4 papers
CAST: History-Adaptive Spectral Clipping for LLM Pretraining
Jiacheng Li, Jianchao Tan, Kefeng Zhang +2
Soft spectral clipping (SSC) reduces gradient singular values, but its effect depends on the gradient scale and clipping threshold. We introduce CAST (Clipping with Adaptive Scales…
TimeRSI: Towards Self-Improved Agentic Deployment for Time-Series Foundation Models
Haoxin Liu, Deqing Fu, Lucheng Fu +4
Time-series foundation models provide strong zero-shot forecast, but deployment for real-world applications still requires task-specific designs for model inputs and outputs. Direc…
Training-Free BioNEL-RAG: Advancing Biomedical Entity Linking through Retrieval-Augmented Generation and Large Language Model
Ziyi Chen, Hui Liu, Ziyang Ling +2
Biomedical Named Entity Linking (BioNEL) is the task of mapping mentions extracted from biomedical texts to canonical entities or concepts in the standardized knowledge base. Altho…
Seeing but Not Believing: Probing the Disconnect Between Visual Attention and Answer Correctness in VLMs
Zhining Liu, Ziyi Chen, Hui Liu +9
Vision-Language Models (VLMs) achieve strong results on multimodal tasks such as visual question answering, yet they can still fail even when the correct visual evidence is present…