QwenLong-L1.5: Post-Training Recipe for Long-Context Reasoning and Memory Management Paper • 2512.12967 • Published 12 days ago • 100
LEO-RobotAgent: A General-purpose Robotic Agent for Language-driven Embodied Operator Paper • 2512.10605 • Published 15 days ago • 6
Visionary: The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform Paper • 2512.08478 • Published 17 days ago • 76
MoCapAnything: Unified 3D Motion Capture for Arbitrary Skeletons from Monocular Videos Paper • 2512.10881 • Published 15 days ago • 29
Wikontic: Constructing Wikidata-Aligned, Ontology-Aware Knowledge Graphs with Large Language Models Paper • 2512.00590 • Published 27 days ago • 45
Canvas-to-Image: Compositional Image Generation with Multimodal Controls Paper • 2511.21691 • Published 30 days ago • 35
Unveiling Intrinsic Dimension of Texts: from Academic Abstract to Creative Story Paper • 2511.15210 • Published Nov 19 • 88
IterResearch: Rethinking Long-Horizon Agents via Markovian State Reconstruction Paper • 2511.07327 • Published Nov 10 • 76
HaluMem: Evaluating Hallucinations in Memory Systems of Agents Paper • 2511.03506 • Published Nov 5 • 93
Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B Paper • 2511.06221 • Published Nov 9 • 131
Lumine: An Open Recipe for Building Generalist Agents in 3D Open Worlds Paper • 2511.08892 • Published Nov 12 • 201
D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI Paper • 2510.05684 • Published Oct 7 • 141
RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation Paper • 2509.16198 • Published Sep 19 • 126
NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodes Paper • 2504.11544 • Published Apr 15 • 44
The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs Paper • 2509.09677 • Published Sep 11 • 34