding needs better agents, not just bigger models that hear.
Active speaker detection (ASD) relies on audiovisual correspondence between speech and visible faces, yet this correspondence becomes unreliable in crowded scenes, or when visual evidence is unavailable. We introduce ROAM-ASD-C and ROAM-ASD-CR to extend ROAM-ASD with contextual and identity-aware reasoning. ROAM-ASD-C jointly reasons across simultaneously visible candidates, allowing other faces to provide complementary evidence when the target observation is ambiguous or incomplete. ROAM-ASD-CR incorporates registered-speaker representations derived from enrollment speech, allowing detection of whether a speaker is active even when that speaker is not visually observed. ROAM-ASD-C achieves state-of-the-art performance across five ASD benchmarks: 96.8% mAP on AVA, 98.9% on WASD, 88.8% on UniTalk, 98.7% on Talkies, and 99.5% on ASW. It also improves ROAM-ASD by up to 13.3 mAP under 75% target-track visual removal.
This paper presents S2SND-v2, a unified online and offline speaker diarization framework built on S2SND that improves acoustic feature extraction and the use of the resulting representations. For acoustic feature extraction, we introduce a speaker-adapted w2v-BERT 2.0 front end and compare full and pruned construction routes. To better use these features, overlap-aware activity-query masking improves speaker embedding extraction under overlap, while late-speaker training aligns unknown-speaker training with online inference conditions. Combining these improvements, the pruned system achieves competitive average diarization error rates of 14.52% online and 12.03% offline across eight test sets.
Diarization-conditioned target-speaker ASR (TS-ASR), in particular Diarization-conditioned Whisper (DiCoW), is an accurate and data-efficient approach to multi-talker transcription. It has, however, three structural limitations: the model transcribes each speaker independently, operates on short (30 s) windows, and optimizes its diarization and TS-ASR components separately. We address the first two. We integrate the diarization conditioning into a longform Parakeet backbone (DiCoP) and add cross-speaker attention, which lets the model attend across the speaker dimension so that speakers are no longer decoded in isolation, and an STNO mask refiner that re-estimates the diarization-derived conditioning. As conversational data with genuine multi-speaker interaction is scarce, we scale training with a pseudo-labeling pipeline that mines 5.4k hours of in-the-wild multi-speaker audio from YODAS2. Combining these with synthetic and real data yields state-of-the-art results across several meeting benchmarks. We open-source the resulting models, DiCoP and Pandemonium, and the pseudo-labeled data.
AI 摘要提出TurnWise轮次级GRPO框架，通过静音补全前缀评分和轮次均值策略优化，分离单步动作的剩余回报并均衡输出权重，显著改善流式视频决策与冗余问题。
原文完整摘要
Streaming video understanding requires models to repeatedly decide whether to respond or continue observing. Recently, Group Relative Policy Optimization (GRPO) has been applied to this setting, with existing approaches emphasizing reward design while retaining a single trajectory-level advantage across turns. Such shared credit can reinforce redundant replies after earlier successes and discourage useful follow-ups after earlier failures. We propose TurnWise, a turn-level GRPO framework that aligns learning with individual streaming decisions. TurnWise addresses the mismatch between trajectory-level feedback and turn-level interaction, promoting informative responses and reducing redundancy. Specifically, turn-level credit assignment uses silence-completed prefix scoring to construct group-relative advantages from each decision's remaining return, separating its learning signal from earlier rewards. Turn-mean policy optimization averages token losses within each turn and then across turns, giving response and waiting decisions equal weight regardless of output length. These complementary designs improve streaming policy learning without a learned critic or additional rollouts. Extensive experiments show our method outperforms prior RL approaches for streaming video understanding.
数据、局限与查阅路线
Turns Matter: Advancing Streaming Video RL via Turn-Level Credit
It reasons adaptively , generating reasoning only when needed, reducing unnecessary token generation and conserving inference compute during routine driving.
Relative-position attention mechanisms offer compelling alternatives to RoPE across various transformer architectures, delivering superior performance in domains such as audio. These mechanisms typically modify attention scores by adding content-position or bias-position terms. Unlike RoPE, which encodes position via per-token rotations directly on the queries and keys, relative-position terms generally require pairwise offset-dependent computation or lookups, complicating their integration into fused attention kernels and introducing severe memory, bandwidth, and compute overheads as sequences scale. To address this bottleneck, we propose an exact attention algorithm that incorporates additive relative-position terms into FlashAttention-style tiled computation. Our method (1) uses offset-aware tiling to avoid redundant indexing and memory accesses, (2) computes only the necessary key/query-relation products and reuses them across token pairs in both forward and backward passes, and (3) uses offset-based gradient sharding and aggregation, eliminating atomic contention. We provide a unified, efficient Triton implementation across diverse relative-position attention mechanisms and evaluate it against naive and specialized implementations. For 8K-token sequences, our method speeds up the forward (backward) pass by 1.8-6.4$\times$ (2.0-21$\times$) and reduces peak memory up to 2.9-128$\times$ (1.4-54$\times$) over the strongest baseline for each mechanism, enabling long-context end-to-end transcription that is 1.8$\times$ faster and uses 2.4$\times$ less memory. Our method thus provides a drop-in, hardware-efficient solution for scaling relative-position attention transformers.
