Trending
- Introducing the Open FinLLM Leaderboard
- The Shape of a Program: Path Signatures for Trace-to-Program Induction
- Improving Parquet Dedupe on Hugging Face Hub
- A New Paradigm for Probabilistic Linear Solvers
- Faster Assisted Generation with Dynamic Speculation
- Branch-and-Commit for Frozen RL Agents: When and Where to Spend Test-Time Compute
- Welcome, Gradio 5
- [2610.37914] Muon Makes the First Mixture-of-Experts Layer Harder to Balance