activity
20242026
collaborators

5 papers

cs.CL2026

Steering at the Source: Style Modulation Heads for Robust Persona Control

Yoshihiro Izawa, Gouki Minegishi, Koshi Eguchi +2

Activation steering offers a computationally efficient mechanism for controlling Large Language Models (LLMs) without fine-tuning. While effectively controlling target traits (e.g.…

cs.DC2026

GTaP: A GPU-Resident Fork-Join Task-Parallel System with a Pragma-Based Interface

Yuki Maeda, Kenjiro Taura

Graphics Processing Units (GPUs) excel at regular data-parallel workloads. In contrast, many irregular workloads are naturally expressed using fork-join task parallelism, which is…

cs.CL2025

Importance-Aware Data Selection for Efficient LLM Instruction Tuning

Tingyu Jiang, Shen Li, Yiyao Song +6

Instruction tuning plays a critical role in enhancing the performance and efficiency of Large Language Models (LLMs). Its success depends not only on the quality of the instruction…

cs.LG2025

How Different from the Past? Spatio-Temporal Time Series Forecasting with Self-Supervised Deviation Learning

Haotian Gao, Zheng Dong, Jiawei Yong +3

Spatio-temporal forecasting is essential for real-world applications such as traffic management and urban computing. Although recent methods have shown improved accuracy, they ofte…

cs.LG2024

Extracting Spatiotemporal Data from Gradients with Large Language Models

Lele Zheng, Yang Cao, Renhe Jiang +4

Recent works show that sensitive user data can be reconstructed from gradient updates, breaking the key privacy promise of federated learning. While success was demonstrated primar…