5 papers · 1 filter
MindCraft: How Concept Trees Take Shape In Deep Models
Bowei Tian, Yexiao He, Wanghao Ye +3
Large-scale foundation models demonstrate strong performance across language, vision, and reasoning tasks. However, how they internally structure and stabilize concepts remains elu…
Predictive Auditing of Hidden Tokens in LLM APIs via Reasoning Length Estimation
Ziyao Wang, Guoheng Sun, Yexiao He +3
Commercial LLM services often conceal internal reasoning traces while still charging users for every generated token, including those from hidden intermediate steps, raising concer…
Why Representation Engineering Works: A Theoretical and Empirical Study in Vision-Language Models
Bowei Tian, Xuntao Lyu, Meng Liu +2
Representation Engineering (RepE) has emerged as a powerful paradigm for enhancing AI transparency by focusing on high-level representations rather than individual neurons or circu…
Towards counterfactual fairness through auxiliary variables
Bowei Tian, Ziyao Wang, Shwai He +5
The challenge of balancing fairness and predictive accuracy in machine learning models, especially when sensitive attributes such as race, gender, or age are considered, has motiva…
Revisiting Federated Fine-Tuning: A Single Communication Round is Enough for Foundation Models
Ziyao Wang, Bowei Tian, Yexiao He +6
The recent advancement of foundation models (FMs) has increased the demand for fine-tuning these models on large-scale cross-domain datasets. To address this, federated fine-tuning…