arXiv Computer Vision
Boosting Reasoning in Large Multimodal Models via Activation Replay
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
Jun 2
Video Reasoning without Training
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.
arXiv AI
Aug 3
Multimodal Reinforcement Learning with Adaptive Verifier for AI Agents
arXiv:2512. 03438v3 Announce Type: replace Abstract: Agentic reasoning models trained with multimodal reinforcement learning (MMRL) have become increasingly capable, yet they are almost universally optimized using sparse, outcome-based rewards computed based on the final answers.
arXiv AI
Jun 2
Boosting RL-Based Visual Reasoning with Selective Adversarial Entropy Intervention
arXiv:2512. 10414v2 Announce Type: replace Abstract: Recently, reinforcement learning (RL) has become a common choice in enhancing the reasoning capabilities of vision-language models (VLMs).
arXiv AI
Jun 19
Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models
arXiv:2510. 21978v2 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has delivered impressive gains in mathematical and multimodal reasoning and has become a standard post-training paradigm for contemporary language and vision-language models.
arXiv AI
Jun 3
Entropy Is Not Enough: Unlocking Effective Reinforcement Learning for Visual Reasoning via Vision-Anchored Token Selection
arXiv:2606. 03937v1 Announce Type: new Abstract: While token-level entropy is commonly recognized as effective for credit assignment in text-only reinforcement learning with verifiable rewards (RLVR), it remains unclear whether this mechanism still holds in visual reasoning.
arXiv AI
Jul 14
SVR-R1: Bootstrapping Multi-modal Reasoning with Self-verification in Reinforcement Learning
arXiv:2607. 10966v1 Announce Type: new Abstract: We introduce Self-Verified Reasoner (SVR-R1), a multi-turn RL framework that turns a model's own verification into a learning signal for multimodal reasoning.