11 papers
Precedent-Informed Reasoning: Mitigating Overthinking in Large Reasoning Models via Test-Time Precedent Learning
Qianyue Wang, Jinwu Hu, Huanxiang Lin +5
Reasoning in Large Language Models (LLMs) often suffers from inefficient long chain-of-thought traces with redundant self-exploration and validation, which inflate computational co…
SeaLLMs-Audio: Large Audio-Language Models for Southeast Asia
Chaoqun Liu, Mahani Aljunied, Guizhen Chen +4
We introduce SeaLLMs-Audio, the first large audio-language model (LALM) tailored for multiple Southeast Asian (SEA) languages-Indonesian (id), Thai (th), and Vietnamese (vi)-alongs…
Scaling Language-Centric Omnimodal Representation Learning
Chenghao Xiao, Hou Pong Chan, Hao Zhang +3
Recent multimodal embedding approaches leveraging multimodal large language models (MLLMs) fine-tuned with contrastive learning (CL) have shown promising results, yet the underlyin…
ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical Reasoning
Yu Sun, Xingyu Qian, Weiwen Xu +8
Reasoning-based large language models have excelled in mathematics and programming, yet their potential in knowledge-intensive medical question answering remains underexplored and…
MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources
Sicong Leng, Jing Wang, Jiaxi Li +12
Large multimodal reasoning models have achieved rapid progress, but their advancement is constrained by two major limitations: the absence of open, large-scale, high-quality long c…
GeoPQA: Bridging the Visual Perception Gap in MLLMs for Geometric Reasoning
Guizhen Chen, Weiwen Xu, Hao Zhang +4
Recent advancements in reinforcement learning (RL) have enhanced the reasoning abilities of large language models (LLMs), yet the impact on multimodal LLMs (MLLMs) is limited. Part…