3 papers
cs.LG2026
Curvature Tuning: Provable Training-free Model Steering From a Single Parameter
Leyang Hu, Matteo Gamba, Randall Balestriero
The scaling of model and data sizes has reshaped the AI landscape, establishing finetuning pretrained models as the standard paradigm for solving downstream tasks. However, dominan…
cs.CL2025
Next Token Perception Score: Analytical Assessment of your LLM Perception Skills
Yu-Ang Cheng, Leyang Hu, Hai Huang +1
Autoregressive pretraining has become the de facto paradigm for learning general-purpose representations in large language models (LLMs). However, linear probe performance across d…
cs.CL2024
DROJ: A Prompt-Driven Attack against Large Language Models
Leyang Hu, Boran Wang
Large Language Models (LLMs) have demonstrated exceptional capabilities across various natural language processing tasks. Due to their training on internet-sourced datasets, LLMs c…