arXiv:2603. 09731v3 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) are increasingly considered as a foundation for embodied agents, yet it remains unclear whether they can reliably reason about the long-term physical consequences of actions from an egocentric viewpoint.
arXiv:2609.39378v1 Announce Type: new Abstract: Real-world embodied tasks, from everyday activities to professional procedures, require agents to act under physical constraints while tracking evolvin...
arXiv:2606. 07433v1 Announce Type: cross Abstract: Video understanding is being rapidly transformed by multimodal large language models (MLLMs), as research moves from short clips to long, multimodal, and knowledge-intensive video scenarios.
arXiv:2610.18499v1 Announce Type: cross Abstract: Egocentric video understanding spans diverse capabilities, modalities, and evaluation formats, yet these are often studied in isolation despite their...
HUG‑VIS is a unified multimodal benchmark for human‑centered visual intelligence, comprising 8,400 half‑body videos of 30 professional actors performing 280 emotion‑action prompts in Mandarin. The dataset provides synchronized video, audio, text, and alpha mattes for four tasks—human emotion recognition, video generation, voice cloning, and video matting—allowing evaluation of both open‑ and closed‑source models under a zero‑shot protocol. Results reveal that linguistic cues dominate emotion recognition, visual affect is weakest, and that automatic metrics and human judgments diverge in generation and cloning tasks, while motion‑related boundary fidelity remains a key challenge for matting.
The paper introduces RoboJudge, a multimodal language model trained to evaluate embodied video generation. It presents RoboJudge-Bench, a benchmark of 800 human‑annotated videos assessing Physical Adherence and Instruction Alignment, and RoboJudge-Train, a 12K‑video dataset with human‑verified scores and rationales. Fine‑tuned on this data, RoboJudge‑9B achieves the highest agreement with human judgments, outperforming existing models and improving performance on external physics benchmarks.
SYNCR is a synthetic benchmark designed to evaluate multimodal large language models on cross‑video reasoning. It contains 4,000 question‑answer pairs across 4,827 unique videos, covering tasks in temporal alignment, spatial tracking, comparative reasoning, and holistic synthesis. The benchmark reveals a significant performance gap between current models and humans, with models excelling at temporal ordering but struggling with precise physical and spatial reasoning.
Video generation models are promising foundations for embodied world models, but only if their generated rollouts are physically valid and faithful to task instructions. Multimodal large language mode...
arXiv:2607. 02680v1 Announce Type: cross Abstract: MLLMs have shown strong zero-shot capabilities across diverse inputs such as across images, video, audio, and text.
arXiv:2606. 31127v1 Announce Type: cross Abstract: To enable personalized, real-time coaching using Augmented Reality glasses or fixed camera setups in domains such as sports, cooking, or music, a system must understand not just what a person does, but how well they execute an activity.
arXiv:2608.21022v1 Announce Type: new Abstract: Micro-actions are subtle, short, low-amplitude body movements, such as a fidgeting hand or a slight head tilt, that humans perform with little consciou...
arXiv:2607. 16322v1 Announce Type: cross Abstract: Micro-gesture recognition demands the detection of fleeting, spatially localized movements that are frequently overwhelmed by dominant static appearances and background noise.