ICER Red-teaming Dataset
Collection
Red-teaming dataset for Text-to-Image Models. Paper: https://arxiv.org/abs/2411.16769 [COLM'26] • 1 item • Updated
AI & ML interests
Research Demos and Tools for Trustworthy and Safe AI Development and Deployment
Recent Activity
pinyuchen
updated a
collection about 1 month ago
bxiong
updated a
Space about 1 month ago
bxiong
published a
Space about 1 month ago
hsiung
authored a
paper 2 months ago
gregH
submitted a
paper to Daily Papers 6 months ago
gregH
authored 6
papers 6 months ago
RADAR: Robust AI-Text Detection via Adversarial Learning
Paper • 2307.03838 • Published • 2
Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes
Paper • 2403.00867 • Published
Token Highlighter: Inspecting and Mitigating Jailbreak Prompts for Large Language Models
Paper • 2412.18171 • Published
Qwen3Guard Technical Report
Paper • 2510.14276 • Published • 17
Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm
Paper • 2511.04570 • Published • 242
OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language World Models
Paper • 2604.10866 • Published • 69
pinyuchen
authored a
paper 6 months ago
hsiung
authored 3
papers 9 months ago
Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets
Paper • 2506.05346 • Published
Spectral Insights into Data-Oblivious Critical Layers in Large Language Models
Paper • 2506.00382 • Published
NCTV: Neural Clamping Toolkit and Visualization for Neural Network Calibration
Paper • 2211.16274 • Published
hsiung
updated a
Space 9 months ago
kumitang
updated a
Space 12 months ago
kumitang
published a
Space 12 months ago
kumitang
updated a
Space 12 months ago