Kejia Zhang's picture

Kejia Zhang

KejiaRobust

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 12 days ago

PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks

liked a dataset 3 months ago

allenai/cosmos_qa

upvoted a paper 3 months ago

GLM-5: from Vibe Coding to Agentic Engineering

View all activity

Organizations

None yet

authored a paper 8 months ago

MANI-Pure: Magnitude-Adaptive Noise Injection for Adversarial Purification

Paper • 2509.25082 • Published Sep 29, 2025 • 3

authored 2 papers 9 months ago

Towards Adversarial Robustness via Debiased High-Confidence Logit Alignment

Paper • 2408.06079 • Published Aug 12, 2024

Poison as Cure: Visual Noise for Mitigating Object Hallucinations in LVMs

Paper • 2501.19164 • Published Jan 31, 2025

authored 2 papers 10 months ago

TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs

Paper • 2507.21584 • Published Jul 29, 2025 • 11

When Tokens Talk Too Much: A Survey of Multimodal Long-Context Token Compression across Images, Videos, and Audios

Paper • 2507.20198 • Published Jul 27, 2025 • 28