IdeaAMBIG: Benchmarking Implementation-Critical Gaps in Research-Idea Specifications Paper • 2609.10539 • Published 27 days ago • 25
Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLM Paper • 2609.04098 • Published Sep 3 • 85
Training Leaves Traces: Centered Residual Signatures for Language Model Lineage Verification Paper • 2608.14929 • Published Aug 14 • 18
TriGlue: a Biology-Inspired Generative Model for Generating Molecular Glue-Induced Ternary Complex Paper • 2607.22143 • Published Aug 4 • 7
PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents Paper • 2608.04003 • Published Aug 4 • 36