6 papers
Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation
Xianhao Zhou, Jianghao Wu
Natural-language descriptions have become a flexible interface for controlling generated speech. Existing evaluations largely assess whether an output matches a prompt, but prompt…
Single-Rollout Hidden-State Dynamics for Training-Free RLVR Data Selection
Jianghao Wu, Jianfei Cai, Weiqiang Wang +3
Reinforcement learning with verifiable rewards (RLVR) can yield large reasoning gains from very few training instances, yet its strong sensitivity to which instances are used makes…
SelfAI: A self-directed framework for long-horizon scientific discovery
Xiao Wu, Ting-Zhu Huang, Liang-Jian Deng +9
Scientific discovery increasingly entails long-horizon exploration of complex hypothesis spaces, yet most existing approaches emphasize final performance while offering limited ins…
SAM-aware Test-time Adaptation for Universal Medical Image Segmentation
Jianghao Wu, Yicheng Wu, Yutong Xie +7
Leveraging the Segment Anything Model (SAM) for medical image segmentation remains challenging due to its limited adaptability across diverse medical domains. Although fine-tuned v…
TAGS: A Test-Time Generalist-Specialist Framework with Retrieval-Augmented Reasoning and Verification
Jianghao Wu, Feilong Tang, Yulong Li +5
Recent advances such as Chain-of-Thought prompting have significantly improved large language models (LLMs) in zero-shot medical reasoning. However, prompting-based methods often r…
Beyond Words: AuralLLM and SignMST-C for Sign Language Production and Bidirectional Accessibility
Yulong Li, Yuxuan Zhang, Feilong Tang +10
Sign language is the primary communication mode for 72 million hearing-impaired individuals worldwide, necessitating effective bidirectional Sign Language Production and Sign Langu…