Vipin Chaudhary

Full Professor@Case Western Reserve University·美国·OpenReview

研究方向

Quantum Computing · Medical Imaging · Machine Learning · Artificial Intelligence · High performance computing · Computer vision · Computer Architecture

Vipin Chaudhary

Don’t Pass@k: A Bayesian Framework for Large Language Model Evaluation

Trust The Typical

Expo-GS: Exposure-Aware Signed Distance Function in Gaussian Splatting for High Dynamic Range

Get the GIST of Graphs with Intersection Signature

NEBULA: Do We Evaluate Vision-Language-Action Agents Correctly?

AutoL2S: Auto Long-Short Reasoning for Efficient Large Language Models

Non-Deep Vision Transformers

Demystifying Hybrid Thinking: Can LLMs Truly Switch Between Think and No-Think?

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

Forte : Finding Outliers with Representation Typicality Estimation

Longer Context, Deeper Thinking: Uncovering the Role of Long-Context Ability in Reasoning

Speculative Thinking: Enhancing Small-Model Reasoning with Large Model Guidance at Inference Time

MQuAKE-Remastered: Multi-Hop Knowledge Editing Can Only Be Advanced with Reliable Evaluations

Attack on LLMs: LoRA Once, Backdoor Everywhere in the Share-and-Play Ecosystem

Graph Transformers Get the GIST: Graph Invariant Structural Trait for Refined Graph Encoding