Publications (18)
FRAME: Feedback-Refined Agent Methodology for Enhancing Medical Research Insights
Chengzhang Yu, Yiming Zhang, Zhixin Liu +3
The automation of scientific research through large language models (LLMs) presents significant opportunities but faces critical challenges in knowledge synthesis and quality assur…
RankCLIP: Ranking-Consistent Language-Image Pretraining
Yiming Zhang, Zhuokai Zhao, Zhaorun Chen +3
Self-supervised contrastive learning models, such as CLIP, have set new benchmarks for vision-language models in many downstream tasks. However, their dependency on rigid one-to-on…
Information Bottleneck Revisited: Posterior Probability Perspective with Optimal Transport
Lingyi Chen, Shitong Wu, Wenhao Ye +5
Information bottleneck (IB) is a paradigm to extract information in one target random variable from another relevant random variable, which has aroused great interest due to its po…
-Generalized Hessian pre-Lie algebras and -Generalized Yang--Baxter Equations
Yining Sun, Zeyu Hao, Ziyi Zhang +1
Inspired by the problem of constructing (-)pre-Lie algebra structures on the dual space of a pre-Lie algebra, we introduce the \(A\)-generalized Yang--Baxter equation as a gene…
Pair-Instability Gap Black Holes in Population III Star Clusters: Pathways, Dynamics, and Gravitational Wave Implications
Weiwei Wu, Long Wang, Shuai Liu +3
The detection of the gravitational wave (GW) event GW190521 raises questions about the formation of black holes within the pair-instability mass gap (PIBHs). We propose that Popula…
Beyond Training: Dynamic Token Merging for Zero-Shot Video Understanding
Yiming Zhang, Zhuokai Zhao, Zhaorun Chen +3
Recent advancements in multimodal large language models (MLLMs) have opened new avenues for video understanding. However, achieving high fidelity in zero-shot video tasks remains c…