activity
20242026
collaborators

6 papers

cs.CV2026

Efficient Long-Context Modeling in Diffusion Language Models via Block Approximate Sparse Attention

Wenhu Zhang, Yiming Wu, Huanyu Wang +6

Diffusion Language Models (DLMs) enable globally coherent, bidirectional, and controllable text generation, offering advantages over traditional autoregressive LLMs, while scaling…

cs.LG2026

Convex Dataset Valuation for Post-Training

Siqi Zeng, Christopher Jung, Rui Li +7

Improving LLM performance on downstream tasks sometimes requires leveraging auxiliary datasets during post-training. In practice, however, developers face constraints on compute, l…

cs.LG2026

Expectation Error Bounds for Transfer Learning in Linear Regression and Linear Neural Networks

Meitong Liu, Christopher Jung, Rui Li +2

In transfer learning, the learner leverages auxiliary data to improve generalization on a main task. However, the precise theoretical understanding of when and how auxiliary data h…

cs.LG2025

Gradual Domain Adaptation: Theory and Algorithms

Yifei He, Haoxiang Wang, Bo Li +1

Unsupervised domain adaptation (UDA) adapts a model from a labeled source domain to an unlabeled target domain in a one-off way. Though widely applied, UDA faces a great challenge…

cs.LG2024

RLHF Workflow: From Reward Modeling to Online RLHF

Hanze Dong, Wei Xiong, Bo Pang +7

We present the workflow of Online Iterative Reinforcement Learning from Human Feedback (RLHF) in this technical report, which is widely reported to outperform its offline counterpa…

cs.LG2024

Mitigating the Alignment Tax of RLHF

Yong Lin, Hangyu Lin, Wei Xiong +14

LLMs acquire a wide range of abilities during pre-training, but aligning LLMs under Reinforcement Learning with Human Feedback (RLHF) can lead to forgetting pretrained abilities, w…