论文

提出 OmniScope，一个无需训练的 token 压缩框架，以 query 作为跨模态共享的语义锚点，并对音频与视频分别估计相关性；由此给出 OmniLLM 推理的简单设计原则：跨模态共享 query，但不共享显著性估计。This work proposes OmniScope, a training-free token compression framework that uses the query as a shared semantic anchor while estimating relevance separately for audio and video, and suggests a simple design principle for OmniLLM inference: share the query across modalities, but not the salience estimates.

研究发现收敛后的扩散损失与提示中结构化语言量成比例关系，并采用两个互补度量：白盒似然指标(GPG)与黑盒属性指标(ED)。Surprisingly, it is found that the converged diffusion loss scales with the amount of structured language in the prompt, and two complementary measures are adapted: a white-box likelihood metric (GPG) and a black-box attribute metric (ED).

本文为RGB-NIR低光成像提供新视角：通过引入3D感知神经建模，无需采集干净RGB数据，并能跨不同噪声水平泛化。This paper offers a new perspective for RGB-NIR low-light imaging by incorporating 3D-aware neural modeling, which obviates the requirement for clean RGB data collection, and generalizes across different noise levels.

提出一种自适应推理时引导框架，利用VLA Latents上的强化学习，发现推理时引导在成功与失败状态下遵循根本不同的scaling laws：动作多样性在基础VLA可能失败时最为有益，但在成功可能性高时可能不必要地扰动已准确的动作。This work introduces an adaptive inference-time steering framework that leverages Reinforcement Learning on VLA Latents, and discovers that inference-time steering follows fundamentally different scaling laws under success and failure states, revealing that action diversity is most beneficial when the base VLA is likely to fail, but can unnecessarily perturb already-accurate actions when success is likely.

研究发现privileged shifts无法给出可靠的答案对齐方向，其幅度主要反映反事实敏感性而非token级学习价值；提出Counterfactual Sensitivity Credit Reallocation (CSCR)，作为GRPO的简单扩展，降低高敏感token的credit并对token级优势重新归一化，同时保留原始credit预算与verifier确定的方向。These findings show that privileged shifts fail to provide reliable answer-aligned directions, while their magnitudes primarily reflect counterfactual sensitivity rather than token-level learning value, and propose Counterfactual Sensitivity Credit Reallocation (CSCR), a simple extension of GRPO that reduces credit for highly sensitive tokens and renormalizes token-level advantages to preserve both the original credit budget and verifier-determined direction.

本文提出 Motion Beyond Morphology（超越形态的运动）这一视角，旨在跨固定结构对应迁移运动，通过两阶段框架保留在不同目标形态间仍具有意义的动力学。This work introduces Motion Beyond Morphology, a perspective that seeks to transfer motion beyond fixed structural correspondence, by preserving dynamics that remain meaningful across different target morphologies by proposing a two-stage framework.

本文提出 3DZip，一种三阶段 token 压缩框架：首先采用粗粒度体素化去除点级冗余，再通过 Determinantal Point Process 基于特征空间多样性选取锚点 token，最后在空间约束下融合剩余 token 以保持几何一致性。3DZip is proposed, a three-stage token compression framework that first applies coarse voxelization to remove point-level redundancy, then selects anchor tokens based on feature-space diversity via a Determinantal Point Process, and finally merges remaining tokens under spatial constraints to preserve geometric coherence.

本文提出 LeapTalk，一种通过单次前向实现稳定且实时说话头生成、可扩展至任意长视频的新颖框架，并引入音频驱动的无分类器引导机制，在极端步数缩减下保持细粒度唇形同步。LeapTalk is proposed, a novel framework that achieves stable and real-time talking-head generation with a single forward step, scaling to arbitrarily long videos, and an audio-driven classifier-free guidance mechanism to maintain fine-grained lip synchronization under extreme step reduction.

