6 papers
Video Models Can Reason with Verifiable Rewards
Tinghui Zhu, Sheng Zhang, James Y. Huang +5
Video diffusion models have made rapid progress in perceptual realism and temporal coherence, but they remain primarily optimized for plausible generation rather than verifiable re…
Be My Eyes: Extending Large Language Models to New Modalities Through Multi-Agent Collaboration
James Y. Huang, Sheng Zhang, Qianchu Liu +5
Large Language Models (LLMs) have demonstrated remarkable capabilities in challenging, knowledge-intensive reasoning tasks. However, extending LLMs to perceive and reason over a ne…
OmniStruct: Universal Text-to-Structure Generation across Diverse Schemas
James Y. Huang, Wenxuan Zhou, Nan Xu +5
The ability of Large Language Models (LLMs) to generate structured outputs that follow arbitrary schemas is crucial to a wide range of downstream tasks that require diverse structu…
DeAL: Decoding-time Alignment for Large Language Models
James Y. Huang, Sailik Sengupta, Daniele Bonadiman +6
Large Language Models (LLMs) are nowadays expected to generate content aligned with human preferences. Current work focuses on alignment at model training time, through techniques…
Offset Unlearning for Large Language Models
James Y. Huang, Wenxuan Zhou, Fei Wang +4
Despite the strong capabilities of Large Language Models (LLMs) to acquire knowledge from their training corpora, the memorization of sensitive information in the corpora such as c…
MetaScale: Test-Time Scaling with Evolving Meta-Thoughts
Qin Liu, Wenxuan Zhou, Nan Xu +5
One critical challenge for large language models (LLMs) for making complex reasoning is their reliance on matching reasoning patterns from training data, instead of proactively sel…