AgentSearchBench: A Benchmark for AI Agent Search in the Wild Paper • 2604.22436 • Published 14 days ago • 13
LLM Safety From Within: Detecting Harmful Content with Internal Representations Paper • 2604.18519 • Published 18 days ago • 24
Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond Paper • 2604.22748 • Published 14 days ago • 224
MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping Paper • 2604.08364 • Published 29 days ago • 100
HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents Paper • 2604.07430 • Published 30 days ago • 187
RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time Paper • 2604.11626 • Published 25 days ago • 101
InCoder-32B-Thinking: Industrial Code World Model for Thinking Paper • 2604.03144 • Published Apr 3 • 233
When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models Paper • 2604.08546 • Published 29 days ago • 115