16 papers
DualToken: Towards Unifying Visual Understanding and Generation with Dual Visual Vocabularies
Wei Song, Yuran Wang, Zijia Song +6
The differing representation spaces required for visual understanding and generation pose a challenge in unifying them within the autoregressive paradigm of large language models.…
Med-R: Crafting Trustworthy LLM Physicians via Retrieval and Reasoning of Evidence-Based Medicine
Keer Lu, Zheng Liang, Da Pan +6
Large Language Models (LLMs) have exhibited remarkable capabilities in clinical scenarios. Despite their potential, existing works face challenges when applying LLMs to medical set…
ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning
Mingyang Chen, Linzhuang Sun, Tianpeng Li +10
Large Language Models (LLMs) have shown remarkable capabilities in reasoning, exemplified by the success of OpenAI-o1 and DeepSeek-R1. However, integrating reasoning with external…
S2SBench: A Benchmark for Quantifying Intelligence Degradation in Speech-to-Speech Large Language Models
Yuanbo Fang, Haoze Sun, Jun Liu +5
End-to-end speech large language models ((LLMs)) extend the capabilities of text-based models to directly process and generate audio tokens. However, this often leads to a decline…
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs
Keer Lu, Keshi Zhao, Zhuoran Zhang +8
As demonstrated by the proprietary Large Language Models (LLMs) such as GPT and Claude series, LLMs have the potential to achieve remarkable proficiency across a wide range of doma…
CFBench: A Comprehensive Constraints-Following Benchmark for LLMs
Tao Zhang, Chenglin Zhu, Yanjun Shen +10
The adeptness of Large Language Models (LLMs) in comprehending and following natural language instructions is critical for their deployment in sophisticated real-world applications…