1 citations · 2 across the 9 of their papers we have counts for
9 papers
Weak-to-Strong On-Policy Distillation
Fangxu Yu, Weijia Xu, Michael Xu +2
On-policy distillation (OPD), which aligns a student with the teacher's token-level distribution on the student's own rollouts, is an effective paradigm for transferring capabiliti…
Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play
Qinsi Wang, Bo Liu, Tianyi Zhou +6
Although reinforcement learning (RL) has emerged as a promising approach for improving vision-language models (VLMs) and multimodal large language models (MLLMs), current methods r…
Can LLMs Detect Their Confabulations? Estimating Reliability in Uncertainty-Aware Language Models
Tianyi Zhou, Johanne Medina, Sanjay Chawla
Large Language Models (LLMs) are prone to generating fluent but incorrect content, known as confabulation, which poses increasing risks in multi-turn or agentic applications where…
Where to show Demos in Your Prompt: A Positional Bias of In-Context Learning
Kwesi Cobbina, Tianyi Zhou
In-context learning (ICL) is a critical emerging capability of large language models (LLMs), enabling few-shot learning during inference by including a few demonstrations (demos) i…
DistFlow: A Fully Distributed RL Framework for Scalable and Efficient LLM Post-Training
Zhixin Wang, Jiaming Xu, Tianyi Zhou +10
Effectively scaling Reinforcement Learning (RL) is crucial for enhancing the reasoning and alignment of Large Language Models. The massive data and complex execution flows inherent…
GenQA: Generating Millions of Instructions from a Handful of Prompts
Jiuhai Chen, Rifaa Qadri, Yuxin Wen +4
Most public instruction finetuning datasets are relatively small compared to the closed source datasets used to train industry models. To study questions about finetuning at scale,…
OPTune: Efficient Online Preference Tuning
Lichang Chen, Jiuhai Chen, Chenxi Liu +6
Reinforcement learning with human feedback~(RLHF) is critical for aligning Large Language Models (LLMs) with human preference. Compared to the widely studied offline version of RLH…
ODIN: Disentangled Reward Mitigates Hacking in RLHF
Lichang Chen, Chen Zhu, Davit Soselia +6
In this work, we study the issue of reward hacking on the response length, a challenge emerging in Reinforcement Learning from Human Feedback (RLHF) on LLMs. A well-formatted, verb…
Learning UI-to-Code Reverse Generator Using Visual Critic Without Rendering
Davit Soselia, Khalid Saifullah, Tianyi Zhou
Automated reverse engineering of HTML/CSS code from UI screenshots is an important yet challenging problem with broad applications in website development and design. In this paper,…