Chaudhary, Vipin
12 publications
NeurIPS
2025
70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float (DFloat11)
NeurIPS
2025
Longer Context, Deeper Thinking: Uncovering the Role of Long-Context Ability in Reasoning
ICLR
2025
MQuAKE-Remastered: Multi-Hop Knowledge Editing Can Only Be Advanced with Reliable Evaluations
NeurIPSW
2024
PROOF of THOUGHT : Neurosymbolic Program Synthesis Allows Robust and Interpretable Reasoning
NeurIPSW
2023
LeanFlex-GKP: Advancing Hassle-Free Structured Pruning with Simple Flexible Group Count