HyQuant: Hybrid-Precision Quantization for LLM Attention Paper • 2608.27875 • Published 22 days ago • 30
Reason Through the Latent! Making Latent Visual Reasoning Necessary Paper • 2609.06746 • Published 13 days ago • 36
Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLM Paper • 2609.04098 • Published 16 days ago • 83
MemTrapBench: Benchmarking Cognitive Traps in LLM Memory Use Paper • 2608.20202 • Published about 1 month ago • 34