DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines Paper • 2607.16617 • Published 13 days ago • 137
Video-Oasis: Rethinking Evaluation of Video Understanding Paper • 2603.29616 • Published 29 days ago • 65
TerraDiT-Ω: Unified Spatial Control for Satellite Image Synthesis with Any Geospatial Primitive Paper • 2606.31029 • Published Jun 30 • 6
LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling Paper • 2606.18023 • Published Jun 16 • 210
No Resource, No Benchmarks, No Problem? Evaluating and Improving LLMs for Code Generation in No-Resource Languages Paper • 2606.16827 • Published Jun 15 • 3
Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models Paper • 2606.03988 • Published Jun 3 • 126
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players Paper • 2605.28816 • Published May 27 • 433
EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation Paper • 2605.23271 • Published May 22 • 82