Ngoc-Hieu Nguyen

When Reasoning Meets Compression: Understanding the Effects of LLMs Compression on Large Reasoning Models

LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models

Mitigating Reward Over-optimization in Direct Alignment Algorithms with Importance Sampling

Wicked Oddities: Selectively Poisoning for Effective Clean-Label Backdoor Attacks

Mitigating Reward Over-optimization in Direct Alignment Algorithms with Adaptive Importance Sampling