collaborators

7 papers

cs.SD2026

MOSS Transcribe Diarize Technical Report

MOSI. AI, :, Donghua Yu +23

Speaker-Attributed, Time-Stamped Transcription (SATS) aims to transcribe what is said and to precisely determine the timing of each speaker, which is particularly valuable for meet…

cs.CV2026

CoRDS: Coreset-based Representative and Diverse Selection for Streaming Video Understanding

Ailar Mahdizadeh, Puria Azadi, Muchen Li +2

Streaming video understanding with large vision-language models (VLMs) requires a compact memory that can support future reasoning over an ever-growing visual history. A common sol…

q-bio.QM2026

Point transformer for protein structural heterogeneity analysis using CryoEM

Muyuan Chen, Muchen Li, Renjie Liao

Structural dynamics of macromolecules is critical to their structural-function relationship. Cryogenic electron microscopy (CryoEM) provides snapshots of vitrified protein at diffe…

cs.CL2025

Test-Time Steering for Lossless Text Compression via Weighted Product of Experts

Qihang Zhang, Muchen Li, Ziao Wang +2

Lossless compression techniques are crucial in an era of rapidly growing data. Traditional universal compressors like gzip offer low computational overhead, high speed, and broad a…

cs.CV2025

Free Lunch Alignment of Text-to-Image Diffusion Models without Preference Image Pairs

Jia Jun Cheng Xian, Muchen Li, Haotian Yang +4

Recent advances in diffusion-based text-to-image (T2I) models have led to remarkable success in generating high-quality images from textual prompts. However, ensuring accurate alig…

cs.CL2025

Leveraging Online Olympiad-Level Math Problems for LLMs Training and Contamination-Resistant Evaluation

Sadegh Mahdavi, Muchen Li, Kaiwen Liu +3

Advances in Large Language Models (LLMs) have sparked interest in their ability to solve Olympiad-level math problems. However, the training and evaluation of these models are cons…