12 papers
MolViBench: Evaluating LLMs on Molecular Vibe Coding
Jiatong Li, Yuxuan Ren, Weida Wang +4
Molecular Vibe Coding, a paradigm where chemists interact with LLMs to generate executable programs for molecular tasks, has emerged as a flexible alternative to chemical agents wi…
Mol-Debate: Multi-Agent Debate Improves Structural Reasoning in Molecular Design
Wengyu Zhang, Xiao-Yong Wei, Qing Li
Text-guided molecular design is a key capability for AI-driven drug discovery, yet it remains challenging to map sequential natural-language instructions with non-linear molecular…
Adaptive Multi-Agent Reasoning for Text-to-Video Retrieval
Jiaxin Wu, Xiao-Yong Wei, Qing Li
The rise of short-form video platforms and the emergence of multimodal large language models (MLLMs) have amplified the need for scalable, effective, zero-shot text-to-video retrie…
MarkovScale: Towards Optimal Sequential Scaling at Inference Time
Youkang Wang, Jian Wang, Rubing Chen +3
Sequential scaling is a prominent inference-time scaling paradigm, yet its performance improvements are typically modest and not well understood, largely due to the prevalence of h…
To Retrieve or To Think? Cross-Boundary Context Evolution for Multi-hop Complex Reasoning
Rubing Chen, Jian Wang, Wenjie Li +2
Current context augmentation methods, such as retrieval-augmented generation, play a crucial role in bridging a model's internal knowledge boundary and external evidence for multi-…
OptPO: Optimal Rollout Allocation for Test-time Policy Optimization
Youkang Wang, Jian Wang, Rubing Chen +3
Test-time policy optimization enables large language models (LLMs) to adapt to distribution shifts by leveraging feedback from self-generated rollouts. However, existing methods re…
OptScale: Probabilistic Optimality for Inference-time Scaling
Youkang Wang, Jian Wang, Rubing Chen +1
Inference-time scaling has emerged as a powerful technique for enhancing the reasoning performance of Large Language Models (LLMs). However, existing approaches often rely on heuri…
Seeing Beyond the Scene: Enhancing Vision-Language Models with Interactional Reasoning
Dayong Liang, Changmeng Zheng, Zhiyuan Wen +3
Traditional scene graphs primarily focus on spatial relationships, limiting vision-language models' (VLMs) ability to reason about complex interactions in visual scenes. This paper…
Cardiac Evidence Backtracking for Eating Behavior Monitoring using Collocative Electrocardiogram Imagining
Xu-Lu Zhang, Zhen-Qun Yang, Dong-Mei Jiang +4
Eating monitoring has remained an open challenge in medical research for years due to the lack of non-invasive sensors for continuous monitoring and the reliable methods for automa…
PolySmart @ TRECVid 2024 Video Captioning (VTT)
Jiaxin Wu, Wengyu Zhang, Xiao-Yong Wei +1
In this paper, we present our methods and results for the Video-To-Text (VTT) task at TRECVid 2024, exploring the capabilities of Vision-Language Models (VLMs) like LLaVA and LLaVA…
PolySmart @ TRECVid 2024 Medical Video Question Answering
Jiaxin Wu, Yiyang Jiang, Xiao-Yong Wei +1
Video Corpus Visual Answer Localization (VCVAL) includes question-related video retrieval and visual answer localization in the videos. Specifically, we use text-to-text retrieval…
PolySmart and VIREO @ TRECVid 2024 Ad-hoc Video Search
Jiaxin Wu, Chong-Wah Ngo, Xiao-Yong Wei +1
This year, we explore generation-augmented retrieval for the TRECVid AVS task. Specifically, the understanding of textual query is enhanced by three generations, including Text2Tex…