activity
20242026
collaborators

6 papers

cs.LG2026

Dual-Modality Multi-Stage Adversarial Safety Training: Robustifying Multimodal Web Agents Against Cross-Modal Attacks

Haoyu Liu, Dingcheng Li, Lukas Rutishauser +1

Multimodal web agents that process both screenshots and accessibility trees are increasingly deployed to interact with web interfaces, yet their dual-stream architecture opens an u…

cs.CV2026

Spiral RoPE: Rotate Your Rotary Positional Embeddings in the 2D Plane

Haoyu Liu, Sucheng Ren, Tingyu Zhu +5

Rotary Position Embedding (RoPE) is the de facto positional encoding in large language models due to its ability to encode relative positions and support length extrapolation. When…

cs.CL2025

IDA-Bench: Evaluating LLMs on Interactive Guided Data Analysis

Hanyu Li, Haoyu Liu, Tingyu Zhu +4

Large Language Models (LLMs) show promise as data analysis agents, but existing benchmarks overlook the iterative nature of the field, where experts' decisions evolve with deeper i…

cs.SD2025

Efficient Fine-Grained Guidance for Diffusion Model Based Symbolic Music Generation

Tingyu Zhu, Haoyu Liu, Ziyu Wang +2

Developing generative models to create or conditionally create symbolic music presents unique challenges due to the combination of limited data availability and the need for high p…

cs.LG2024

Structured Diffusion Models with Mixture of Gaussians as Prior Distribution

Nanshan Jia, Tingyu Zhu, Haoyu Liu +1

We propose a class of structured diffusion models, in which the prior distribution is chosen as a mixture of Gaussians, rather than a standard Gaussian distribution. The specific m…

cs.DC2024

A Preliminary Study on Accelerating Simulation Optimization with GPU Implementation

Jinghai He, Haoyu Liu, Yuhang Wu +2

We provide a preliminary study on utilizing GPU (Graphics Processing Unit) to accelerate computation for three simulation optimization tasks with either first-order or second-order…