arXiv Computer Vision September 22, 2026 By Yu-Ho Chang, Chi-Hsi Kung, Yi-Hsuan Tsai, Yi-Ting Chen

Action-Slot: Structured Action-Centric Representation Learning for Multi-Agent Atomic Activity Understanding

Read the original on arXiv Computer Vision →

The paper introduces Action‑Slot, a structured action‑centric representation learning framework for multi‑agent atomic activity understanding. It reformulates slot attention into activity‑aligned slots, parallel spatio‑temporal updates, and background regularization to disentangle concurrent, asynchronous activities directly from raw video. Additionally, an attention‑difference pseudo‑mask method enables weakly supervised localization, and a new synthetic dataset, TACO, provides balanced atomic activity coverage with pixel‑level annotations.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv Machine Learning

Jul 2

Local Motion Matters: A Deconstruct-Recompose Paradigm for Reinforcement Learning Pre-training from Videos

arXiv:2607. 00808v1 Announce Type: new Abstract: Pre-training on large-scale videos to improve reinforcement learning efficiency is promising yet remains challenging.

By Jinwen Wang, Youfang Lin, Xiaobo Hu, Shuo Wang, Kai Lv

agents reinforcement-learning robotics

arXiv AI

Jul 7

Token-Based Affordance Grounding with Large Vision-Language Models

arXiv:2607. 03595v1 Announce Type: cross Abstract: Affordance grounding aims to localize image regions that support a specific action, serving as a core capability for physical intelligence and embodied perception.

By Seung Il Lee, Qinqian Lei, Daguang Xu, Dong Yang, Robby T. Tan, Yixin Chen, Bo Wang

llms robotics multimodal benchmarks

arXiv AI

Aug 13

Glance, Scrutinize, and Think: Advancing Video Anomaly Detection from Training-Free to Agentic Reasoning

arXiv:2608. 11260v1 Announce Type: new Abstract: Video Anomaly Detection (VAD) aims to identify anomalous events and localize their temporal intervals.

By Shibo Gao, Peipei Yang, Xu-Yao Zhang, Linlin Huang

llms agents reinforcement-learning fine-tuning multimodal benchmarks safety

Hugging Face Trending Papers

Jun 1

WALL-WM: Carving World Action Modeling at the Event Joints

WALL-WM is a World Action Model that shifts video-action learning from chunk-centric optimization to event-grounded Vision-Language-Action pretraining, using semantically coherent action events as the atomic unit of learning. Existing WAMs commonly initialize from multimodal or video foundation models and then optimize fixed-length action chunks conditioned directly on the current observation and instruction.

multimodal benchmarks

arXiv AI

6d ago

CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating

The paper introduces CaC, a coarse‑to‑fine anomaly reward model that uses Vision‑Language Models to first scan globally for anomalous time windows, then ground anomalies spatially, and finally reason with structured spatiotemporal Chain‑of‑Thought. It builds the first large‑scale generated video anomaly dataset with detailed annotations and trains the model through a three‑stage progressive paradigm, including reinforcement learning with Group Relative Policy Optimization. Experiments show CaC improves fine‑grained anomaly detection by 25.7% and reduces generated‑video anomalies by 11.7% while enhancing overall video quality.

By Jiyuan Wang, Huan Ouyang, Jiuzhou Lin, Chunyu Lin, Dewen Fan, Boheng Zhang, Haonan Fan, Honglie Wang, Yiyang Fan, Zhenlong Yuan, Zijun Li, Yongrui Heng, Guosheng Lin, Fan Yang

llms reinforcement-learning fine-tuning multimodal benchmarks

arXiv Computer Vision

Aug 21

SportsGrounder: Proposal-Aided Interleaved Grounding for Dense Sports Video Reasoning

arXiv:2608. 07932v2 Announce Type: replace Abstract: Sports video analysis is crucial for athletic analytics and broadcasting enhancement.

By Yizhi Li, Jiawei Jiang, Guanhong Wang, Yingcai Wu, Gaoang Wang

multimodal benchmarks safety

One email a morning, machine-written

Related stories

Local Motion Matters: A Deconstruct-Recompose Paradigm for Reinforcement Learning Pre-training from Videos

Token-Based Affordance Grounding with Large Vision-Language Models

Glance, Scrutinize, and Think: Advancing Video Anomaly Detection from Training-Free to Agentic Reasoning

WALL-WM: Carving World Action Modeling at the Event Joints

CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating

SportsGrounder: Proposal-Aided Interleaved Grounding for Dense Sports Video Reasoning