Confucius4-R2T2: A Stable-Prefix Streaming ASR Model for Real Real-Time Transcription
AI 摘要流式语音识别越来越多地被机器（例如翻译器和语音代理）所使用，这些机器在出现时对每个令牌进行操作。后来修改的令牌会导致浪费工作或错误操作。在这项工作中，我们提出了 Kongfz4-R2T2（Real Real-Time Transcription 的缩写），这是一种稳定前缀流式 ASR 模型，它从不修改其早期输出，同时保持高精度和低延迟。 R2T2是通过对Qwen3-ASR-1.7B在1500小时的中英文音频上进行后训练而获得的，同时冻结其预训练的音频编码器和投影仪。该适应基于最长稳定前缀（LSP）的概念，这是我们在这项工作中引入的一个新概念。我们证明LSP在前缀顺序下是单调的，与全音频输出一致，并且在等于整个早期输出的标签中最大。从 LSP 标签中学习可以将全上下文模型转换为稳定前缀流模型，而无需任何架构更改。广泛的评估表明，R2T2 使流式识别接近基本模型的全上下文质量，同时提供具有低发射延迟的稳定文本。
原文完整摘要
Streaming speech recognition is increasingly consumed by machines, such as translators and voice agents, that act on each token as it appears. A token that is later revised costs wasted work or a wrong action. In this work, we present Confucius4-R2T2 (short for Real Real-Time Transcription), a stable-prefix streaming ASR model that never modifies its earlier output while maintaining high accuracy and low latency. R2T2 is obtained by post-training Qwen3-ASR-1.7B on 1,500 hours of Chinese and English audio while freezing its pre-trained audio encoder and projector. The adaptation is based on the concept of Longest Stable Prefix (LSP), a new notion that we introduce in this work. We prove that LSP is monotone under the prefix order, consistent with the full-audio output, and maximal among labels that equal a whole earlier output. Learning from LSP labels converts a full-context model into a stable-prefix streaming one without any architectural change. Extensive evaluations show that R2T2 brings streaming recognition close to the base model's full-context quality while delivering stable text with low emission lag. Its gains extend beyond the post-training languages, demonstrating a practical path from full-context ASR to stable streaming. We open-source the model weights and code at https://huggingface.co/netease-youdao/Confucius4-R2T2 and https://github.com/netease-youdao/Confucius4-R2T2.
VidDub: Replacement-Aware Distillation for Two-Step Video Dubbing
AI 摘要视频配音旨在合成与目标语音匹配的嘴唇动作，同时保留源视频的说话者身份、头部姿势和背景。现有的编辑器主要是通过在原始配对音频下进行自我重建来进行训练的，尽管当驾驶语音被替换时，源嘴会成为冲突的目标。我们引入了替换感知的跨音频监督：配对音频样本使用全帧重建，而未配对的替换音频样本掩盖了源嘴重建损失，并仅通过视听同步来监督嘴，同时保留未掩盖的面部区域和背景。由于离线配音预先提供了完整的源视频和目标语音，因此我们推出了 VidDub，这是一个全上下文扩散编辑器，可简化为两个去噪步骤 (2 NFE)。我们具有替换意识的老师首先学习准确的嘴唇同步，而不会回归到冲突的源嘴部运动。然后，匹配轨迹回归将教师的 CFG 引导轨迹传输给两步学生，分布匹配蒸馏在步进压缩后恢复视觉质量。我们将发布精选的训练数据集、VidDub-Bench、固定的配对和跨音频评估清单、预处理输出和统一评估代码。
原文完整摘要
Video dubbing aims to synthesize lip movements that match target speech while preserving the speaker identity, head pose, and background of a source video. Existing editors are predominantly trained via self-reconstruction under original paired audio, even though the source mouth becomes a conflicting target when driving speech is replaced. We introduce replacement-aware cross-audio supervision: paired-audio samples use full-frame reconstruction, whereas unpaired replacement-audio samples mask out source-mouth reconstruction losses and supervise the mouth solely through audio-visual synchronization while preserving unmasked facial regions and background. Because offline dubbing provides the complete source video and target speech beforehand, we present VidDub, a full-context diffusion editor distilled into two denoising steps (2 NFE). Our replacement-aware teacher first learns accurate lip synchronization without regressing toward conflicting source mouth movements. Matched trajectory regression then transfers the teacher's CFG-guided trajectories to a two-step student, and distribution matching distillation recovers visual quality after step compression. We will release the curated training dataset, VidDub-Bench, fixed paired- and cross-audio evaluation manifests, preprocessing outputs, and unified evaluation code. Across three training seeds, masking out conflicting source-mouth reconstruction improves cross-audio Sync-C by 0.833; the final two-step model combines strong lip synchronization with superior visual quality, identity preservation, and visual speech recognition across four benchmarks.
Human-Centred, Risk-Constrained Evaluation of Financial Document Recognition: Evidence, Critical Errors, and Selective Automation
AI 摘要财务文档识别通常使用字符和单词错误率进行评估，尽管这些指标并不表示系统是否保留了人员和组织采取行动所依据的财务事实。本文开发了一个以人为本、风险约束的框架，用于评估作为证据恢复和决策支持的财务文件识别。它定义了与可见源区域相关的类型化财务事实，并将逐字转录、确定性标准化和业务解释分开。分层质量模型涵盖文本、本地化、布局、表格、字段、事实正确性、证据基础、不确定性、稳健性和操作性能。非补偿性验收门对关键字段错误使用单方面的不确定性界限，防止强大的总分掩盖数量、标识符、符号、周期或实体关联方面的失败。选择性自动化被表述为一个受约束的路由问题，该问题考虑了残余风险、人工审核能力和审核成本。该框架进一步规定了注释和裁决程序、防泄漏基准划分、统计估计、亚组分析和重现性卡。正式结果确定了补偿评分的局限性、零观察错误后的非零风险上限，以及用于将不确定案例路由至人工审核的损失敏感决策规则。
原文完整摘要
Financial document recognition is often assessed using character and word error rates, although these metrics do not express whether a system preserves the financial facts on which people and organisations act. This paper develops a human-centred, risk-constrained framework for evaluating financial document recognition as evidence recovery and decision support. It defines typed financial facts linked to visible source regions and separates verbatim transcription, deterministic normalization, and business interpretation. A layered quality model covers text, localization, layout, tables, fields, fact correctness, evidence grounding, uncertainty, robustness, and operational performance. Non-compensatory acceptance gates use one-sided uncertainty bounds for critical-field errors, preventing strong aggregate scores from masking failures in amounts, identifiers, signs, periods, or entity associations. Selective automation is formulated as a constrained routing problem that accounts for residual risk, human-review capacity, and review cost. The framework further specifies annotation and adjudication procedures, leakage-resistant benchmark partitions, statistical estimands, subgroup analyses, and a reproducibility card. Formal results establish the limitations of compensatory scoring, the non-zero upper risk bound after zero observed errors, and a loss sensitive decision rule for routing uncertain cases to human review. The contribution is theoretical and methodological; no new model, dataset, or empirical performance result is claimed.
