arXiv Computer Vision

Test-time Reinforcement Learning for Anomalous Video Understanding

The paper introduces a test‑time reinforcement learning framework for anomalous video understanding, addressing challenges such as unreliable pseudo‑labels, inadequate reward design, and collapsed group‑relative advantages. It proposes dual‑query consistency filtering, an entropy‑aware consensus reward, and a virtual negative anchor mechanism to improve sample reliability, reward quality, and policy‑gradient signals. Experiments on VAU‑Bench demonstrate significant performance gains, especially on the ECVA subset where accuracy rises from 75.81% to 90.00%.

arXiv AI
Sep 28

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
arXiv AI
Oct 2

Cog-VADU: A Training-Free Cognitive Reasoning Framework for Video Anomaly Detection and Understanding

Cog-VADU is a training‑free framework that transforms video anomaly detection into a sequential cognitive reasoning task. It uses Chain‑of‑Anomaly Detection Thought Prompting (CoADTP) to create a recurrent reasoning chain across video segments, preserving temporal memory and distinguishing complex anomalies from high‑motion normal activities. A cross‑modal re‑ranking stage aligns textual rationales with visual embeddings to enforce semantic consistency and temporal coherence, yielding competitive zero‑shot performance on multiple VAD benchmarks.

By Mohd Ubaid Wani, Sara Atito, Josef Kittler, Muhammad Awais
arXiv Machine Learning
Aug 31

Post-Training VLMs for Video Mistake Detection

The paper introduces a new protocol, Mistake Detection Video Question Answering (MD‑VQA), to evaluate whether models can determine if a step in a video follows its description, covering both seen and unseen actions. It proposes a post‑training approach for video‑language models that uses a reward function to highlight discrepancies between instructions and video content. Experiments show this method surpasses zero‑shot, fine‑tuned, and other post‑training baselines, especially on unseen procedures, improving performance by up to 11.6% on EP‑VQA.

By Federico Spurio, Olga Zatsarynna, Lars Doorenbos, Emad Bahrami, Gianpiero Francesca, Juergen Gall
arXiv Computer Vision
Sep 16

Probe-VAD: Ordinal Likelihood Probing for Training-Free Video Anomaly Detection

Probe‑VAD introduces an ordinal binary‑probing framework that leverages frozen vision‑language models for training‑free video anomaly detection. By querying ten ordered severity thresholds and extracting YES/NO continuation likelihoods, it builds a cumulative severity profile that is converted into a continuous anomaly score with isotonic projection for ordinal consistency. Experiments on public benchmarks show that this simple interface yields superior performance at low computational cost, avoiding the limitations of caption‑based compression or restricted numerical scoring.

By Jiawei Gu, Qilin Zhao, Tengkuo Guo, Zhiming Zhong, Shuangqing Zhang, Fan Lyu, Fang Zhao, Guo-Sen Xie, Caifeng Shan
arXiv Computer Vision
Oct 23

What Do Verifiable Rewards Teach Video-Language Models About Time? A Controlled Multi-Model Study

The paper investigates how reinforcement learning from verifiable rewards (RLVR) affects video‑language models’ understanding of time. Four open models were fine‑tuned under different data recipes—verified synthetic questions, unverified self‑supervised tasks, a 1:1 mix, and a verified+real mix—and evaluated on in‑domain and out‑of‑domain real‑video benchmarks with frames ordered, shuffled, or absent. Results show that verified training boosts in‑domain accuracy, largely through non‑visual gains, but can severely harm out‑of‑domain performance unless real verified data is added; moreover, no recipe induces genuine temporal‑order grounding, indicating that verifiable rewards improve benchmark scores without teaching temporal understanding.

By Avyay Sadhu, Patrick Cooper
arXiv AI
Jul 24

TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics

arXiv:2602. 19313v2 Announce Type: replace-cross Abstract: General-purpose robot learning requires dense, instruction-conditioned feedback that can distinguish meaningful task progress from stalled, failed, or partially completed behavior.

By Shirui Chen, Cole Harrison, Ying-Chun Lee, Angela Jin Yang, Zhongzheng Ren, Lillian J. Ratliff, Jiafei Duan, Dieter Fox, Ranjay Krishna