Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters Paper • 2602.10604 • Published 2 days ago • 161
SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning Paper • 2602.08234 • Published 4 days ago • 64
sentence-transformers/all-MiniLM-L6-v2 Sentence Similarity • 22.7M • Updated Mar 6, 2025 • 156M • • 4.46k
When Modalities Conflict: How Unimodal Reasoning Uncertainty Governs Preference Dynamics in MLLMs Paper • 2511.02243 • Published Nov 4, 2025 • 25