6 papers
Storage Is Not Strategy: State-Conditioned Support Control for LLM Unlearning
Tianhao Qian, Ziming Hong, Chongyang Gao +2
Many localized large language model (LLM) unlearning methods select a small parameter subset from a localization signal and keep it fixed during optimization. The parameters most a…
Relative Kinetic Utility: Calibrating Cross-Layer Credit for Global Structured LLM Pruning
Tianhao Qian, Guilin Qi, Jiayu Chen
Global structured pruning requires channels from different layers to compete under a shared sparsity budget, raising two coupled challenges: identifying which channels should be re…
Resource-constrained Amazons chess decision framework integrating large language models and graph attention
Tianhao Qian, Zhuoxuan Li, Jinde Cao +2
Artificial intelligence has advanced significantly through the development of intelligent game-playing systems, providing rigorous testbeds for decision-making, strategic planning,…
PAC-CF: Calibrating Irreversible Frontier Pruning in LLM-Guided Search
Tianhao Qian, Jiayu Chen, Lixu Wang +1
LLM-guided search explores multiple candidate trajectories, but at substantial test-time cost. Pruning low-scoring frontier candidates can control this cost, yet it also turns pote…
Alternating Gradient Flow Utility: A Unified Metric for Structural Pruning and Dynamic Routing in Deep Networks
Tianhao Qian, Zhuoxuan Li, Jinde Cao +2
Efficient deep learning traditionally relies on static heuristics like weight magnitude or activation awareness (e.g., Wanda, RIA). While successful in unstructured settings, we ob…
Large Language Model for Discrete Optimization Problems: Evaluation and Step-by-step Reasoning
Tianhao Qian, Guilin Qi, Z. Y. Wu +3
This work investigated the capabilities of different models, including the Llama-3 series of models and CHATGPT, with different forms of expression in solving discrete optimization…