Vipin Chaudhary

3 papers Case Western Reserve University

• 70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float (DFloat11)
• Grammars of Formal Uncertainty: When to Trust LLMs in Automated Reasoning Tasks
• Longer Context, Deeper Thinking: Uncovering the Role of Long-Context Ability in Reasoning