collaborators

5 papers

cs.LG2025

Weak-to-Strong Generalization Even in Random Feature Networks, Provably

Marko Medvedev, Kaifeng Lyu, Dingli Yu +3

Weak-to-Strong Generalization (Burns et al., 2024) is the phenomenon whereby a strong student, say GPT-4, learns a task from a weak teacher, say GPT-2, and ends up significantly ou…

cs.CV2025

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?

Simon Park, Abhishek Panigrahi, Yun Cheng +3

Vision Language Models (VLMs) are impressive at visual question answering and image captioning. But they underperform on multi-step visual reasoning -- even compared to LLMs on the…

cs.AI2025

AI-Assisted Generation of Difficult Math Questions

Vedant Shah, Dingli Yu, Kaifeng Lyu +8

Current LLM training positions mathematical reasoning as a core capability. With publicly available sources fully tapped, there is unmet demand for diverse and challenging math que…

cs.CL2025

Can Models Learn Skill Composition from Examples?

Haoyu Zhao, Simran Kaur, Dingli Yu +2

As large language models (LLMs) become increasingly advanced, their ability to exhibit compositional generalization -- the capacity to combine learned skills in novel ways not enco…

cs.LG2025

Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates

Kaifeng Lyu, Haoyu Zhao, Xinran Gu +3

Public LLMs such as the Llama 2-Chat underwent alignment training and were considered safe. Recently Qi et al. [2024] reported that even benign fine-tuning on seemingly safe datase…