activity
20172025
most citedRecent Advance in Content-based Image Retrieval: A Literature Survey

162 citations · 680 across the 95 of their papers we have counts for

collaborators

73 papers

cs.CV2025

VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal Large Language Models

Weiye Xu, Jiahao Wang, Weiyun Wang +10

Visual reasoning is a core component of human intelligence and a critical capability for advanced multimodal models. Yet current reasoning evaluations of multimodal large language…

cs.CV2025

Cross-Modal Consistency Learning for Sign Language Recognition

Kepeng Wu, Zecheng Li, Hezhen Hu +2

Pre-training has been proven to be effective in boosting the performance of Isolated Sign Language Recognition (ISLR). Existing pre-training methods solely focus on the compact pos…

cs.CV2025

Multi-Cue Adaptive Visual Token Pruning for Large Vision-Language Models

Bozhi Luan, Wengang Zhou, Hao Feng +3

As the computational needs of Large Vision-Language Models (LVLMs) increase, visual token pruning has proven effective in improving inference speed and memory efficiency. Tradition…

cs.CV2025

DesignDiffusion: High-Quality Text-to-Design Image Generation with Diffusion Models

Zhendong Wang, Jianmin Bao, Shuyang Gu +3

In this paper, we present DesignDiffusion, a simple yet effective framework for the novel task of synthesizing design images from textual descriptions. A primary challenge lies in…

cs.AI2025

Model Evolution Framework with Genetic Algorithm for Multi-Task Reinforcement Learning

Yan Yu, Wengang Zhou, Yaodong Yang +3

Multi-task reinforcement learning employs a single policy to complete various tasks, aiming to develop an agent with generalizability across different scenarios. Given the shared c…

cs.CL2025

Multi-Level Optimal Transport for Universal Cross-Tokenizer Knowledge Distillation on Language Models

Xiao Cui, Mo Zhu, Yulei Qin +3

Knowledge distillation (KD) has become a prevalent technique for compressing large language models (LLMs). Existing KD methods are constrained by the need for identical tokenizers…