InSight-o3: Empowering Multimodal Foundation Models with Generalized Visual Search Paper • 2512.18745 • Published Dec 21, 2025 • 12
SWE-RM: Execution-free Feedback For Software Engineering Agents Paper • 2512.21919 • Published 27 days ago • 10
ProEdit: Inversion-based Editing From Prompts Done Right Paper • 2512.22118 • Published 27 days ago • 18
MAI-UI Technical Report: Real-World Centric Foundation GUI Agents Paper • 2512.22047 • Published 27 days ago • 27
InsertAnywhere: Bridging 4D Scene Geometry and Diffusion Models for Realistic Video Object Insertion Paper • 2512.17504 • Published Dec 19, 2025 • 97
Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learning Paper • 2512.20605 • Published about 1 month ago • 61
SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios Paper • 2512.18470 • Published Dec 20, 2025 • 11
Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning Paper • 2512.20848 • Published 30 days ago • 35
HiStream: Efficient High-Resolution Video Generation via Redundancy-Eliminated Streaming Paper • 2512.21338 • Published 29 days ago • 22
DreaMontage: Arbitrary Frame-Guided One-Shot Video Generation Paper • 2512.21252 • Published 29 days ago • 35
Learning to Reason in 4D: Dynamic Spatial Understanding for Vision Language Models Paper • 2512.20557 • Published about 1 month ago • 50
TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times Paper • 2512.16093 • Published Dec 18, 2025 • 94
SemanticGen: Video Generation in Semantic Space Paper • 2512.20619 • Published about 1 month ago • 92
UCoder: Unsupervised Code Generation by Internal Probing of Large Language Models Paper • 2512.17385 • Published Dec 19, 2025 • 19
Can LLMs Estimate Student Struggles? Human-AI Difficulty Alignment with Proficiency Simulation for Item Difficulty Prediction Paper • 2512.18880 • Published Dec 21, 2025 • 25
Region-Constraint In-Context Generation for Instructional Video Editing Paper • 2512.17650 • Published Dec 19, 2025 • 51
DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI Paper • 2512.16676 • Published Dec 18, 2025 • 211