A speech deepfake detector estimates whether a recording is synthetic, but a forensic analyst also asks which system produced it, whether recordings share a source, and what evidence supports each conclusion. We present VeriSpoof, an audio language model that unifies five tasks with shared weights: deepfake detection, generator attribution (generator, acoustic model and vocoder), recording-condition analysis, synthesized-span localisation, and source verification. Each decision is supported by grounded rationales whose statements can be independently verified. Answers are scored by sentence likelihood, allowing detection and source verification to be thresholded without separate heads. Rationale statements can be checked against waveform measurements, span labels, or generator metadata. Counterfactual examples train decisions to follow the stated evidence. Across the 14 Speech-DF-Arena test sets, VeriSpoof-Plus achieves 2.14% pooled EER, ranking third of 28 systems and first among open-weight systems. VeriSpoof-Base, trained only on official training splits of eight corpora, achieves 4.43% EER, less than half that of the next open-weight detector. With the same weights, VeriSpoof-Plus verifies whether recordings from generators unseen in training share a source at 6.2% EER. Controlled studies show that the audio representation governs detection, the LLM governs recording comparison, and source supervision is necessary for neural-codec fakes. Statement-checkable rationales catch partial fakes missed by one-step answers (99.6% vs. 78.4% on PartialEdit) and determine decisions under edits unseen in training (99.5%). Training updates only 29.7M of 2.85B parameters, fitting a single 24 GB GPU with gradient checkpointing. We release both models, inference code, a demo, and VeriSpoof-Bench, the evaluation suite covering these questions.
We introduce Sage-Taiyi, a metacognition-inspired architecture that uses accumulated scientific understanding to guide what to investigate next and how to investigate it. Through explicit monitoring and control, the system revises its understanding of evidence, assumptions, and unresolved questions, then uses these assessments to adapt research targets and select reusable reasoning methods. On Taiyi-Bench, an AI co-scientist ideation benchmark comprising 265 tasks from 50 papers across ten disciplines, Sage-Taiyi ranks first on all eight metrics of historical rediscovery and open-ended ideation, achieving an Overall score of 54.0 compared with 47.9 for the strongest baseline, AI Scientist-v2. It also performs well on two external scientific ideation benchmarks. Five expert-guided collaborations further connect its proposals to experimental and computational validation across chemistry, materials science, and engineering. In chemistry, reaction-condition optimization raises the yield of cobalt-catalyzed carbonylation from trace amounts to 84% and photocatalytic allylic amination from 13% to 69%. These results support metacognitive regulation as an approach to scientific ideation and its progression toward practical validation.
We introduce Sage-Taiyi, a metacognition-inspired architecture that uses accumulated scientific understanding to guide what to investigate next and how to investigate it. Through explicit monitoring and control, the system revises its understanding of evidence, assumptions, and unresolved questions, then uses these assessments to adapt research targets and select reusable reasoning methods.
On Taiyi-Bench, an AI co-scientist ideation benchmark comprising 265 tasks from 50 papers across ten disciplines, Sage-Taiyi ranks first on all eight metrics of historical rediscovery and open-ended ideation, achieving an Overall score of 54.0 compared with 47.9 for the strongest baseline, AI Scientist-v2.
In chemistry, reaction-condition optimization raises the yield of cobalt-catalyzed carbonylation from trace amounts to 84% and photocatalytic allylic amination from 13% to 69%.
In our research collaborations, this loop connects Sage-Taiyi’s candidate solutions and search formulations to experiments and simulations, with domain experts participating in idea selection and validation.
Models for physical AI tasks, such as robotics and autonomous driving, need not reason solely in language. They can use visual plans--points, bounding boxes, and trajectories--to represent spatial goals and anticipate motion. However, autoregressive vision-language models generate these plans one coordinate token at a time, making richer predictions increasingly costly. We introduce VFlash, a method for fast, accurate visual planning through Flash Primitive Decoding. VFlash exploits the known structure of visual primitives to predict their coordinates jointly, using a lightweight drafter that generates an entire primitive in one forward pass. The layout adapts to the primitive's type, dimensionality, and length, supporting compact boxes and long, variable-length trajectories. Crucially, spatial accuracy need not require reproducing an autoregressive model's exact token sequence. VFlash therefore trains on annotated primitives and directly accepts structurally valid predictions without target-token agreement. Across the evaluated 2D and 3D robot trajectory tasks, VFlash consistently reduces prediction errors relative to autoregressive decoding. Preliminary single-rollout measurements indicate approximately 25x faster generation for 3D point motion forecasting. A world action model conditioned on VFlash plans achieves 70.2% average success across four MolmoSpaces task suites, compared with 62.6% for the baseline.
We identify a key limitation of existing feed-forward 3DGS methods: Gaussian attributes are typically predicted in a radial-distance-normalized space that canonicalizes a global radial statistic of the reconstructed geometry, while the spacing between neighboring Gaussian centers can still vary substantially across scene scales and camera configurations. This mismatch induces systematic shifts in Gaussian-scale targets, leading to ambiguous supervision. To address this, we propose SplatAnything with Gaussian Spacing Normalization (GSNorm), which canonicalizes a robust scene-level statistic of Gaussian spacing to provide a more consistent spatial reference for Gaussian prediction. To rigorously assess our method, we further establish a systematic benchmark spanning diverse datasets, input sparsity levels, and challenging extrapolated viewpoints. Extensive experiments demonstrate that SplatAnything achieves state-of-the-art performance, with particularly strong gains under substantial variations in scene scale and viewpoint. Project page: https://zju3dv.github.io/SplatAnything
we propose SplatAnything with Gaussian Spacing Normalization (GSNorm), which canonicalizes a robust scene-level statistic of Gaussian spacing to provide a more consistent spatial reference for Gaussian prediction.
Table 1: Quantitative comparison across seven benchmark datasets, averaged over 4–64 input views. The top-3 results are highlighted as first, second, and third.
