collaborators

12 papers

cs.CL2026

WPG-MoE: Weak-Prior-Guided Dense Mixture-of-Experts for User-Level Social Media Depression Detection

Xian Li, Yuanhe Tian, Yang Yang +2

Online social media posts provide scalable signals for early depression screening, and recent studies mainly improve pre-classification evidence through risk-post selection, sympto…

cs.CV2026

Recent Advances in Multi-modal 3D Intelligence: A Comprehensive Survey and Evaluation

Yinjie Lei, Zixuan Wang, Feng Chen +3

Multi-modal 3D Intelligence has gained considerable attention due to its wide applications in autonomous driving and world simulation, etc. Compared to conventional single-modal 3D…

cs.AI2026

Understanding Chain-of-Thought in Large Language Models via Topological Data Analysis

Chenghao Li, Chaoning Zhang, Yi Lu +10

With the development of large language models (LLMs), particularly with the introduction of the long reasoning chain technique, the reasoning ability of LLMs in complex problem-sol…

cs.CV2026

GeoPurify: A Data-Efficient Geometric Distillation Framework for Open-Vocabulary 3D Segmentation

Weijia Dou, Xu Zhang, Yi Bin +5

Recent attempts to transfer features from 2D Vision-Language Models (VLMs) to 3D semantic segmentation expose a persistent trade-off. Directly projecting 2D features into 3D yields…

cs.CV2025

Fast SAM2 with Text-Driven Token Pruning

Avilasha Mandal, Chaoning Zhang, Fachrina Dewi Puspitasari +6

Segment Anything Model 2 (SAM2), a vision foundation model has significantly advanced in prompt-driven video object segmentation, yet their practical deployment remains limited by…

cs.CL2025

Syzygy of Thoughts: Improving LLM CoT with the Minimal Free Resolution

Chenghao Li, Chaoning Zhang, Yi Lu +7

Chain-of-Thought (CoT) prompting enhances the reasoning of large language models (LLMs) by decomposing problems into sequential steps, mimicking human logic and reducing errors. Ho…