9 papers
BIRD: Distilling Decision Boundaries into Rationales for MLLM Adaptation
Anglin Liu, Yanlin Wu, Ruichao Chen +6
Adapting general-purpose multimodal large language models (MLLMs) to specialized domains requires learning domain-specific decision criteria, which often hinge on subtle visual dis…
IDEEA: training-free Input-Dependent stEEring via Activation cluster matching
Zheng Wang, Muchen Li, Renjie Liao +1
Steering aligns large language models (LLMs) by injecting a bias into selected activations at inference time, offering a far cheaper alternative to weight-update methods such as su…
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…
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…
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…
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…
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…
On the Effect of Negative Gradient in Group Relative Deep Reinforcement Optimization
Wenlong Deng, Yi Ren, Muchen Li +3
Reinforcement learning (RL) has become popular in enhancing the reasoning capabilities of large language models (LLMs), with Group Relative Policy Optimization (GRPO) emerging as a…
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…