原文依据
We evaluate on seven datasets: ScanNet (Dai et al., 2017), NRGBD (Azinović et al., 2022), DL3DV (Ling et al., 2024), Tanks and Temples (Knapitsch et al., 2017), Mip-NeRF 360 (Barron et al., 2022), ETH3D (Schops et al., 2017), and DTU (Jensen et al., 2014).
边界依据
PSNR does not always faithfully reflect perceptual rendering quality, as it can favor overly smooth predictions that achieve low pixel-wise errors while losing high-frequency details.
From Pixels to Actions--Towards Native Vision-Language-Action Policies
AI 摘要提出无独立视觉编码器的NEO-VLA，直接由轻量卷积分块并与语言端到端联合计算，让动作专家利用不同深度的视觉演化特征，显著增强具身控制鲁棒性与精度。
原文完整摘要
Vision-language-action models are typically built on a simple premise: perception is first compressed by visual encoders, and action reasoning begins only afterwards. Yet manipulation often hinges on precisely the visual signals most vulnerable to this abstraction, e.g., local geometry, boundaries, depth, and subtle state changes. This raises a fundamental question: should action policies inherit a fixed visual endpoint, or directly access evolving visual computation? We introduce NEO-VLA, a structurally encoder-free vision-language-action framework. Images are tokenized by lightweight patch convolutional layers and evolve jointly with language throughout the backbone, allowing a flow-matching action expert to draw from instruction-conditioned visual representations at different depths. This simple change reveals a consistent pattern. Native architectures outperform encoder-based counterparts under controlled comparisons; full fine-tuning reduces but does not erase the gap, and additional scale alone cannot recover it. More strikingly, layer-wise probing shows that the action-critical signals often peak well before the final visual representation. Across diverse manipulation settings and distribution shifts, NEO-VLA consequently achieves stronger and more robust control. Together, these results suggest that embodied control benefits from access to visual representations across the computational hierarchy, rather than a fixed encoder output.
WorldFoundry: Towards Unified Infrastructure for World Intelligence
AI 摘要界定生成式世界模型标准并推出开源基础设施WorldFoundry，整合超270个模型与74个基准，规范多模态世界的运行时管理与可复现评估协议。
原文完整摘要
Visual generative models increasingly blur the line between synthesizing observations and simulating environments. Yet visual plausibility alone does not constitute successful world modeling: compelling outputs may lack persistent state, physical dynamics, or causally consistent responses to interactions. We define a generative world model as a predictive dynamical system that maintains a persistent, history-conditioned representation of an environment, updates that representation in response to actions or interventions, and generates temporally coherent trajectories that reflect outcomes under observed and counterfactual interventions. From this definition, we derive an intelligence-oriented framework spanning perceptual grounding, persistent state modeling, controllable transformation, dynamics-aware prediction, and closed-loop interaction. We present WorldFoundry, open-source infrastructure for reproducible inference and evaluation across video, 3D and 4D, embodied action, and interactive world systems. WorldFoundry unifies model and benchmark discovery, runtime and asset preparation, execution orchestration, artifact management, and interactive visualization, while modality-specific adapters preserve native inputs, execution semantics, output representations, and evaluation protocols. Explicit manifests, durable artifact contracts, and evidence-aware scorecards separate execution readiness from evaluative claims, making each claim traceable to its supporting artifacts. The catalog contains 270 model entries, 74 benchmarks, and 62 registered metric entries, with readiness and execution evidence recorded separately. WorldFoundry enables reproducible comparison of persistent, controllable dynamics across heterogeneous systems, advancing the field from perceptual synthesis toward measurable world intelligence.
AI 摘要提出A2-MEAS具身多智能体框架与A2-WLA动作模型，以代码为接口协同纠错与环境演化，在BEHAVIOR 2026等基准与真机长程任务中大幅提升了成功率与吞吐量。
原文完整摘要
Foundation models increasingly guide robot actions, yet sustained autonomy requires efficient control and failure recovery. We introduce A2-MEAS, an embodied multi-agent framework built around code as a scaling interface. Learned correction codes combine corrective language, spatial evidence, execution history, and action proposals. MetaBrain provides training supervision and runtime guidance. A correction encoder and adapter absorb this knowledge into policy weights during training, while fresh codes adapt behavior with frozen weights at deployment. The action model, A2-WLA, adds motion-aware history and a latent world model to a vision-language-action policy. Surprisingly, this simple design with action pretraining and task specialization reaches 0.5755 Q-score on the 50-task BEHAVIOR 2026 public subset before online correction, 2.21x the 2025 winner's reported 0.2605 across different benchmark editions and training configurations. On all 100 BEHAVIOR 2026 public tasks, A2-MEAS achieves 0.6411 Q-score and 45.40% task success. On RoboTwin 2.0, A2-WLA achieves 93.98% average success, rising to 95.05% with the complete system. Across 12 real-robot tasks in five household settings, A2-WLA achieves 57.92% average success versus 26.67% for pi0.5. In long-horizon pour-over coffee preparation, a history-conditioned adapter raises post-failure completion at two filter-handling steps from 14% to 94% and from 8% to 82%, compared with A2-WLA retries. Our training infrastructure delivers 427.1 samples per second, 4.03x the throughput of a pi0.5 reference implementation on matched hardware. We will release the system, models, training scripts, and infrastructure to support efficient embodied learning.
PCBRouteAgent: How Close Are LLM Agents to Becoming PCB Routing Engineers?
AI 摘要提出多模态PCB布线智能体PCBRouteAgent，将全局拓扑规划与局部底层执行解耦并引入结构化反馈重试，在PCBWorld-Bench真实板级测试集上取得领先的完全通过率。
原文完整摘要
Automating printed circuit board (PCB) routing requires coordinating board-level connectivity decisions with geometric execution under strict design rules. Although recent agents can interact with native routing tools, reliable routing on complex boards remains challenging. We present PCBRouteAgent, a multimodal PCB routing agent inspired by how human engineers coordinate global strategy with local execution. A Global Routing Planner combines board images and structured electrical and geometric information to specify connection topology, routing order, corridors, and layer transitions. A Detailed Routing Executor realizes these guides through KiCad's native routing engine and performs bounded local recovery. Unresolved failures are returned as structured feedback, enabling targeted guide revisions while preserving accepted routes. We evaluate PCBRouteAgent on 247 synthetic and real-world boards from four PCBWorld-Bench test splits. It achieves clean-pass rates of 100%, 94.9%, 100%, and 40% on D2, D3-A, D3-B, and D3-C, respectively. On the three real-world subsets, PCBRouteAgent outperforms the best evaluated baseline in clean-pass rate by 13.9, 36, and 10 percentage points, respectively.
