Memory as Plans: World-Action Modeling with Memory-Grounded Planning Paper • 2609.11561 • Published 6 days ago • 39
UniH^3: Unifying Hierarchical Homogeneity and Heterogeneity for All-in-One Medical Image Restoration Paper • 2609.11156 • Published 6 days ago • 24
RoboSPA: Can VLA Models Go Beyond Simple Scenes and Short-Horizon Tasks? Paper • 2609.05324 • Published 12 days ago • 28
LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes Paper • 2609.03796 • Published 13 days ago • 236
SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation Paper • 2608.17426 • Published 29 days ago • 159
Can We Defend Against AI-Generated Video Attacks on Real-World Crisis Events? A Systematic Evaluation of Detectors, Generators and Social Dissemination Paper • 2608.14391 • Published Aug 14 • 282
OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution Paper • 2608.00677 • Published Aug 1 • 263
Don't Scroll Back: Missing-Evidence Memory for Streaming Dialogue Summarization Paper • 2608.09043 • Published Aug 10 • 8
MASS: Multiplayer World Models with Authoritative Shared State Paper • 2608.06257 • Published Aug 10 • 18
DataSpace: Benchmarking Data Agents for Verifiable Analytics over Heterogeneous Workspaces Paper • 2608.03451 • Published Aug 4 • 34
UniWorld-Design: From Pixel Generation to Layer-Native Design Paper • 2608.03971 • Published Aug 4 • 25
RecHarness: A Bandit-Routed Agentic Harness for Self-Evolving Recommender Systems Paper • 2607.29241 • Published Jul 31 • 12
QQWorld: Quantile-Quantile Matching for World Model Regularization Paper • 2607.28415 • Published Jul 30 • 32