本文提出 DeepVoyager-VL，一种面向视觉在环搜索的长程多模态深度搜索框架，通过构建多模态事件图驱动数据合成，从而产出具有中间视觉依赖与长推理链的问题。DeepVoyager-VL is proposed, a long-horizon multimodal deep-search framework for vision-in-the-loop search that constructs a multimodal event graph to drive data synthesis, yielding problems with intermediate visual dependencies and long reasoning chains.

本文提出 DreamTraj，从单张 RGB 图像和任务指令预测物体 6-DoF 轨迹，推理时无需视频、深度或 CAD 模型，是首个直接从中间视频扩散表征（而非生成像素）解码物体 6-DoF 轨迹的方法This work proposes DreamTraj, which predicts a 6-DoF object trajectory from a single RGB image and a task instruction, requiring no video, depth, or CAD model at inference, and is the first approach to directly decode object 6-DoF trajectories from intermediate video diffusion representations rather than generated pixels.

在四种拆分 backbone 上，ReBA 降低所有报告 benchmark 输入的负载，同时保持与 Std-Aux 相当的平均任务准确率，并在分辨率与分块变化下降低测试范围内的平均负载与最差物理负载Across four split backbones, ReBA lowers load on every reported benchmark input while keeping mean task accuracy comparable to Std-Aux, and lowers average load over the tested range and worst physical load under resolution and tiling shifts.

本文在中间层附加轻量预测头，保持 backbone 冻结，并利用中间预测与最终预测的差异作为采样时的自引导方向，训练一个能够自引导的冻结预训练像素扩散模型This work attaches a lightweight prediction head to an intermediate layer, keep the backbone frozen, and use the discrepancy between the intermediate and final predictions as a self-guidance direction during sampling to train a frozen, pretrained pixel diffusion model that can guide itself.

一种模型无关的模态失败框架，仅依赖部署可观察信号，返回逐样本失败分类、逐模态互补矩阵（将错误归因到模态）以及响亮 vs 静默 dropout 画像（区分可监控失败与远离决策边界未被标记的失败）A model-agnostic modality-failure framework that returns a per-example failure taxonomy, a per-modality complementarity matrix that attributes error to modalities, and a loud-vs-silent dropout profile separating monitorable failures from those that pass unflagged far from the decision boundary, using only deployment-observable signals.

在作者研究的粗粒度属性上，MLLM 编码了视觉证据但无法可靠控制对其的依赖For the coarse attributes the authors study, MLLMs encode the visual evidence but cannot reliably control their reliance on it, indicating that for the coarse attributes they study, MLLMs cannot reliably control their reliance on it.

提出 Video-DR，采用解耦的感知-探索流水线与分阶段工具解锁，强制在 web 检索前进行充分的跨帧视觉定位，实现突破模仿学习上限的自主探索。Video-DR is introduced, featuring a decoupled perception-exploration pipeline with stage-wise tool unlocking that compels exhaustive cross-frame visual grounding prior to web retrieval, enabling autonomous exploration that breaks the imitation-learning ceiling.

提出 V2N (Video to Notes)，首个完整的 VPT 系统：共享时序 backbone 驱动 onset、offset、key hold、velocity 等任务专属 head，采用逐帧监督而非仅在窗口中心进行联合训练。This work presents V2N (Video to Notes), the first complete VPT system: a shared temporal backbone feeds task-specific heads for onset, offset, key hold, and velocity, jointly trained with per-frame supervision rather than only at the window center.

提出 MiniWorld，一个从零训练流式视频世界模型的可复现框架，采用 chunk-wise 非递减噪声调度与两阶段继续训练，提升时间建模与稳定性，将促进未来视频世界模型的研究。MiniWorld is presented, a reproducible framework for training streaming video world models from scratch that adopts a chunk-wise non-decreasing noise schedule and two-stage continued training to improve temporal modeling and stability and will facilitate future research on video world modeling.

为人体动作识别引入新问题域：基于标准 RGB 视频对儿童步态行为进行细粒度分析，并描述一个统一的端到端框架用于解码儿科步态的基本组成。This work introduces a new problem domain for human action recognition: the fine-grained analysis of children's gait behaviors from standard RGB video, and describes a unified end-to-end framework for decoding fundamental components of pediatric gait.

