5 papers
HyperGuide: Hyperbolic Guidance for Efficient Multi-Step Reasoning in Large Language Models
Yuyu Liu, Haotian Xu, Yanan He +3
Multi-step reasoning remains a central challenge for large language models: single-pass generation is efficient but lacks accuracy; tree-search methods explore multiple paths but a…
Resting Neurons, Active Insights: Robustifying Activation Sparsity in LLMs via Spontaneity
Haotian Xu, Jiannan Yang, Tian Gao +2
Activation sparsity offers a compelling route to accelerate large language model (LLM) inference by selectively suppressing hidden activations, yet existing approaches exhibit seve…
When Structure Doesn't Help: LLMs Do Not Read Text-Attributed Graphs as Effectively as We Expected
Haotian Xu, Yuning You, Tengfei Ma
Graphs provide a unified representation of semantic content and relational structure, making them a natural fit for domains such as molecular modeling, citation networks, and socia…
Concept-Guided Backdoor Attack on Vision Language Models
Haoyu Shen, Weimin Lyu, Haotian Xu +1
Vision-Language Models (VLMs) have achieved impressive progress in multimodal text generation, yet their rapid adoption raises increasing concerns about security vulnerabilities. E…
FCOS: A Two-Stage Recoverable Model Pruning Framework for Automatic Modulation Recognition
Yao Lu, Tengfei Ma, Zeyu Wang +5
With the rapid development of wireless communications and the growing complexity of digital modulation schemes, traditional manual modulation recognition methods struggle to extrac…