CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating

arXiv:2605.11723 · cs.CV, cs.AI · Submitted 2026-05-12 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-05-12

Updated: 2026-09-25

Terminology

• GRPO — 35× in this paper · explained in 6 episodes
• Accuracy — 25× in this paper · explained in 1 episode
• Grounding — 23× in this paper · explained in 3 episodes
• Alignment — 21× in this paper · explained in 1 episode
• Consistency — 13× in this paper · explained in 3 episodes
• Benchmark — 12× in this paper · explained in 2 episodes
• Verification — 11× in this paper · explained in 2 episodes
• Ablation — 10× in this paper · explained in 1 episode
• Reinforcement Learning — 7× in this paper · explained in 4 episodes
• Generative Model — 6× in this paper · explained in 2 episodes
• Generative Models — 6× in this paper · explained in 2 episodes
• Hallucination — 6× in this paper · explained in 3 episodes
• Diffusion Model — 5× in this paper · explained in 8 episodes
• Fine-Tuning — 5× in this paper · explained in 5 episodes
• Adam — 4× in this paper · explained in 2 episodes
• Concentrate and Concentrate — 4× in this paper
• Diffusion Models — 3× in this paper · explained in 6 episodes
• Foundation Model — 3× in this paper · explained in 3 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• Group Relative Policy Optimization — 3× in this paper
• Best-of-N Sampling — 2× in this paper · explained in 2 episodes
• Contrastive Learning — 2× in this paper · explained in 5 episodes
• Fidelity — 2× in this paper · explained in 2 episodes
• Group Relative Policy Optimization (GRPO) — 2× in this paper · explained in 5 episodes
• Multimodal Reasoning — 2× in this paper · explained in 5 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Annotation Errors — 1× in this paper · explained in 1 episode
• Annotator Agreement — 1× in this paper · explained in 1 episode
• Bradley-Terry model — 1× in this paper · explained in 2 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Computational overhead — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Flow Matching — 1× in this paper · explained in 8 episodes
• Flow Matching Model — 1× in this paper · explained in 2 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• GRPO Objective — 1× in this paper · explained in 2 episodes
• Latent Diffusion Model — 1× in this paper · explained in 2 episodes
• Provenance — 1× in this paper · explained in 3 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes
• Reward Function — 1× in this paper · explained in 2 episodes
• Reward Hacking — 1× in this paper · explained in 8 episodes
• Sparsity — 1× in this paper · explained in 4 episodes
• Structured Reasoning — 1× in this paper · explained in 3 episodes
• Verifiable Rewards — 1× in this paper · explained in 2 episodes

Sources

• A Survey on Video Anomaly Detection via Deep Learning: Human, Vehicle, and Environment
• Qwen3-VL Technical Report
• VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation
• PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation
• CropVLM: Learning to Zoom for Fine-Grained Vision-Language Perception
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• Investigating Text Insulation and Attention Mechanisms for Complex Visual Text Generation
• Sculpting Features from Noise: Reward-Guided Hierarchical Diffusion for Task-Optimal Feature Transformation
• RePer-360: Releasing Perspective Priors for 360$^\circ$ Depth Estimation via Self-Modulation
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning
• LTX-2: Efficient Joint Audio-Visual Foundation Model
• VideoScore2: Think before You Score in Generative Video Evaluation
• EVE: Verifiable Self-Evolution of MLLMs via Executable Visual Transformations
• GPT-4o System Card
• HunyuanVideo: A Systematic Framework For Large Video Generative Models
• Skyra: AI-Generated Video Detection via Grounded Artifact Reasoning
• DiffPCN: Latent Diffusion Model Based on Multi-view Depth Images for Point Cloud Completion
• DRL4AOI: A DRL Framework for Semantic-aware AOI Segmentation in Location-Based Services
• Flow-GRPO: Training Flow Matching Models via Online RL

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models