在视觉问答与视觉定位任务上对多模态紧凑双线性池化（MCB）进行了广泛评测，结果一致表明 MCB 优于去掉 MCB 的消融版本This work extensively evaluates Multimodal Compact Bilinear pooling (MCB) on the visual question answering and grounding tasks and consistently shows the benefit of MCB over ablations without MCB.

提出 WorldCycle，一种自验证 RL 框架，从普通动作序列中构建闭合动作循环及其重复执行，并优化两个互补奖励：空间闭合奖励（强制镜像的前向与反向片段之间的对称性）以及时间一致性奖励（对齐多次循环执行间的状态）。WorldCycle is introduced, a self-verifiable RL framework that constructs closed action cycles and their repeated executions from ordinary action sequences, and optimizes two complementary rewards: a spatial closure reward enforcing symmetry between mirrored forward and reverse segments, and a temporal consistency reward aligning states across repeated cycle executions.

在 BridgeVLA 基础上开发 BridgeVLA++，引入统一的时空记忆架构，建模持久化的空间上下文与时间交互历史，使其可在保留 BridgeVLA 数据效率与泛化能力的同时对观测历史进行推理。BridgeVLA++ is developed by equipping BridgeVLA with a unified spatio-temporal memory architecture that models persistent spatial context and temporal interaction history that can reason over observation histories while preserving BridgeVLA's data efficiency and generalization capabilities.

提出 RSTG（Recovering Learning Signals via Adaptive Teacher Guidance），在最关键的位置选择性地、精确地施加蒸馏，显著优于朴素的 GRPO+OPD。RSTG (Recovering Learning Signals via Adaptive Teacher Guidance), which applies distillation selectively and precisely where it matters most, and substantially outperforms naive GRPO+OPD.

提出 AVE-Agent，一种模块化 agent 框架，将复杂指令分解为相互依赖的子任务，并通过自我反思与评估器反馈迭代改进编辑结果，在联合编辑中提升指令执行、保真度保持以及音视频对齐，同时保持有竞争力的感知质量。AVE-Agent is proposed, a modular agent framework that decomposes complex instructions into dependent subtasks and iteratively improves editing results through self-reflection and evaluator feedback, and improves instruction execution, Fidelity Preserving, and audio-visual alignment in joint editing while maintaining competitive perceptual quality.

提出 CoCoEvolve，通过定义显式的一一对应关系，并利用表征间的一致性优化模型，在无需额外标注的前提下提升图表、表格与代码表征之间的跨模态一致性。This work introduces CoCoEvolve, a method to improve consistency across chart, table, and code representations by defining explicit one-to-one correspondences and optimizing models using agreement between representations, without additional annotations.

提出 DRIFT（Denoising Redirection via Input perturbation of the Flow-matching Trajectory），一种测试期通用对抗补丁，贴在机器人夹爪上，针对现成策略的去噪速度场进行攻击。This work introduces DRIFT (Denoising Redirection via Input perturbation of the Flow-matching Trajectory), a test-time universal adversarial patch placed on the robot's gripper that attacks the denoising velocity field of an off-the-shelf policy.

文章论证了 Transformers 可作为医学图像分割任务的强大编码器，并通过与 U-Net 结合，恢复了局部空间信息以增强更精细的细节。It is argued that Transformers can serve as strong encoders for medical image segmentation tasks, with the combination of U-Net to enhance finer details by recovering localized spatial information.

文章提出了 SegFormer，一个简单高效且强大的语义分割框架，将 Transformers 与轻量级 MLP 解码器统一，并在 Cityscapes-C 上展示了出色的零样本鲁棒性。SegFormer is presented, a simple, efficient yet powerful semantic segmentation framework which unifies Transformers with lightweight multilayer perception (MLP) decoders and shows excellent zero-shot robustness on Cityscapes-C.

