arXiv Computer Vision
Token-Level Video Reinforcement Learning
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
Jul 3
Rank-Then-Act: Reward-Free Control from Frame-Order Progress
arXiv:2607. 01897v1 Announce Type: cross Abstract: We introduce Rank-Then-Act (RTA), a framework for learning control policies from expert video demonstrations without environment rewards.
arXiv Machine Learning
Jul 31
S-GRPO: Unified Post-Training for Large Vision-Language Models
arXiv:2604. 16557v2 Announce Type: replace Abstract: Current post-training methodologies for adapting Large Vision-Language Models (LVLMs) generally fall into two paradigms: Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL).
arXiv Computer Vision
Aug 24
Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs
The paper introduces OraRL, a reinforcement learning framework that leverages annotations as oracle rollouts to improve sample efficiency and scalability for video multimodal large language models (MLLMs). By decoupling advantage estimation and employing sign‑balanced pruning, OraRL achieves faster training and better performance across multiple video‑perception benchmarks compared to existing methods. The approach scales from 0.8B to 9B parameters and handles up to 100k prompts, delivering significant gains in temporal mIoU, tracking accuracy, segmentation, and spatial‑intelligence metrics.
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.
arXiv Computer Vision
Sep 23
Video-HopChain: Multi-Hop Questions and Confidence-Gated Exploration for Video Reasoning Models
Video-HopChain introduces a new dataset of 22,550 multi‑hop video questions over 13,378 videos, each question consisting of three to six yes/no sub‑questions whose integer answers sum to a verifiable reward. Training a Qwen3‑VL‑8B model with GRPO on this dataset improves performance across eight video‑understanding benchmarks from 55.4 to 57.9, and the addition of Confidence‑Gated Exploration (CGE) raises the mean to 59.3. The authors release the dataset, checkpoint, and training code for further research.
arXiv AI
6d ago
Stepwise Intrinsic Rewards for Reasoning in Large Language Models
The paper introduces Stepwise Marginal Information Gain (MIG), an intrinsic process reward that evaluates how each reasoning step of a large language model (LLM) or vision-language model (VLM) improves the likelihood of the reference answer. MIG rewards only new likelihood maxima, preventing duplicate credit, and is combined with outcome, format, and self‑distillation objectives to guide training. Experiments on eight benchmarks show that this method outperforms outcome‑only reinforcement learning and improves accuracy by up to 4.8 points over binary‑reward training, including a 12.6‑point gain on MathVerse and a 12.9‑point advantage on vision‑language transfer at 7B parameters.