36 posts in total
2026
Reading Notes of Huxley-Gödel Machine: Human-Level Coding Agent Development by an Approximation of the Optimal Self-Improving Machine
Reading Notes of Context Language Models
Reading Notes of DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
Reading Notes of Welcome to the Era of Experience
Reading Notes of Selective Context: Compressing Context to Enhance Inference Efficiency of Large Language Models
Reading Notes of LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models
Reading Notes of JLens: Verbalizable Representations Form a Global Workspace in Language Models
Reading Notes of Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning
Reading Notes of ForesightKV: Optimizing KV Cache Eviction for Reasoning Models by Learning Long-Term Contribution
Reading Notes of RLKV: Which Heads Matter for Reasoning? RL-Guided KV Cache Compression