activity
20242026
collaborators

9 papers

cs.CV2026

UniNDM: A Unified Noise-driven Detection and Mitigation Framework Against Sexual Content in Text-to-Image Generation

Yao Huang, Yitong Sun, Huanran Chen +8

Despite the impressive generative capabilities of text-to-image diffusion models, they remain vulnerable to implicit sexual prompts, where subtle cues disguised as benign terms or…

cs.LG2026

MESA: Improving MoE Safety Alignment via Decentralized Expertise

Yitong Sun, Yao Huang, Teng Li +5

Mixture-of-Experts (MoE) architectures scale Large Language Models (LLMs) efficiently, enabling greater capacity with reduced computational cost by dynamically routing inputs to re…

cs.CL2025

DeceptionBench: A Comprehensive Benchmark for AI Deception Behaviors in Real-world Scenarios

Yao Huang, Yitong Sun, Yichi Zhang +3

Despite the remarkable advances of Large Language Models (LLMs) across diverse cognitive tasks, the rapid enhancement of these capabilities also introduces emergent deceptive behav…

cs.CV2025

The Path to Reconciling Quality and Safety in Text-to-Image Generation: Dataset, Method, and Evaluation

Shouwei Ruan, Zhenyu Wu, Yao Huang +5

Content safety is a fundamental challenge for text-to-image (T2I) models, yet prevailing methods enforce a debilitating trade-off between safety and generation quality. We argue th…

cs.CV2025

NDM: A Noise-driven Detection and Mitigation Framework against Implicit Sexual Intentions in Text-to-Image Generation

Yitong Sun, Yao Huang, Ruochen Zhang +4

Despite the impressive generative capabilities of text-to-image (T2I) diffusion models, they remain vulnerable to generating inappropriate content, especially when confronted with…

cs.AI2025

Oyster-I: Beyond Refusal -- Constructive Safety Alignment for Responsible Language Models

Ranjie Duan, Jiexi Liu, Xiaojun Jia +27

Large language models (LLMs) typically deploy safety mechanisms to prevent harmful content generation. Most current approaches focus narrowly on risks posed by malicious actors, of…