Harness-S: Learning from Sibling Harnesses for Generalizable Agent Training
AI 摘要提出Harness-S框架，在基础执行系统失败时调用专用孪生工具套件进行挽救与经验回传，训练后策略可在原始环境下显著提升AppWorld等基准的泛化表现。
原文完整摘要
Harness evolution from a common base exhibits Locality, Complementarity, and Nonstationarity: variants repair different failures, and their utility changes as the policy learns. Rather than seeking a universally superior harness, we introduce Harness-S to selectively rescue failures of a base execution system through sibling harnesses and transfer the resulting capabilities into a single policy that remains effective under the original harness. Directional Harness Evolution develops specialized sibling harnesses along distinct repair directions, forming a reusable Sibling Harness Pool that remains fixed during policy training. Complementary Harness Rescue Training invokes this pool only when all initial attempts under the base harness fail. The same policy generates fresh rollouts under selected auxiliary harnesses, and these trajectories replace the failed group for reinforcement learning. An Adaptive Harness Router selects the Top-k variants using Harness Behavior Profiles and voting across multiple LLMs. Policy-aware profile re-anchoring refreshes this evidence as the policy learns. Across AppWorld, SWE-Gym, and DBBench, the trained policy substantially outperforms policy-only training when returned to the original base harness. Behavioral analyses and held-out cases support the transfer of harness-elicited behaviors into the policy itself. Reusing the router for Rank-1 inference provides additional gains at the same executor rollout count.
Learning Heterogeneous Tactile Representation for General Dexterous Manipulation
AI 摘要开发触觉基座模型LingBot-Touch，统一了压阻、磁性和视触觉等多模态传感器表征；可即插即用地接入各类具身策略，有效提升跨平台灵巧操作性能。
原文完整摘要
Tactile sensing is an indispensable modality for contact-rich dexterous manipulation, a capability that hints at the ultimate frontiers of embodied intelligence. However, commercially available tactile sensors are still at a relatively early stage of development, with each type of sensor offering irreplaceable strengths alongside its own drawbacks. A key challenge is thus to free tactile understanding from sensor-specific physics, so that embodied models can effectively leverage heterogeneous tactile data. To this end, we develop LingBot-Touch, a tactile foundation model characterized by the following properties. (i) Our model yields a unified representation across different tactile sensors (i.e., piezoresistive, magnetic, and visuotactile sensors), and is easily extensible to new sensor types. (ii) The resulting tactile tokens are plug-and-play: they can be seamlessly integrated into policy models across paradigms, from diffusion policy to vision-language-action (VLA) models such as $π_{0.5}$ and LingBot-VLA, consistently enhancing manipulation dexterity. (iii) Extensive experiments, spanning simulation and real-robot deployments across multiple hardware platforms, demonstrate that our tactile representation substantially benefits complex manipulation tasks while maintaining strong computational efficiency. We believe the findings in this work demonstrate the potential of leveraging cross-sensor data to scale tactile learning, and offer encouraging insights for the design of future hardware and embodied models.
WeLM-Image: A Unified Image Generation Model towards Visual Intelligence
AI 摘要推出统一文生图与编辑的WeLM-Image，采用混合Transformer与稀疏MoE架构支持单卡部署，在多项开源基准中取得领先，蒸馏版本可实现4.98秒快速推理。
原文完整摘要
We present \textbf{WeLM-Image}, a unified image foundation model that integrates multimodal understanding into text-to-image generation, instruction-guided editing, and multi-reference synthesis. Designed for single-GPU deployment in WeChat's large-scale consumer applications, the model processes text, reference images, and target latents as one interleaved sequence. A Mixture-of-Transformers (MoT) backbone combines shared attention with independent understanding and generation parameters to limit optimization interference. Equipping each path with Mixture-of-Experts (MoE) modules provides sparse capacity, with 31.7B stored parameters and approximately 5.4B generation parameters activated per target latent token. A generation-oriented data engine combines a knowledge-grounded visual vocabulary with large-scale visual clustering to balance semantic coverage and editing tasks, while training-time evaluation guides iterative data refinement. Bilingual annotations and verified editing supervision support progressive training up to native 1.5K resolution. We optimize generation and editing separately with rubric- and checklist-based rewards, then consolidate the specialized policies through noise-aware on-policy distillation. In the reported overall comparisons, the 1536-resolution model ranks first among the evaluated open-source models on PRISM-Bench, Qwen-Image-Bench, and UnicBench. MeanFlow-based few-step distillation yields WeLM-Image-Turbo, which generates a $1024\times1024$ image in 4.98\,s on a single NVIDIA H20 GPU using eight guidance-free steps.
TailSteer: Trajectory-Tail Steering for Drift-Resistant Multi-turn Image Editing
AI 摘要提出TailSteer后训练框架，在保持前期去噪动态的同时将内容保留校准集中在扩散轨迹尾部，无需成对数据即大幅缓解15至20轮连续编辑中的视觉累积漂移。
原文完整摘要
Strong single-turn editing performance does not guarantee reliable multi-turn interaction: as edited outputs are repeatedly reused, small unintended changes can accumulate into severe visual drift. This long-term drift is often mitigated through training on multi-turn data or cross-turn rollouts, potentially altering pretrained priors, or through specialized inference-time mechanisms that are difficult to scale to foundation models. We introduce TailSteer, a final-stage training framework that improves multi-turn robustness while retaining the generative and editing capabilities acquired through earlier training. TailSteer follows a simple principle: keep early denoising dynamics close to those of the base model and concentrate preservation corrections near the trajectory tail, where fine-grained deviations can be suppressed. These corrections are learned from the editor's own on-policy denoising rollouts, using unchanged source content as a preservation reference without requiring curated ground-truth editing pairs. Experiments across the FLUX, SenseNova, and Qwen families show that TailSteer substantially reduces cumulative drift over 15-20 editing turns while largely preserving base-model performance on extensive text-to-image and single-image editing benchmarks. These results demonstrate that long-horizon editing robustness can be unlocked in foundation models after TailSteer, rather than by relearning their existing capabilities.
