OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond
Paper • 2605.19660 • Published • 40
Yuan-Li-FNLP
Yuan-Li-FNLP
AI & ML interests
None yet
Recent Activity
upvoted a paper about 2 months ago
OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond upvoted a paper about 2 months ago
World Action Models: The Next Frontier in Embodied AI upvoted a paper 4 months ago
AI Can Learn Scientific TasteOrganizations
None yet
upvoted 2
papers about 2 months ago
upvoted 4
papers 4 months ago
AI Can Learn Scientific Taste
Paper • 2603.14473 • Published • 431
Utonia: Toward One Encoder for All Point Clouds
Paper • 2603.03283 • Published • 187
BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning
Paper • 2603.04918 • Published • 56
R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning
Paper • 2505.23794 • Published • 1