Erik Cambria

Human Behavior Atlas: Benchmarking Unified Psychological And Social Behavior Understanding

Mitigating Jailbreaks with Intent-Aware LLMs

Debiasing CLIP: Interpreting and Correcting Bias in Attention Heads

Toward Experiment-Guided Hypothesis Ranking via Simulated Experimental Feedback

OptiRSDE: A Novel Approach with Temporal Smoothing and Optimized Feature Matching for Fast and Robust Depth Estimation

Modular Refinement of Small Language Models for Physics Reasoning via Localized Error Feedback

Individualized Cognitive Simulation in Large Language Models: Evaluating Different Cognitive Representation Methods

MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses

MOOSE-Chem2: Exploring LLM Limits in Fine-Grained Scientific Hypothesis Discovery via Hierarchical Search