Dong Nie

activity

20242026

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

1 citations · 2 across the 9 of their papers we have counts for

collaborators

Showing 2025Show all

2 papers · 1 filter

cs.CV2025

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

$μ^{2}$ 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…

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

μ2Tokenizer: Differentiable Multi-Scale Multi-Modal Tokenizer for Radiology Report Generation

$μ^{2}$ Tokenizer: Differentiable Multi-Scale Multi-Modal Tokenizer for Radiology Report Generation