GameVerse: A Minute-Scale Gameplay Dataset for Long-Horizon Interactive World Modeling
AI 摘要构建分钟级游戏交互视频数据集GameVerse，涵盖1655小时长视频与3.49亿帧，提供稳定的时序相机轨迹和事件级标注，显著拓展了交互式世界模型的生成时域。
原文完整摘要
Recent advances in interactive world models have made it possible to generate controllable, dynamic environments from action inputs. Yet current models struggle to maintain coherence beyond roughly one minute of rollout, a limitation rooted not in model capacity but in the scarcity of long-horizon training data. Existing gameplay video datasets typically consist of clips under ten seconds, with captions that describe whole clips in coarse and undifferentiated text, which is insufficient for controllable long-horizon generation. We address this with GameVerse, a minute-scale gameplay video dataset purpose-built for long-horizon interactive world modeling. GameVerse contains 69.7K clips spanning 1,655 hours and 349.6 million frames across diverse first- and third-person gameplay, including 1,358 hours of continuous two-minute sequences, an order of magnitude longer than prior datasets. Clips pass through a unified pipeline of scene-consistent segmentation, quality filtering, camera pose estimation, and event-based caption annotation. Each clip is paired with a temporally stable camera trajectory that remains coherent across minutes, together with captions that separate static scene context from dynamic foreground events and align to event boundaries rather than fixed time windows. Comprehensive analysis shows that GameVerse surpasses existing public datasets in scale, diversity, and annotation quality. Experiments further demonstrate that training on GameVerse substantially extends the temporal horizon of interactive world models.
Video-Coder: Reinforcing Agentic Coding for Video Generation
AI 摘要节选近年来，视频生成在视觉质量和时间一致性方面取得了显着进步。然而，生成具有精确空间结构、连贯运动动力学和可控场景组成的视频仍然具有挑战性。在本文中，我们介绍了 Video-Coder，这是训练代码驱动的视频生成代理的首次尝试，它自主编写和执行代码来构建动态 3D 场景（视频草稿），为下游视频生成器提供结构和运动信号。为了支持这种范例，我们设计了一个专用的数据管道，并策划了两个高质量的数据集：Video-Coder-SFT-6k 和 Video-Coder-RL-2k，其中包含不同的提示和真实参考视频。我们进一步开发了 VideoCoder Harness，这是一个集成了代码执行、3D 场景渲染以及用于代理训练和推理的执行反馈的统一交互环境。然后，我们使用 SFT 训练 Video-Coder，然后利用具有双重奖励反馈的原生代理强化学习，其中结合了基于执行的奖励和基于视频的奖励。
原文完整摘要
Recent years have witnessed remarkable progress in video generation in terms of visual quality and temporal consistency. However, generating videos with precise spatial structure, coherent motion dynamics, and controllable scene composition remains challenging. In this paper, we introduce Video-Coder, the first attempt to train a code-driven video generation agent, which autonomously writes and executes code to construct a dynamic 3D scene (Draft Video) that provides structure and motion signals to downstream video generators. To support this paradigm, we design a dedicated data pipeline and curate two high-quality datasets, Video-Coder-SFT-6k and Video-Coder-RL-2k, which contain diverse prompts and ground-truth reference videos. We further develop the Video- Coder Harness, a unified interactive environment integrating code execution, 3D scene rendering, and execution feedback for agent training and inference. We then train Video-Coder with SFT fol- lowed by harness-native agentic reinforcement learning with dual reward feedback, which combines execution-based and video-based rewards. Additionally, we design an annealing training strategy that gradually reduces the execution reward over time, allowing the model to rely more on the video reward in the later training stages. Experiments show that Video-Coder achieves significant gains, improving Minimax-H3 by approximately 7 points on PhyGenBench and 24 points on VBench-2.0. We hope this work can serve as an open foundation for coding agents in video generation, and we fully open-source our data, models, and code
From Autonomous Agents to Cognitive Symbionts: Toward AI-Augmented Human Intelligence
主要贡献把个人 AI 的设计目标从替人完成任务，转向帮助人理解、记忆和决策。文章整理了系统何时介入、记住什么、怎样保留用户控制权的设计问题。
关键亮点作者提出一个值得单独评估的问题：撤去 AI 后，用户是否保留了学到的能力？这是一份研究议程，未提供新系统的对照实验。
原文完整摘要
For a decade, progress in artificial intelligence has been measured by how much a machine can do on its own. Large foundation models now write code and run multistep tasks, and personal agents act on a person's behalf. Yet people still forget what they once knew, miss what they are not looking at, fail to find the right words, and face hard choices without the benefit of their own history, because the machine that could help stands outside the situation. As AI moves into the physical world, attention has settled on one kind of intelligent individual, the embodied robot; we argue that the era of Physical AI holds a second kind of equal importance, the person augmented by AI. Alongside artificial general intelligence, which asks how intelligent a machine can be, stands AI-augmented human intelligence (AHI), which asks how much intelligence a machine can enable in a particular person. Realizing it calls for a new kind of system, a cognitive symbiont: a lifelong, embedded, real-time, private, low-friction, and proactive companion that senses what the person senses through external devices, keeps their context across years, models their situation and their mind, takes part in their thinking at the right moment, carries out everyday tasks with their context, and keeps learning the person as both change. We give the paradigm a conceptual core, the cognitive gap between what a person could bring to a situation and what they can hold in working memory, and organize its design space as a symbiosis loop of sensing, keeping, understanding, living alongside, acting for and thinking with the person, and growing, enclosed by a personal runtime and by trust. Because a symbiont changes what a person can do in front of others, it also raises risks of a new kind, from covert assistance in examinations to pressure on everyone to adopt it, and we treat their governance as part of the paradigm.
