ObjexMT: Objective Extraction and Metacognitive Calibration for LLM-as-a-Judge under Multi-Turn Jailbreaks Paper • 2508.16889 • Published Aug 23, 2025 • 2
One-Shot is Enough: Consolidating Multi-Turn Attacks into Efficient Single-Turn Prompts for LLMs Paper • 2503.04856 • Published Mar 6, 2025 • 2
Qwen2-VL Collection Vision-language model series based on Qwen2 • 16 items • Updated 2 days ago • 226
Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching Paper • 2503.05179 • Published Mar 7, 2025 • 46