arXiv Machine Learning
Towards Scalable RLVR: Multimodal Instruction Following Data Synthesis and Distillation
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jun 30
Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL
arXiv:2604. 28123v3 Announce Type: replace-cross Abstract: The standard post-training recipe for large multimodal models (LMMs) applies supervised fine-tuning (SFT) on curated demonstrations followed by reinforcement learning with verifiable rewards (RLVR).
arXiv Computation and Language
Aug 27
VISA: Agentic Self-Evolving Data Synthesis for Multimodal Instruction Following
VISA (Visual Instruction Synthesis Agent) is an agentic framework that transforms multimodal instruction synthesis into a self‑evolving loop. Each cycle analyzes images to filter constraints, samples new constraint sets, generates candidate instructions, and verifies them using executable tools and large language model judges. Failed samples trigger diagnostic recovery, while accepted samples are evaluated against the target model to estimate difficulty, with all feedback written back to memory to adapt future rounds and provide reward signals for reinforcement learning.
arXiv AI
Jun 8
Teaching the Way, Not the Answer: Privileged Tutoring Distillation for Multimodal Policy Optimization
arXiv:2606. 07000v1 Announce Type: new Abstract: Recent post-training methods, particularly Reinforcement Learning with Verifiable Rewards (RLVR), have significantly enhanced the reasoning ability of Large Vision-Language Models (LVLMs).
arXiv AI
Aug 11
StructReward: Efficient Structured Process Rewards for Self-Correcting Multimodal Reasoning
arXiv:2608. 08326v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as an effective approach for improving multimodal reasoning.
arXiv Computer Vision
Aug 25
VinciCoder: Unifying Multimodal Code Generation via Coarse-to-fine Visual Reinforcement Learning
VinciCoder is a unified framework for multimodal code generation that addresses the limitations of single-task models by training on a large-scale curated corpus of 1.3 M direct generation pairs and 300 k visual‑refinement tasks. It introduces a coarse‑to‑fine Visual Reinforcement Learning (ViRL) approach that uses visual similarity across multi‑scale patches to provide an implementation‑agnostic reward, improving alignment between rendered outputs and input visuals. Experiments on diverse benchmarks show VinciCoder outperforms existing methods, and ablation studies confirm the effectiveness of ViRL.
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.