SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning Paper • 2602.13515 • Published Feb 13 • 44
Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters Paper • 2602.10604 • Published Feb 11 • 194
SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning Paper • 2602.08234 • Published Feb 9 • 74
sentence-transformers/all-MiniLM-L6-v2 Sentence Similarity • 22.7M • Updated Mar 6, 2025 • 196M • • 4.67k
When Modalities Conflict: How Unimodal Reasoning Uncertainty Governs Preference Dynamics in MLLMs Paper • 2511.02243 • Published Nov 4, 2025 • 25
pyannote/speaker-diarization-precision-2 Voice Activity Detection • Updated Sep 16, 2025 • 4.26k • 13