Designer-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic Design Paper • 2609.22086 • Published 4 days ago • 22
RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments Paper • 2609.15364 • Published 8 days ago • 78
ZipTok3D: High-Fidelity 3D Tokenization with Compact Token Prefixes Paper • 2609.01740 • Published 21 days ago • 28
ZipTok3D: High-Fidelity 3D Tokenization with Compact Token Prefixes Paper • 2609.01740 • Published 21 days ago • 28
ZipTok3D: High-Fidelity 3D Tokenization with Compact Token Prefixes Paper • 2609.01740 • Published 21 days ago • 28
Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling Paper • 2608.30821 • Published 22 days ago • 67
Block3D: Efficient Text-to-3D Generation via Block-Wise Diffusion Paper • 2608.19567 • Published Aug 20 • 33
Block3D: Efficient Text-to-3D Generation via Block-Wise Diffusion Paper • 2608.19567 • Published Aug 20 • 33
Unlocking the Potential of Image Editing via Concept Scaling and Dense Supervision Paper • 2608.16812 • Published Aug 17 • 50
EviRank: Structured Relevance Evidence for Multimodal Image Re-ranking Paper • 2608.20886 • Published Aug 21 • 11
Block3D: Efficient Text-to-3D Generation via Block-Wise Diffusion Paper • 2608.19567 • Published Aug 20 • 33
PixVL: Self-Supervised Training of Pixel-Level MLLMs via a Unified Mask--Text Consistency Cycle Paper • 2608.01354 • Published Aug 2
EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning Paper • 2608.06197 • Published Aug 6 • 47
Memory Decoder at Scale: A Pretrained, Parametric Long-Term Memory Paper • 2607.27919 • Published Jul 30 • 62
ReCA: Multi-Shot Long Video Extrapolation via Recursive Context Allocation Paper • 2605.26525 • Published May 26
Beyond Relevance-Centric Retrieval: Rubric-Oriented Document Set Selection and Ranking Paper • 2607.19747 • Published Jul 22 • 29
TaskGround: Structured Executable Task Inference for Full-Scene Household Reasoning Paper • 2605.18109 • Published May 18
WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces Paper • 2606.09426 • Published Jun 8 • 49