activity
20242026
collaborators

6 papers

cs.LG2026

Training Data Efficiency in Multimodal Process Reward Models

Jinyuan Li, Chengsong Huang, Langlin Huang +4

Multimodal Process Reward Models (MPRMs) are central to step-level supervision for visual reasoning in MLLMs. Training MPRMs typically requires large-scale Monte Carlo (MC)-annotat…

cs.CV2026

LiViBench: An Omnimodal Benchmark for Interactive Livestream Video Understanding

Xiaodong Wang, Langling Huang, Zhirong Wu +4

The development of multimodal large language models (MLLMs) has advanced general video understanding. However, existing video evaluation benchmarks primarily focus on non-interacti…

cs.CL2025

POSS: Position Specialist Generates Better Draft for Speculative Decoding

Langlin Huang, Chengsong Huang, Jixuan Leng +2

Speculative decoding accelerates Large Language Model (LLM) inference by using a small draft model to predict multiple tokens, and a large target model to verify these tokens in pa…

cs.CL2025

CrossWordBench: Evaluating the Reasoning Capabilities of LLMs and LVLMs with Controllable Puzzle Generation

Jixuan Leng, Chengsong Huang, Langlin Huang +4

Existing reasoning evaluation frameworks for Large Language Models (LLMs) and Large Vision-Language Models (LVLMs) predominantly assess either text-based reasoning or vision-langua…

cs.LG2025

Efficient Test-Time Scaling via Self-Calibration

Chengsong Huang, Langlin Huang, Jixuan Leng +2

Increasing test-time computation is a straightforward approach to enhancing the quality of responses in Large Language Models (LLMs). While Best-of-N sampling and Self-Consistency…

cs.LG2024

Divide, Reweight, and Conquer: A Logit Arithmetic Approach for In-Context Learning

Chengsong Huang, Langlin Huang, Jiaxin Huang

In-Context Learning (ICL) emerges as a key feature for Large Language Models (LLMs), allowing them to adapt to new tasks by leveraging task-specific examples without updating model…