arXiv Computer Vision

WorldReward: Reward Modeling for Camera-Conditioned World Models

WorldReward introduces a vision‑language model–based reward system for camera‑conditioned world models, combining action consistency and visual quality evaluation. It processes paired videos by splitting them into action‑aligned chunks, structuring visual evidence, and aggregating decisions through voting. The model is trained on a large, reasoning‑augmented preference dataset and outperforms GPT‑5.5 on a human‑annotated benchmark, improving both action execution and visual quality when applied to RL post‑training.

arXiv Computer Vision
Sep 10

VideoTIR: Accurate Understanding for Long Videos with Efficient Tool-Integrated Reasoning

VideoTIR introduces a reinforcement‑learning approach to improve long‑video understanding by encouraging multimodal large language models to use comprehensive multi‑level toolkits efficiently. It combines Zero‑RL and SFT cold‑starting strategies to help models retrieve and focus on meaningful video segments, images, and regions, thereby reducing hallucinations. The method includes Toolkit Action Grouped Policy Optimization (TAGPO) to streamline tool‑calling and a sandbox‑based trajectory synthesis framework for high‑quality data, achieving strong results on three long‑video QA benchmarks.

By Zhe Gao, Shiyu Shen, Taifeng Chai, Weinong Wang, Haotian Xu, Xing Wu, Wenbin Li, Qi Fan, Yang Gao, Dacheng Tao
arXiv Computer Vision
Aug 27

PreResQ-R1: Response-Preference Disentangled Ranking-and-Scoring Reinforcement Optimization for Robust Visual Quality Assessment

PreResQ‑R1 introduces a Preference‑Response Disentangled Reinforcement Learning framework for Visual Quality Assessment that jointly optimizes absolute score regression and relative ranking consistency. It employs a dual‑branch reward system—modeling intra‑sample response coherence and inter‑sample preference alignment—trained with Group Relative Policy Optimization. The method extends to video quality assessment via a global‑temporal and local‑spatial data flow strategy, achieving state‑of‑the‑art results on 10 IQA and 5 VQA benchmarks with only 6K images and 28K videos, and provides human‑aligned reasoning traces.

By Zehui Feng, Weichuan Wang, Xiaohan Chen, Ting Han
arXiv Computer Vision
Sep 7

Persistent Robot World Models: Stabilizing Multi-Step Rollouts via Reinforcement Learning

The paper introduces a reinforcement learning post‑training scheme that trains robot world models on their own autoregressive rollouts, using a contrastive RL objective adapted from diffusion models. It also proposes a training protocol that compares multiple variable‑length futures, a multi‑view visual fidelity reward, and demonstrates state‑of‑the‑art rollout fidelity on the DROID dataset, outperforming baselines on LPIPS, SSIM, and human preference tests.

By Jai Bardhan, Patrik Drozdik, Josef Sivic, Vladimir Petrik
arXiv Computer Vision
Sep 11

From Evaluation to Enhancement: Benchmarking and Improving Think-with-Video Reasoning for Video Generative Models

The paper introduces VWG-Bench, a benchmark covering nine reasoning dimensions and 38 tasks to evaluate video generative models on symbolic reasoning, physical laws, and goal pursuit. It also presents Vid-PRE, a prompt-rewriting framework that offloads reasoning to a VLM, improving logical performance without changing the generator architecture. Experiments show that current models excel at visual quality but struggle with logic-heavy tasks, while Vid-PRE significantly boosts reasoning across multiple generators.

By Meng Luo, Yicheng Liu, Jiahao Wang, Yuanxing Zhang, Xin Tao, Pengfei Wan, Kun Gai, Hao Fei
arXiv AI
Aug 28

CounterVid: Counterfactual Video Generation for Mitigating Action and Temporal Hallucinations in Video-Language Models

CounterVid introduces a scalable counterfactual video generation framework that creates videos differing only in actions or temporal structure while keeping scene context intact. The approach uses multimodal LLMs for action proposals and diffusion models for editing, producing a synthetic dataset of ~26k preference pairs for action recognition and sequence ordering. With the MixDPO optimization method, the authors demonstrate significant improvements in action recognition and temporal ordering on Qwen2.5‑VL and InternVL3 backbones, while maintaining overall video understanding.

By Tobia Poppi, Burak Uzkent, Amanmeet Garg, Lucas Porto, Garin Kessler, Yezhou Yang, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara, Florian Schiffers
arXiv AI
Aug 25

Aligning Human Sense: Calibrated Distributional Reward Learning for Video Generation

arXiv:2608.21425v1 Announce Type: cross Abstract: Video generation is central to AI-powered content creation. Aligning generated videos with human preferences is a key criterion for evaluating genera...

By Nai-Xin Zhai, Weihua Cheng, Dexu Yu, Yikai Gu, Hanwen Du, Junchen Fu, Chenxi Huang, Yingwei Song, Liyuan Lillian Ma, Yang Ran, Youhua Li, Yongxin Ni
arXiv Computer Vision
Aug 25

FIRM-Video: Check Before You Score for Reliable Text-to-Video Reward Modeling

arXiv:2608.21839v1 Announce Type: new Abstract: Reliable reward models are essential for text-to-video evaluation and alignment. However, the trade-off between evaluation accuracy and inference effic...

By Peiyuan Zhang, Xiangyu Zhao, Hongbo Liu, Xiaoxing Hu, Mingxin Liu, Shuran Ma, Yunhang Shen, Jian Hu, Haihan Gao, Haoyu Cao, Xue Yang
arXiv AI
Jun 2

From Human Videos to Robot Manipulation: A Survey on Scalable Vision-Language-Action Learning with Human-Centric Data

arXiv:2606. 00054v1 Announce Type: cross Abstract: Recent progress in generalizable embodied control has been driven by large-scale pretraining of Vision-Language-Action (VLA) models.

By Zhiyuan Feng, Qixiu Li, Huizhi Liang, Rushuai Yang, Yichao Shen, Zhiying Du, Zhaowei Zhang, Yu Deng, Li Zhao, Hao Zhao, Zongqing Lu, Oier Mees, Marc Pollefeys, Jiaolong Yang, Baining Guo
arXiv AI
Aug 11

TrustRoboReward: Preference-Ordered Isotonic Score Editing for Multi-Paradigm Robot Reward Models

arXiv:2608. 08491v1 Announce Type: new Abstract: Reward models are a bottleneck for reinforcement learning in embodied AI.

By Yidong Wang, Yan Zhan, Ziteng Feng, Zhenyu Cui, Ziyi Zhou, Renzhao Liang, Jiaxuan Zhu, Zilei Yang, Yiran Zhao, Zhongkuan Mao, Bo Jia, Hanchu Ni, Chenggang Xie, Biao Liu, Yi Zhang, Yong Dai, Xiaozhu Ju, Wei Ye, Shikun Zhang
arXiv AI
Jun 26

Joint Reward Modeling: Internalizing Chain-of-Thought for Efficient Visual Reward Models

arXiv:2602. 07533v2 Announce Type: replace Abstract: Reward models are critical for reinforcement learning from human feedback, as they determine the alignment quality and reliability of generative models.

By Yankai Yang, Yancheng Long, Hongyang Wei, Wei Chen, Tianke Zhang, Kaiyu Jiang, Haonan Fan, Changyi Liu, Jiankang Chen, Kaiyu Tang, Bin Wen, Fan Yang, Tingting Gao, Han Li, Shuo Yang