Wang, Ping

The Dark Side of Function Calling: Pathways to Jailbreaking Large Language Models

Large language models (LLMs) have demonstrated remarkable capabilities, but their power comes with significant security considerations. While extensive research has been conducted on the safety of...

HELM: Steering Long-Horizon Agents with Learned Hierarchical Memory and Epistemic Governance

Expanding the Solvable Frontier: Policy-Adaptive Curriculum Learning for Reasoning RL

FLUID-V: Elastic-Horizon Diffusion Decoding for Vision-Language Models

From Passive Response to Proactive Correction: Enhancing LLM Robustness Against Input Fact Perturbations

LeafNATS: An Open-Source Toolkit and Live Demo System for Neural Abstractive Text Summarization

Few-Shot Text Classification with Edge-Labeling Graph Neural Network-Based Prototypical Network

Adaptive Graph Convolutional Network for Knowledge Graph Entity Alignment

Hypergraph based Understanding for Document Semantic Entity Recognition

VHASR: A Multimodal Speech Recognition System With Vision Hotwords

The Music Maestro or The Musically Challenged, A Massive Music Evaluation Benchmark for Large Language Models

Selective Prefix Tuning for Pre-trained Language Models

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers

Dialogue-RAG: Enhancing Retrieval for LLMs via Node-Linking Utterance Rewriting

A Simple yet Efficient Prompt Compression Method for Text Classification Data Annotation Using LLM

The Dark Side of Function Calling: Pathways to Jailbreaking Large Language Models

Can Large Language Models Be Good Language Teachers?

Surprise Calibration for Better In-Context Learning