Sommelier: Scalable Open Multi-turn Audio Pre-processing for Full-duplex Speech Language Models Paper • 2603.25750 • Published 11 days ago • 10
Gen-Searcher: Reinforcing Agentic Search for Image Generation Paper • 2603.28767 • Published about 18 hours ago • 39
Running on Zero Featured 323 DLSS 5 Anything 🎮 323 Turn any image into a DLSS 5 meme (using FLUX.2-klein-9b-kv)
On Token's Dilemma: Dynamic MoE with Drift-Aware Token Assignment for Continual Learning of Large Vision Language Models Paper • 2603.27481 • Published 2 days ago • 24
SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks Paper • 2603.24755 • Published 6 days ago • 25
Running on CPU Upgrade Featured 71 Cohere Multilingual ASR 🎙 71 Transcribe audio clips to text in many languages
view article Article How I contributed a new model to the Transformers library using Codex about 20 hours ago • 30
RealChart2Code: Advancing Chart-to-Code Generation with Real Data and Multi-Task Evaluation Paper • 2603.25804 • Published 5 days ago • 19
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis Paper • 2603.20278 • Published 14 days ago • 91