UI-Venus Technical Report: Building High-performance UI Agents with RFT Paper • 2508.10833 • Published Aug 14, 2025 • 46
VenusBench-Mobile: A Challenging and User-Centric Benchmark for Mobile GUI Agents with Capability Diagnostics Paper • 2604.06182 • Published Feb 6 • 3
FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts Paper • 2311.05608 • Published Nov 9, 2023
Post-Training Leaves Behavioral Shadows on Unrelated Decisions Paper • 2609.29233 • Published 8 days ago • 267
Post-Training Leaves Behavioral Shadows on Unrelated Decisions Paper • 2609.29233 • Published 8 days ago • 267