10 papers
Improving Adversarial Transferability on Vision-Language Pre-training Models via Surrogate-Specific Bias Correction
Lijia Yu, Jiuxin Cao, Yuchen Qiang +3
Adversarial examples reveal vulnerabilities in Vision-Language Pre-training (VLP) models and provide insights for improving robustness. A key property is cross-model transferabilit…
EvoRubric: Self-Evolving Rubric-Driven RL for Open-Ended Generation
Xin Guan, Xiaomeng Hu, Shen Huang +6
Reinforcement Learning (RL) has significantly advanced Large Language Models (LLMs) in verifiable domains, but aligning models for open-ended generation remains profoundly challeng…
ViewSAM: Learning View-aware Cross-modal Semantics for Weakly Supervised Cross-view Referring Multi-Object Tracking
Jiawei Ge, Xintian Zhang, Jiuxin Cao +9
Cross-view Referring Multi-Object Tracking (CRMOT) aims to track multiple objects specified by natural language across multiple camera views, with globally consistent identities. D…
Debate-Enhanced Pseudo Labeling and Frequency-Aware Progressive Debiasing for Weakly-Supervised Camouflaged Object Detection with Scribble Annotations
Jiawei Ge, Jiuxin Cao, Xinyi Li +5
Weakly-Supervised Camouflaged Object Detection (WSCOD) aims to locate and segment objects that are visually concealed within their surrounding scenes, relying solely on sparse supe…
Evidence-Augmented Policy Optimization with Reward Co-Evolution for Long-Context Reasoning
Xin Guan, Zijian Li, Shen Huang +3
While Reinforcement Learning (RL) has advanced LLM reasoning, applying it to long-context scenarios is hindered by sparsity of outcome rewards. This limitation fails to penalize un…
DyTopo: Dynamic Topology Routing for Multi-Agent Reasoning via Semantic Matching
Yuxing Lu, Yucheng Hu, Xukai Zhao +1
Multi-agent systems built from prompted large language models can improve multi-round reasoning, yet most existing pipelines rely on fixed, trajectory-wide communication patterns t…