Give Me FP32 or Give Me Death? Challenges and Solutions for Reproducible Reasoning Paper • 2506.09501 • Published Jun 11 • 18
70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float Paper • 2504.11651 • Published Apr 15 • 30
Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models Paper • 2503.16419 • Published Mar 20 • 76