WUSH-KV: KV Cache Quantization with Data-Adaptive Transforms Paper • 2609.38121 • Published 5 days ago • 16
Disaggregated Quantization: Specializing LLM Prefill and Decode Paper • 2609.26333 • Published 12 days ago • 91
Reasoning Shift: How Context Silently Shortens LLM Reasoning Paper • 2604.01161 • Published Apr 1 • 32
Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs Paper • 2510.11288 • Published Oct 13, 2025 • 48
Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization Paper • 2509.23202 • Published Sep 27, 2025 • 30