ukisai/Swift-1.5-Qwen3.8-Flash-Next-NVFP4 Image-Text-to-Text • 120B • Updated 9 days ago • 1.14k • 13
prism-ml/Ternary-Bonsai-2-27B-gguf Text Generation • 27B • Updated 7 days ago • 3.87M • 2.36k
Llama8B LLM2Vec embeddings Collection Small encoders bridged into the Llama8B LLM2Vec space (for NVIDIA Kimodo and beyond). Beta, v2 coming. • 1 item • Updated Aug 30
4DAnyone: Create Anyone in 4D from a Casual Monocular Video Paper • 2608.20335 • Published Aug 20 • 86
FACET: Preserving Source Intent and Executable State in Terminal Task Synthesis Paper • 2608.18580 • Published Aug 19 • 96
EnvHarness: Awakening Static Worlds for Agent Learning Paper • 2608.19880 • Published Aug 20 • 176
FlashPrefill V2: Block-Sparse Prefill Attention for Long-Context LLM Serving Paper • 2608.19758 • Published Aug 20 • 21
Can We Defend Against AI-Generated Video Attacks on Real-World Crisis Events? A Systematic Evaluation of Detectors, Generators and Social Dissemination Paper • 2608.14391 • Published Aug 14 • 287
AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning Paper • 2608.05987 • Published Aug 6 • 104