13 papers
One Analyst Is Not Ground Truth: Grading Agent-Built Financial Models Against Observed Professional Practice
Jiacheng Lu, Sinuo Wang, Yiming Li +15
Language model agents can now construct complete financial models, but it remains unclear whether they have learned the financial judgment that gives those models meaning. Existing…
Echoes within the Reasoning: Stealthy and Effective Watermarking via Chain of Thought
Jiacheng Lu, Yiming Li, Tao Song +4
Large Language Models with Chain-of-Thought reasoning capabilities represent valuable intellectual property, yet existing black-box watermarking methods often trade robustness for…
FedMomentum: Preserving LoRA Training Momentum in Federated Fine-Tuning
Peishen Yan, Yang Hua, Hao Wang +4
Federated fine-tuning of large language models (LLMs) with low-rank adaptation (LoRA) offers a communication-efficient and privacy-preserving solution for task-specific adaptation.…
SettleFL: Trustless and Scalable Reward Settlement Protocol for Federated Learning on Permissionless Blockchains (Extended version)
Shuang Liang, Yang Hua, Linshan Jiang +4
In open Federated Learning (FL) environments where no central authority exists, ensuring collaboration fairness relies on decentralized reward settlement, yet the prohibitive cost…
pFedNavi: Structure-Aware Personalized Federated Vision-Language Navigation for Embodied AI
Qingqian Yang, Hao Wang, Sai Qian Zhang +6
Vision-Language Navigation VLN requires large-scale trajectory instruction data from private indoor environments, raising significant privacy concerns. Federated Learning FL mitiga…
POLAR: Policy-based Layerwise Reinforcement Learning Method for Stealthy Backdoor Attacks in Federated Learning
Kuai Yu, Xiaoyu Wu, Peishen Yan +6
Federated Learning (FL) enables decentralized model training across multiple clients without exposing local data, but its distributed feature makes it vulnerable to backdoor attack…
Learning Identifiable Structures Helps Avoid Bias in DNN-based Supervised Causal Learning
Jiaru Zhang, Rui Ding, Qiang Fu +6
Causal discovery is a structured prediction task that aims to predict causal relations among variables based on their data samples. Supervised Causal Learning (SCL) is an emerging…
THOR: A Generic Energy Estimation Approach for On-Device Training
Jiaru Zhang, Zesong Wang, Hao Wang +8
Battery-powered mobile devices (e.g., smartphones, AR/VR glasses, and various IoT devices) are increasingly being used for AI training due to their growing computational power and…
FedCod: An Efficient Communication Protocol for Cross-Silo Federated Learning with Coding
Peishen Yan, Jun Li, Hao Wang +4
Federated Learning (FL) is an innovative distributed machine learning paradigm that enables multiple parties to collaboratively train a model without sharing their raw data, thereb…
M3TR: Temporal Retrieval Enhanced Multi-Modal Micro-video Popularity Prediction
Jiacheng Lu, Weijian Wang, Mingyuan Xiao +5
Accurately predicting the popularity of micro-videos is a critical but challenging task, characterized by volatile, `rollercoaster-like' engagement dynamics. Existing methods often…
Poisoning with A Pill: Circumventing Detection in Federated Learning
Hanxi Guo, Hao Wang, Tao Song +4
Without direct access to the client's data, federated learning (FL) is well-known for its unique strength in data privacy protection among existing distributed machine learning tec…
Exploring Diffusion Models' Corruption Stage in Few-Shot Fine-tuning and Mitigating with Bayesian Neural Networks
Xiaoyu Wu, Jiaru Zhang, Yang Hua +4
Few-shot fine-tuning of Diffusion Models (DMs) is a key advancement, significantly reducing training costs and enabling personalized AI applications. However, we explore the traini…
CGI-DM: Digital Copyright Authentication for Diffusion Models via Contrasting Gradient Inversion
Xiaoyu Wu, Yang Hua, Chumeng Liang +4
Diffusion Models (DMs) have evolved into advanced image generation tools, especially for few-shot generation where a pretrained model is fine-tuned on a small set of images to capt…