分析表明，VisualBERT 能够在无任何显式监督的情况下将语言元素对应到图像区域，甚至对句法关系敏感，例如能够跟踪动词与其论元对应图像区域之间的关联。Analysis demonstrates that VisualBERT can ground elements of language to image regions without any explicit supervision and is even sensitive to syntactic relationships, tracking, for example, associations between verbs and image regions corresponding to their arguments.

在输入和输出直接进行 4 倍下采样与上采样的设定下，实验表明，基于纯 Transformer 的 U 形编码器-解码器网络优于完全卷积或 Transformer 与卷积相结合的方法。Under the direct down-sampling and up-sampled of the inputs and outputs by 4x, experiments demonstrate that the pure Transformer-based U-shaped Encoder-Decoder network outperforms those methods with full Convolution or the combination of transformer and convolution.

BLIP 通过引导式 caption 方式有效利用含噪网络数据，由 captioner 生成合成 caption，并由 filter 去除噪声样本；在以零样本方式直接迁移到视频-语言任务时，展现出强大的泛化能力。BLIP effectively utilizes the noisy web data by bootstrapping the captions, where a captioner generates synthetic captions and a filter removes the noisy ones, and demonstrates strong generalization ability when directly transferred to video-language tasks in a zero-shot manner.

本文提出了首个用于睡眠阶段分类的深度学习方法，无需计算频谱图或提取手工特征即可端到端学习，利用了全部多变量多模态 PSG 信号（EEG、EMG、EOG），并能利用每个 30 秒窗口数据的时序上下文。This work introduces here the first deep learning approach for sleep stage classification that learns end-to-end without computing spectrograms or extracting handcrafted features, that exploits all multivariate and multimodal polysomnography (PSG) signals (EEG, EMG, and EOG), and that can exploit the temporal context of each 30-s window of data.

这些结果将视觉地理定位确立为场景文本仲裁的连续诊断手段，并提供了一个受控框架，用于评估 MLLMs 如何解决冲突的多模态证据。These results establish visual geolocation as a continuous diagnostic of scene-text arbitration and provide a controlled framework for evaluating how MLLMs resolve conflicting multimodal evidence.

PaDoc 是一个布局驱动的解析器，将预测布局视为共享页面表示上的分支结构，在五个并发级别下均为最快的 end-to-end 解析器。PaDoc is proposed, a layout-grounded parser that treats the predicted layout as a branching structure over a shared page representation that is the fastest end-to-end parser at five concurrency levels and is the fastest end-to-end parser at five concurrency levels.

EffectLearner 是一个语义推理增强框架，结合基于 VLM 的 Object-Effect Reasoner 与基于 DiT 的 Video Eraser，在 EffectWorld-Eval 和具有挑战性的 EffectWorld-Wild 上均取得明显优势，证明其能在复杂真实场景中实现高质量的视频物体擦除。EffectLearner is proposed, a semantic-reasoning-enhanced framework that combines a VLM-based Object-Effect Reasoner with a DiT-based Video Eraser that achieves clear advantages on both EffectWorld-Eval and the challenging EffectWorld-Wild, demonstrating its ability to deliver high-quality video object removal in complex real-world scenes.

World-to-Wrist VLA (W2-VLA) 是一个用于细粒度机器人操作的 VLA 模型，具备任务条件下的未来腕部建模；W2-CoT 是一个合成流水线，生成描述操作进度、物理过渡线索和腕部局部证据的结构化标注。World-to-Wrist VLA (W2-VLA), a VLA model for fine-grained robot manipulation with task-conditioned future wrist modeling, and W2-CoT, a synthesis pipeline that produces structured annotations describing manipulation progress, physical transition cues, and wrist-local evidence.

SmartMage 是一个统一的 MLLM，动态调度异构模态以实现语义感知的 3D 场景理解，在五个 3D 场景理解基准上达到 SOTA，并在仅 RGB 视频理解基准上取得具有竞争力的结果。SmartMage is proposed, a unified MLLM that dynamically orchestrates heterogeneous modalities for semantic-aware 3D scene understanding and achieves state-of-the-art performance across five 3D scene understanding benchmarks, and attains competitive results on RGB-only video understanding benchmarks.