… It contains 2,061 examples across three levels: active visual evidence seeking , controlled offline interleaved multimodal search, and open-web interleaved multimodal search. …
… The following papers were recommended by the Semantic Scholar API Self-Distilled RLVR 2026 Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation 2026 Demystifying OPD: Length Inflation and Stabilization Strategies for Large Language Models 2026 Rethin… …
… However, this offline paradigm introduces a Supervision-Perception Mismatch: the student model is forced to align with fine-grained details beyond its perceptual capacity, learning to guess rather than to see. …
… The following papers were recommended by the Semantic Scholar API CodeMMR: Bridging Natural Language, Code, and Image for Unified Retrieval 2026 The Geometry of Compromise: Unlocking Generative Capabilities via Controllable Modality Alignment 2026 NanoVDR: Distilling a 2B Vision-Language Retriever … …
… The following papers were recommended by the Semantic Scholar API Flow Matching Policy with Entropy Regularization 2026 ScoRe-Flow: Complete Distributional Control via Score-Based Reinforcement Learning for Flow Matching 2026 Truncated Rectified Flow Policy for Reinforcement Learning with One-Step … …