Chain-of-Thought Compression Should Not Be Blind: V-Skip for Efficient Multimodal Reasoning via Dual-Path Anchoring Paper • 2601.13879 • Published Jan 20
Programming with Data: Test-Driven Data Engineering for Self-Improving LLMs from Raw Corpora Paper • 2604.24819 • Published 22 days ago • 88
Intern-Atlas: A Methodological Evolution Graph as Research Infrastructure for AI Scientists Paper • 2604.28158 • Published 19 days ago • 47
NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation Paper • 2605.10813 • Published 8 days ago • 13
PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents Paper • 2605.10341 • Published 8 days ago • 32
PAGER: Bridging the Semantic-Execution Gap in Point-Precise Geometric GUI Control Paper • 2605.15963 • Published 4 days ago • 8
PAGER: Bridging the Semantic-Execution Gap in Point-Precise Geometric GUI Control Paper • 2605.15963 • Published 4 days ago • 8
PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents Paper • 2605.10341 • Published 8 days ago • 32
Programming with Data: Test-Driven Data Engineering for Self-Improving LLMs from Raw Corpora Paper • 2604.24819 • Published 22 days ago • 88
The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook Paper • 2604.02029 • Published Apr 2 • 151
The Trinity of Consistency as a Defining Principle for General World Models Paper • 2602.23152 • Published Feb 26 • 201
The Trinity of Consistency as a Defining Principle for General World Models Paper • 2602.23152 • Published Feb 26 • 201
Thinking with Drafting: Optical Decompression via Logical Reconstruction Paper • 2602.11731 • Published Feb 12 • 35
Thinking with Drafting: Optical Decompression via Logical Reconstruction Paper • 2602.11731 • Published Feb 12 • 35
Decouple to Generalize: Context-First Self-Evolving Learning for Data-Scarce Vision-Language Reasoning Paper • 2512.06835 • Published Dec 7, 2025 • 5
GGBench: A Geometric Generative Reasoning Benchmark for Unified Multimodal Models Paper • 2511.11134 • Published Nov 14, 2025 • 33
Envision: Benchmarking Unified Understanding & Generation for Causal World Process Insights Paper • 2512.01816 • Published Dec 1, 2025 • 94
OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning Paper • 2306.11249 • Published Jun 20, 2023 • 2
SimVPv2: Towards Simple yet Powerful Spatiotemporal Predictive Learning Paper • 2211.12509 • Published Nov 22, 2022
Depth3DLane: Monocular 3D Lane Detection via Depth Prior Distillation Paper • 2504.18325 • Published Apr 25, 2025