collaborators

5 papers

cs.LG2026

Post-Training is About States, Not Tokens: A State Distribution View of SFT, RL, and On-Policy Distillation

Dong Nie

Large language model post-training methods such as supervised fine-tuning (SFT), reinforcement learning (RL), and distillation are often analyzed through their loss functions: maxi…

cs.LG2026

Sub-JEPA: Subspace Gaussian Regularization for Stable End-to-End World Models

Kai Zhao, Dongliang Nie, Yuchen Lin +4

Joint-Embedding Predictive Architectures (JEPAs) provide a simpleframework for learning world models by predicting future latent representations.However, JEPA training is subject t…

cs.LG2026

UNA: A Unified Supervised Framework for Efficient LLM Alignment Across Feedback Types

Zhichao Wang, Bin Bi, Can Huang +7

RL alignment methods, including RLHF and DPO, are primarily based on pairwise preference data. Although scalar or score-based feedback has been collected in some settings, it is ra…

cs.CV2026

Seeing the Forest and the Trees: Query-Aware Tokenizer for Long-Video Multimodal Language Models

Siyou Li, Huanan Wu, Juexi Shao +10

Despite the recent advances in the video understanding ability of multimodal large language models (MLLMs), long video understanding remains a challenge. One of the main issues is…

cs.LG2025

Tokenizer: Differentiable Multi-Scale Multi-Modal Tokenizer for Radiology Report Generation

Siyou Li, Pengyao Qin, Huanan Wu +4

Automated radiology report generation (RRG) aims to produce detailed textual reports from clinical imaging, such as computed tomography (CT) scans, to improve the accuracy and effi…