OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Paper • 2605.19660 • Published 5 days ago • 39 • 3
OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Paper • 2605.19660 • Published 5 days ago • 39
Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation Paper • 2604.10098 • Published Apr 11 • 81
Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation Paper • 2604.10098 • Published Apr 11 • 81
OpenSpatial: A Principled Data Engine for Empowering Spatial Intelligence Paper • 2604.07296 • Published Apr 8 • 40
The Art of Efficient Reasoning Collection Project: https://wutaiqiang.github.io/project/Art • 8 items • Updated Mar 18 • 2
The Art of Efficient Reasoning Collection Project: https://wutaiqiang.github.io/project/Art • 8 items • Updated Mar 18 • 2
The Art of Efficient Reasoning Collection Project: https://wutaiqiang.github.io/project/Art • 8 items • Updated Mar 18 • 2
CHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning Paper • 2603.00889 • Published Mar 1 • 55