P$^2$-MOPD: Accelerating Multi-Teacher On-Policy Distillation via Parameter Priors
AI 摘要提出P$^2$-MOPD方法，将多教师参数作为先验，并联合优化混合系数与可微学生模型参数，在多个领域下以一半的步数超越传统MOPD的最终平均恢复性能。
原文完整摘要
Multi-teacher on-policy distillation consolidates expert capabilities by supervising student-generated trajectories, whereas task arithmetic offers a training-free alternative through linear parameter combinations. We view the linear combination of student and expert parameters as a single differentiable model and propose P$^2$-MOPD, which jointly optimizes the mixing coefficients and the student weights under the same on-policy distillation objective. Unlike task arithmetic, which stays within the span of the frozen student and expert parameters for any choice of merging coefficients, P$^2$-MOPD keeps the student trainable, so the experts act as parameter priors without confining it to this span. Across four domains at 1.7B and 4B scales, P$^2$-MOPD achieves faster and more balanced recovery than MOPD from the same initialization, surpassing its final average recovery in half the training steps. At the end of training, our 1.7B model reaches 94.7% average recovery, versus 80.9% for MOPD.
A frontier AI model is trained in an AI data center, on tens of thousands of accelerators joined by a dedicated network, and every training step ends with all of them exchanging data at once. Between racks, that network is optical, and each of its four layers, from lasers to switches, runs a fixed or after-the-fact policy. Lasers sharing an enclosure, cooling, and power can fail together. At a fixed spare ratio, correlated failure provably caps a pool's availability however large it grows. In this paper, we present a comprehensive predictive control plane framework, called Halley, that reads each resource's next state and acts before the failure occurs. It has four components, each carrying a formal guarantee: LightReserve that sizes the laser pool to provide a coverage bound, FoldFit that schedules the switch within $11/9$ of the optimal, ThermaLead that holds a microring with one-step-ahead control, and TriageGuard that protects the highest-risk modules first. Halley gives each layer a predictive controller that defers to the deployed policy when unsure. Composed from simulations at that point, effective goodput, the share of ideal throughput kept, rises from 65.2\% to 76.5\% if a window that exhausts its spares is lost. If only the dark channels' bandwidth is lost, it reaches 67.4\%. Per megawatt, that is up to 1.03--1.17 times the training; for the same training, up to 3.3--14.7\% less data center capacity. \textsf{Halley}'s fallback circuits are formally verified and are shown to achieve close timing on a commercial FPGA, and pass a 130~nm signoff.
Protein engineering requires navigating rugged fitness landscapes, where small sequence changes can produce large functional differences, but experimental screening can only sample a small fraction of sequence space. Thus, a central challenge is to efficiently traverse the large combinatorial space of mutations in silico. We introduce ProTEUS, a mutation-resolved world model for closed-loop protein evolution. Pretrained on deep mutational scanning assays, ProTEUS learns a joint representation of sequence, evolutionary, and structural information using MutationFormer, a mutation-biased attention architecture. Variants are represented as states in this joint latent space, and mutations define actions whose functional consequences are predicted. To support exploration of many mutants, we developed a fast, physics-constrained all-atom predictor that utilizes explicit geometric constraint enforcement to achieve >10 fold increase in speed than AlphaFold3 with guaranteed physical validity. Lastly, ProTEUS refines its prediction and understanding of protein activity through closed loop experimental feedback to guide evolution toward a desired phenotype. ProTEUS surpasses established models in both zero-shot and supervised fine-tuning mutation prediction tasks. We experimentally demonstrate its utility in two closed-loop multi-objective engineering campaigns on aldehyde dehydrogenase and levansucrase, yielding variants with >10 fold higher activity than wild type. ProTEUS provides a world-model framework that connects virtual evaluation of mutational outcomes with experimental learning for efficient protein evolution.
ExRL: Sample-Efficient Online Adaptation of Long-Chunk Policies via Execution Length Control
AI 摘要预测长动作块（通常跨越数十个时间步）已成为功能日益强大的机器人策略的关键要素。在本文中，我们发现，由于要优化的动作块的高维性，用现有的强化学习（RL）方法来适应这些长块策略可能需要许多在线样本，这使得这种适应在交互数据收集成本高昂的现实场景中不切实际。我们的主要见解是将适应从优化操作转变为优化执行每个预测操作块的时间。这使得适应空间保持低维，同时其表现力随着块大小而增长。因此，我们引入了 Execution at the Right Length (ExRL)，这是一种简单的方法，它使用轻量级适配器来增强基本策略，该适配器可以预测每个块的执行长度，并使用离策略 RL 算法进行训练。在模拟基准和现实世界的机器人任务中，ExRL 能够以最少的特定于任务的超参数调整来对各种长块策略进行样本高效的适应。
原文完整摘要
Predicting long action chunks, often spanning dozens of timesteps, has become a key ingredient in increasingly capable robot policies. In this paper, we find that adapting these long-chunk policies with existing reinforcement learning (RL) methods can require many online samples due to the high dimensionality of the action chunks being optimized, making such adaptation impractical in real-world scenarios where interaction data are costly to collect. Our key insight is to shift adaptation from optimizing actions to optimizing how long to execute each predicted action chunk. This keeps the adaptation space low-dimensional while its expressivity grows with the chunk size. We thus introduce Execution at the Right Length (ExRL), a simple approach which augments the base policy with a lightweight adapter that predicts the execution length of each chunk and is trained using off-policy RL algorithms. Across simulation benchmarks and real-world robotic tasks, ExRL enables sample-efficient adaptation of a diverse range of long-chunk policies with minimal task-specific hyperparameter tuning.
