papers

Publications (68)

cs.CV2022

Scaling Autoregressive Models for Content-Rich Text-to-Image Generation

Jiahui Yu, Yuanzhong Xu, Jing Yu Koh +14

We present the Pathways Autoregressive Text-to-Image (Parti) model, which generates high-fidelity photorealistic images and supports content-rich synthesis involving complex compos…

cs.CV2019

Improving Object Detection from Scratch via Gated Feature Reuse

Zhiqiang Shen, Honghui Shi, Jiahui Yu +7

In this paper, we present a simple and parameter-efficient drop-in module for one-stage object detectors like SSD when learning from scratch (i.e., without pre-trained models). We…

cs.CV2020

Cross-Supervised Object Detection

Zitian Chen, Zhiqiang Shen, Jiahui Yu +1

After learning a new object category from image-level annotations (with no object bounding boxes), humans are remarkably good at precisely localizing those objects. However, buildi…

math.RT2023

Transfer of derived equivalences from subalgebras to endomorphism algebras II

Shengyong Pan, Jiahui Yu

We investigate derived equivalences between subalgebras of some -Auslander-Yoneda algebras from a class of -angles in weakly -angulated categories. The derived equivalenc…

cs.CV2020

Neural Sparse Representation for Image Restoration

Yuchen Fan, Jiahui Yu, Yiqun Mei +4

Inspired by the robustness and efficiency of sparse representation in sparse coding based image restoration models, we investigate the sparsity of neurons in deep networks. Our met…

cs.CR2026

MCP-Guard: A Multi-Stage Defense-in-Depth Framework for Securing Model Context Protocol in Agentic AI

Wenpeng Xing, Zhonghao Qi, Yupeng Qin +6

While Large Language Models (LLMs) have achieved remarkable performance, they remain vulnerable to jailbreak. The integration of Large Language Models (LLMs) with external tools vi…