152 citations · 226 across the 15 of their papers we have counts for
17 papers
Doing More with Less Tokens: Hierarchical Reinforcement Learning for Efficient Coding Agents
Haobin Li, Liang Jiang, Zhenyu Huang +2
Recently, coding agents have emerged as a dominant paradigm for real-world software engineering (SWE) scenarios, which solve complex tasks through multi-turn interactions with deve…
Imagine Before Acting: Prospective Skill Identification for LLM Agents
Shuo Liu, Yutong Yang, Haohao Xiao +2
Effective skill identification is crucial for LLM agents to reuse task-solving experience for complex task execution, which however remains challenging as agents must accurately id…
Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports
Haobin Li, Ping Deng, Weizhong Qian +4
Coding agents powered by large language models (LLMs) are increasingly adopted in software engineering (SWE) scenarios, capable of fixing a specific bug in large-scale codebase. Ho…
Robust Multi-view Clustering against Imperfect Information
Zhichao Huang, Haochen Zhou, Hao Wang +2
Real-world multi-view data always suffer from imperfect information problem, where the view-specific observations are absent (i.e., Incomplete Views, IV) and cross-view corresponde…
Reliable Thinking with Images
Haobin Li, Yutong Yang, Yijie Lin +3
As a multimodal extension of Chain-of-Thought (CoT), Thinking with Images (TWI) has recently emerged as a promising avenue to enhance the reasoning capability of Multi-modal Large…
ARK: A Dual-Axis Multimodal Retrieval Benchmark along Reasoning and Knowledge
Yijie Lin, Guofeng Ding, Haochen Zhou +3
Existing multimodal retrieval benchmarks largely emphasize semantic matching on daily-life images and offer limited diagnostics of professional knowledge and complex reasoning. To…
Toward Robust and Harmonious Adaptation for Cross-modal Retrieval
Haobin Li, Mouxing Yang, Xi Peng
Recently, the general-to-customized paradigm has emerged as the dominant approach for Cross-Modal Retrieval (CMR), which reconciles the distribution shift problem between the sourc…
Learning with Dual-level Noisy Correspondence for Multi-modal Entity Alignment
Haobin Li, Yijie Lin, Peng Hu +2
Multi-modal entity alignment (MMEA) aims to identify equivalent entities across heterogeneous multi-modal knowledge graphs (MMKGs), where each entity is described by attributes fro…
LLaVA-ReID: Selective Multi-image Questioner for Interactive Person Re-Identification
Yiding Lu, Mouxing Yang, Dezhong Peng +3
Traditional text-based person ReID assumes that person descriptions from witnesses are complete and provided at once. However, in real-world scenarios, such descriptions are often…
Learning Locally, Revising Globally: Global Reviser for Federated Learning with Noisy Labels
Yuxin Tian, Mouxing Yang, Yuhao Zhou +5
Conventional federated learning (FL) heavily depends on high-quality labels, which are often impractical in the real world, leading to the federated label-noise (F-LN) problem. Wor…
Test-time Adaptation for Cross-modal Retrieval with Query Shift
Haobin Li, Peng Hu, Qianjun Zhang +3
The success of most existing cross-modal retrieval methods heavily relies on the assumption that the given queries follow the same distribution of the source domain. However, such…
An Empirical Study of Parameter Efficient Fine-tuning on Vision-Language Pre-train Model
Yuxin Tian, Mouxing Yang, Yunfan Li +4
Recent studies applied Parameter Efficient Fine-Tuning techniques (PEFTs) to efficiently narrow the performance gap between pre-training and downstream. There are two important fac…
Decoupled Contrastive Multi-View Clustering with High-Order Random Walks
Yiding Lu, Yijie Lin, Mouxing Yang +3
In recent, some robust contrastive multi-view clustering (MvC) methods have been proposed, which construct data pairs from neighborhoods to alleviate the false negative issue, i.e.…
Semantic Invariant Multi-view Clustering with Fully Incomplete Information
Pengxin Zeng, Mouxing Yang, Yiding Lu +3
Robust multi-view learning with incomplete information has received significant attention due to issues such as incomplete correspondences and incomplete instances that commonly af…
Incomplete Multi-view Clustering via Prototype-based Imputation
Haobin Li, Yunfan Li, Mouxing Yang +3
In this paper, we study how to achieve two characteristics highly-expected by incomplete multi-view clustering (IMvC). Namely, i) instance commonality refers to that within-cluster…
Graph Matching with Bi-level Noisy Correspondence
Yijie Lin, Mouxing Yang, Jun Yu +3
In this paper, we study a novel and widely existing problem in graph matching (GM), namely, Bi-level Noisy Correspondence (BNC), which refers to node-level noisy correspondence (NN…
Twin Contrastive Learning for Online Clustering
Yunfan Li, Mouxing Yang, Dezhong Peng +3
This paper proposes to perform online clustering by conducting twin contrastive learning (TCL) at the instance and cluster level. Specifically, we find that when the data is projec…