Blog
This is a personal blog of Jinuk Kim.
-
Trust Regions and Off-Policy Corrections in LLM RL
From REINFORCE to one master equation, grouping policy-gradient methods by the ratio each one controls
-
Rule2DRC
Benchmarking LLM Agents for DRC Script Synthesis with Execution-Guided Test Generation
-
GuidedQuant
Large Language Model Quantization via Exploiting End Loss Guidance
-
LayerMerge
Neural Network Depth Compression through Layer Pruning and Merging
-
Efficient CNN Depth Compression
Efficient Latency-Aware CNN Depth Compression via Two-Stage Dynamic Programming
