collaborators

6 papers

cs.AI2026

SafePyramid: A Hierarchical Benchmark for In-context Policy Guardrailing

Jiacheng Zhang, Haoyu He, Sen Zhang +5

In real-world applications, guardrails are often expected to identify unsafe user-model interactions according to application-specific safety policies, rather than relying on prede…

cs.SD2026

PhyAVBench: A Challenging Audio Physics-Sensitivity Benchmark for Physically Grounded Text-to-Audio-Video Generation

Tianxin Xie, Wentao Lei, Kai Jiang +27

Text-to-audio-video (T2AV) generation is central to applications such as filmmaking and world modeling. However, current models often fail to produce physically plausible sounds. P…

cs.CV2026

NeXT-IMDL: Build Benchmark for NeXT-Generation Image Manipulation Detection & Localization

Yifei Li, Haoyuan He, Yu Zheng +5

The accessibility surge and abuse risks of user-friendly image editing models have created an urgent need for generalizable, up-to-date methods for Image Manipulation Detection and…

cs.CR2025

MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrieval

Saksham Sahai Srivastava, Haoyu He

Large Language Model (LLM) agents increasingly rely on long-term memory and Retrieval-Augmented Generation (RAG) to persist experiences and refine future performance. While this ex…

cs.LG2025

MDPO: Overcoming the Training-Inference Divide of Masked Diffusion Language Models

Haoyu He, Katrin Renz, Yong Cao +1

Diffusion language models, as a promising alternative to traditional autoregressive (AR) models, enable faster generation and richer conditioning on bidirectional context. However,…

cs.CL2025

Scholar Inbox: Personalized Paper Recommendations for Scientists

Markus Flicke, Glenn Angrabeit, Madhav Iyengar +10

Scholar Inbox is a new open-access platform designed to address the challenges researchers face in staying current with the rapidly expanding volume of scientific literature. We pr…