Sparse attention cuts the cost of long-context inference by making the attention matrix sparse: each query attends only a subset of the sequence, chosen by a fixed pattern or, in recent production LLMs, learned per query. In DeepSeek Sparse Attention (DSA), the attention of DeepSeek-V3.2 and the GLM-5 family, every layer is preceded by a lightning indexer that scores the whole cache and keeps the k=2048 highest-scoring tokens for the layer to attend. At long context this indexer scan, not the sparse attention it feeds, is where the decode time goes. But adjacent layers select nearly the same tokens, so a layer can attend the selection of the previous indexer layer instead of its own. This removes the dependency: each indexer then runs concurrently with the attention of its layer. The resulting Multi-layer Indexer (MLI) needs no retraining and no new weights. Its default realization changes no kernel, running inside SGLang's production decode graph; an optional fused decode kernel accelerates it further on DeepSeek-V3.2. MLI composes with IndexCache (the cross-layer reuse GLM-5.2 ships as IndexShare): IndexCache drops the indexer from some layers, and MLI hides the scan on the rest. We serve DeepSeek-V3.2 and GLM-5 under IndexCache's protocol at retentions 1/2 to 1/32 (the fraction of layers that keep an indexer) and contexts 10K to 195K. At equal retention the composition decodes faster than IndexCache: up to 14.5% faster on DeepSeek-V3.2 and 9.8% on GLM-5 at 1/2, and 7.9% and 5.1% at 1/4, largest where IndexCache keeps the most indexers and growing with context. At retention 1/r it is faster still than IndexCache at 1/(2r) while keeping twice the fresh selections: at 128K it reaches 1.32x the unmodified model's decode throughput at 1/4, above IndexCache's 1.28x at 1/8. Its LongBench, RULER and LongBench v2 accuracy stays within a few percentage points of IndexCache's.
Market-Conditioned JEPA: Learning from Unpredictable Market Shocks
AI 摘要金融时间序列的大部分变化是由整个市场的冲击驱动的，而这些冲击无法从资产自身的历史中预测。每项资产的自我监督学习将这种变化视为不可减少的噪音。在潜在因素模型下，我们表明，对已实现的市场因素进行条件预测使得资产的市场暴露对于最佳预测是必要的，同时减少了学习特定资产组件的噪音。基于这一见解，我们引入了市场条件 JEPA (MC-JEPA)，这是一种针对金融时间序列的联合嵌入预测架构。在训练过程中，我们根据其他资产的未来目标嵌入为每项资产构建留一市场条件，并通过从资产自身表示派生的因子负载将其纳入其中。根据 11 年的分钟级中国 A 股数据，MC-JEPA 在回报、市场敞口、风险和流动性的九个目标上比单资产 JEPA 有所改善，其中在敞口、风险和流动性方面的收益最为强劲且具有统计显着性。它在所有流动性目标和两小时到五天的回报范围内实现了最佳 RankIC，优于时间序列基础模型和自我监督基线，并在历史回测中提供了最佳的投资组合表现。
原文完整摘要
Much of the variation in financial time series is driven by market-wide shocks that cannot be predicted from an asset's own history. Per-asset self-supervised learning treats this variation as irreducible noise. Under a latent factor model, we show that conditioning prediction on the realized market factor makes the asset's market exposure necessary for optimal prediction, while reducing the noise against which the asset-specific component is learned. Building on this insight, we introduce Market-Conditioned JEPA (MC-JEPA), a joint-embedding predictive architecture for financial time series. During training, we construct a leave-one-out market condition for each asset from the future target embeddings of other assets and incorporate it through factor loadings derived from the asset's own representation. On 11 years of minute-level Chinese A-share data, MC-JEPA improves over per-asset JEPA across nine targets spanning returns, market exposure, risk, and liquidity, with the strongest and most statistically significant gains in exposure, risk, and liquidity. It achieves the best RankIC on all liquidity targets and on return horizons from two hours to five days, outperforming time-series foundation models and self-supervised baselines, and delivers the best portfolio performance in a historical backtest. Ablations show that the return and exposure gains require the condition to be aligned with the realized market movement. After restoring the volatility scale removed by normalization, the predictor's factor loadings rank stocks by market beta nearly as well as a supervised probe, without labels. A synthetic factor-model study with known parameters shows that conditioning improves the recovery of both market exposure and the asset-specific component.
AI 摘要学习非线性动力系统的连续时间演化依赖于基于轨迹的目标，这需要在训练过程中模拟学习到的动力学并通过数值方案进行反向传播，其成本随着推出时间的推移而增长。我们表明，随着推出范围的增加，基于轨迹的目标会退化，从而阻碍基于梯度的优化，并且数值方案通过将学习的雅可比行列式的频谱限制在其绝对稳定区域，从而使学习的动力学产生偏差。为了克服这些限制，我们引入了速度匹配（VM），这是一种无需模拟的目标，依赖于分段线性插值和随机配置，并将采样步骤中的速度总体风险近似为二阶。我们开发了基于速度的学习的理论框架，引入了稳定性估计，可以根据速度误差控制轨迹误差，这使我们能够在深度神经网络对学习的速度场进行参数化时建立通用且连续时间的近似结果。
原文完整摘要
Learning the continuous-time evolution of nonlinear dynamical systems relies on trajectory-based objectives, which require simulating the learned dynamics during training and backpropagating through the numerical scheme, at a cost that grows with the rollout horizon. We show that trajectory-based objectives degenerate as the rollout horizon increases, hindering gradient-based optimization, and that the numerical scheme biases the learned dynamics by constraining the spectrum of the learned Jacobian to its absolute stability region. To overcome these limitations, we introduce Velocity Matching (VM), a simulation-free objective that relies on piecewise-linear interpolation and stochastic collocation, and approximates the velocity population risk to second order in the sampling step. We develop a theoretical framework for velocity-based learning, introducing stability estimates that control trajectory errors in terms of velocity errors, which enable us to establish universal and continuous-time approximation results when the learned velocity field is parameterized by deep neural networks. Building on a bias-variance decomposition of the VM objective, we show that its higher-order approximation of the velocity population risk yields a consistent minimizer; that it relates to the residual of an A-stable continuous-stage Runge-Kutta scheme, thus connecting VM to implicit integration without requiring any implicit solve; and that it implicitly matches the action of the learned Jacobian to that of the true one along the observed trajectories, without requiring access to the underlying velocity field or its Jacobian. Numerical experiments on nonlinear ordinary differential equations and semi-discretized time-dependent partial differential equations show that VM improves accuracy over trajectory-based objectives, while avoiding both the cost of simulation and the instabilities of long rollouts.