68 citations · 78 across the 13 of their papers we have counts for
13 papers
CLT-Forge: A Scalable Library for Cross-Layer Transcoders and Attribution Graphs
Florent Draye, Vedant Palit, Abir Harrasse +8
Mechanistic interpretability seeks to understand how Large Language Models (LLMs) represent and process information. Recent approaches based on dictionary learning and transcoders…
Position: Token Taxes Can Mitigate AI's Economic Risks
Lucas Irwin, Tung-Yu Wu, Fazl Barez
AI-driven automation threatens to erode government tax bases, lower living standards, and disempower citizens--risks that mirror the 40-year stagnation of wages during the first in…
Query Circuits: Explaining How Language Models Answer User Prompts
Tung-Yu Wu, Fazl Barez
Explaining why a language model produces a particular output requires local, input-level explanations. Existing methods uncover global capability circuits (e.g., indirect object id…
U-shaped and Inverted-U Scaling behind Emergent Abilities of Large Language Models
Tung-Yu Wu, Pei-Yu Lo
Large language models (LLMs) have been shown to exhibit emergent abilities in some downstream tasks, where model performance stagnates at first and then improves sharply and unpred…
AND: Audio Network Dissection for Interpreting Deep Acoustic Models
Tung-Yu Wu, Yu-Xiang Lin, Tsui-Wei Weng
Neuron-level interpretations aim to explain network behaviors and properties by investigating neurons responsive to specific perceptual or structural input patterns. Although there…
Data-Efficient 3D Visual Grounding via Order-Aware Referring
Tung-Yu Wu, Sheng-Yu Huang, Yu-Chiang Frank Wang
3D visual grounding aims to identify the target object within a 3D point cloud scene referred to by a natural language description. Previous works usually require significant data…
Model Extraction Attack against Self-supervised Speech Models
Tsu-Yuan Hsu, Chen-An Li, Tung-Yu Wu +1
Self-supervised learning (SSL) speech models generate meaningful representations of given clips and achieve incredible performance across various downstream tasks. Model extraction…
The Efficacy of Self-Supervised Speech Models for Audio Representations
Tung-Yu Wu, Chen-An Li, Tzu-Han Lin +2
Self-supervised learning (SSL) speech models, which can serve as powerful upstream models to extract meaningful speech representations, have achieved unprecedented success in speec…
Locally Interpretable One-Class Anomaly Detection for Credit Card Fraud Detection
Tungyu Wu, Youting Wang
For the highly imbalanced credit card fraud detection problem, most existing methods either use data augmentation methods or conventional machine learning models, while neural netw…
Mini-batch Metropolis-Hastings MCMC with Reversible SGLD Proposal
Tung-Yu Wu, Y. X. Rachel Wang, Wing H. Wong
Traditional MCMC algorithms are computationally intensive and do not scale well to large data. In particular, the Metropolis-Hastings (MH) algorithm requires passing over the entir…
Convergence of Contrastive Divergence with Annealed Learning Rate in Exponential Family
Bai Jiang, Tung-yu Wu, Wing H. Wong
In our recent paper, we showed that in exponential family, contrastive divergence (CD) with fixed learning rate will give asymptotically consistent estimates \cite{wu2016convergenc…
Convergence of Contrastive Divergence Algorithm in Exponential Family
Bai Jiang, Tung-Yu Wu, Yifan Jin +1
The Contrastive Divergence (CD) algorithm has achieved notable success in training energy-based models including Restricted Boltzmann Machines and played a key role in the emergenc…
Learning Summary Statistic for Approximate Bayesian Computation via Deep Neural Network
Bai Jiang, Tung-yu Wu, Charles Zheng +1
Approximate Bayesian Computation (ABC) methods are used to approximate posterior distributions in models with unknown or computationally intractable likelihoods. Both the accuracy…