Hui Xue
- Papers
- 12
Cite
Notes
Only stored in your browser.
Authored papers
12SkillNet: Create, Evaluate, and Connect AI Skills
arXiv 2026
AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security
arXiv 2026
A Safety Report on GPT-5.2, Gemini 3 Pro, Qwen3-VL, Doubao 1.8, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5
arXiv 2026
Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics
arXiv 2026
Hyperspherical Latents Improve Continuous-Token Autoregressive Generation
arXiv 2025
Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency
ICCV 2025
S-Eval: Towards Automated and Comprehensive Safety Evaluation for Large Language Models
arXiv 2024
Text Image Inpainting via Global Structure-Guided Diffusion Models
arXiv 2024
COCO-O: A Benchmark for Object Detectors under Natural Distribution Shifts
coco-o-a-benchmark-for-object-detectors-under
Synthesizing Coherent Story with Auto-Regressive Latent Diffusion Models
arXiv 2022
Supervised Prototypical Contrastive Learning for Emotion Recognition in Conversation
arXiv 2022
Deeper Insights into Weight Sharing in Neural Architecture Search
arXiv 2020
Affiliations
Frequent co-authors
10from 12 papers