StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling Paper • 2608.15089 • Published 7 days ago • 432
Hunyuan3D-Buffalo 1.0: A Unified Multimodal Model for Scalable 3D Generation, Understanding, and Editing Paper • 2608.02711 • Published 18 days ago • 90
Paused Agents 299 LTX 2.3 Finetuned I2V 🎬 299 LTX 2.3 finetuned I2V with identity & voice conditioning
F2LLM Technical Report: Matching SOTA Embedding Performance with 6 Million Open-Source Data Paper • 2510.02294 • Published Oct 2, 2025 • 48