The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning Paper • 2606.29526 • Published 13 days ago • 161
Drop-Then-Recovery: How Redundant Are Vision-Language-Action Models? Paper • 2606.27755 • Published 15 days ago • 6
Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models Paper • 2606.03988 • Published Jun 3 • 126
stefanocarrera/autophagycode_D_he_train-mercury_Qwen3-8B_strategy_surplexity_t1_g5_run2_metrics Viewer • Updated Jun 3 • 164 • 17 • 1
Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs Paper • 2605.30611 • Published May 28 • 250
OmniVerifier-M1: Multimodal Meta-Verifier with Explicit Structured Recalibration Paper • 2605.28805 • Published May 27 • 11
GenEvolve: Self-Evolving Image Generation Agents via Tool-Orchestrated Visual Experience Distillation Paper • 2605.21605 • Published May 20 • 15
Perception or Prejudice: Can MLLMs Go Beyond First Impressions of Personality? Paper • 2605.22109 • Published May 21 • 171
Multi-Objective and Mixed-Reward Reinforcement Learning via Reward-Decorrelated Policy Optimization Paper • 2605.13641 • Published May 13 • 51