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:2605. 21854v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have rapidly converged on a small set of architectural patterns: discrete-token autoregression (e.
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.
arXiv:2610.01973v1 Announce Type: new Abstract: Reinforcement learning (RL) for video generation usually assigns one scalar reward to an entire sampled video. Yet a video is not uniformly flawed: som...
arXiv:2606. 11209v1 Announce Type: cross Abstract: Visual question answering increasingly requires multi-step reasoning.
arXiv:2606. 24477v1 Announce Type: cross Abstract: Video large language models (LLMs) are often constrained by computation and memory budgets, leading them to use reduced frame rates and spatial resolutions, which may cause them to miss critical information for question answering (QA).
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:2510. 17045v2 Announce Type: replace-cross Abstract: Video reasoning using Large Multimodal Models (LMMs) relies on costly reinforcement learning (RL) and verbose chain-of-thought, resulting in substantial computational overhead during both training and inference.
The paper introduces POISE, a reinforcement learning algorithm that uses a model’s internal states as a value estimator to reduce variance in reinforcement learning with verifiable rewards (RLVR). By employing a lightweight probe that reads internal signals during the forward pass, POISE predicts baselines online and uses a cross‑rollout construction to keep gradients unbiased. Experiments on Qwen3‑4B and OLMo3‑7B‑Instruct‑DPO across six domains show POISE outperforms existing RLVR baselines, offering more stable training and a value model that generalizes across tasks and scales with the policy.
arXiv:2607. 25487v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models translate natural-language commands into robot action sequences, but leading systems on the LIBERO-Plus robustness benchmark use three- to seven-billion-parameter backbones whose memory demands can exceed embedded robotic budgets.
arXiv:2608.20814v1 Announce Type: new Abstract: Though Multimodal Large Language Models (MLLMs) have shown impressive potential in video understanding, long video understanding (LVU) remains challeng...
arXiv:2607. 02959v1 Announce Type: cross Abstract: We introduce VSeek, an agentic framework that transforms long-video question answering (LVQA) from a passive, single-pass perception task into a multi-turn retrieval process.
arXiv:2609.39168v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has improved the reasoning capabilities of Multimodal Large Language Models (MLLMs), yet existing...