Fine-grained Conversational Decoding via Isotropic and Proximal Search Paper • 2310.08130 • Published Oct 12, 2023
Learning From Correctness Without Prompting Makes LLM Efficient Reasoner Paper • 2403.19094 • Published Mar 28, 2024
BPP-Search: Enhancing Tree of Thought Reasoning for Mathematical Modeling Problem Solving Paper • 2411.17404 • Published Nov 26, 2024
1bit-Merging: Dynamic Quantized Merging for Large Language Models Paper • 2502.10743 • Published Feb 15, 2025