AI研究論文每日精選

SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints

LAION-SG: An Enhanced Large-Scale Dataset for Training Complex Image-Text Models with Structural Annotations

POINTS1.5: Building a Vision-Language Model towards Real World Applications

Learning Flow Fields in Attention for Controllable Person Image Generation

Track4Gen: Teaching Video Diffusion Models to Track Points Improves Video Generation

The BrowserGym Ecosystem for Web Agent Research

StyleMaster: Stylize Your Video with Artistic Generation and Translation

Generative Densification: Learning to Densify Gaussians for High-Fidelity Generalizable 3D Reconstruction

StreamChat: Chatting with Streaming Video

FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models

3DSRBench: A Comprehensive 3D Spatial Reasoning Benchmark

Mogo: RQ Hierarchical Causal Transformer for High-Quality 3D Human Motion Generation

I Don't Know: Explicit Modeling of Uncertainty with an [IDK] Token

Video Creation by Demonstration

StyleStudio: Text-Driven Style Transfer with Selective Control of Style Elements

KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models

Bootstrapping Language-Guided Navigation Learning with Self-Refining Data Flywheel

MIT-10M: A Large Scale Parallel Corpus of Multilingual Image Translation