Search Results for author:
Found 11 papers, 7 papers with code
EAR: Erasing Concepts from Unified Autoregressive Models
In this paper, we propose Erasure Autoregressive Model (EAR), a fine-tuning method for effective and utility-preserving concept erasure in AR models.
AI Agent Behavioral Science
Recent advances in large language models (LLMs) have enabled the development of AI agents that exhibit increasingly human-like behaviors, including planning, adaptation, and social dynamics across diverse, interactive, and open-ended scenarios.
Taming Hyperparameter Sensitivity in Data Attribution: Practical Selection Without Costly Retraining
Data attribution methods, which quantify the influence of individual training data points on a machine learning model, have gained increasing popularity in data-centric applications in modern AI.
TimeCausality: Evaluating the Causal Ability in Time Dimension for Vision Language Models
Based on our TimeCausality, we find that while the current SOTA open-source VLMs have achieved performance levels comparable to closed-source models like GPT-4o on various standard visual question answering tasks, they fall significantly behind on our benchmark compared with their closed-source competitors.
Energy-Weighted Flow Matching for Offline Reinforcement Learning
To overcome this limitation, we explore energy-guided flow matching, a generalized form of the diffusion process.
FoMo: A Foundation Model for Mobile Traffic Forecasting with Diffusion Model
Mobile traffic forecasting allows operators to anticipate network dynamics and performance in advance, offering substantial potential for enhancing service quality and improving user experience.
$\texttt{dattri}$: A Library for Efficient Data Attribution
Using the developed $\texttt{dattri}$ library, we are able to perform a comprehensive and fair benchmark analysis across a wide range of data attribution methods.
Computational Copyright: Towards A Royalty Model for Music Generative AI
This research is one of the early attempts to integrate technical advancements with economic and legal considerations in the field of music generative AI, offering a computational copyright solution for the challenges posed by the opaque nature of AI technologies.
Joint Activity Recognition and Indoor Localization With WiFi Fingerprints
In this paper, we propose a novel deep learning framework for joint activity recognition and indoor localization task using WiFi Channel State Information~(CSI) fingerprints.
Joint Activity Recognition and Indoor Localization
The key rationale behind this type of work is that people behaviors can influence the WiFi signal propagation and introduce specific patterns into WiFi signals, called WiFi fingerprints, which further can be explored to identify human activities and locations.
Human-Computer Interaction
CSI-Net: Unified Human Body Characterization and Pose Recognition
We build CSI-Net, a unified Deep Neural Network~(DNN), to learn the representation of WiFi signals.
