AI Onderzoekspapers Dagelijks

X-Prompt: Towards Universal In-Context Image Generation in Auto-Regressive Vision Language Foundation Models

o1-Coder: an o1 Replication for Coding

Switti: Designing Scale-Wise Transformers for Text-to-Image Synthesis

Open-Sora Plan: Open-Source Large Video Generation Model

FLOAT: Generative Motion Latent Flow Matching for Audio-driven Talking Portrait

VISTA: Enhancing Long-Duration and High-Resolution Video Understanding by Video Spatiotemporal Augmentation

SOLAMI: Social Vision-Language-Action Modeling for Immersive Interaction with 3D Autonomous Characters

TAPTRv3: Spatial and Temporal Context Foster Robust Tracking of Any Point in Long Video

GATE OpenING: A Comprehensive Benchmark for Judging Open-ended Interleaved Image-Text Generation

Efficient Track Anything

The Well: a Large-Scale Collection of Diverse Physics Simulations for Machine Learning

Steering Rectified Flow Models in the Vector Field for Controlled Image Generation

VLsI: Verbalized Layers-to-Interactions from Large to Small Vision Language Models

TinyFusion: Diffusion Transformers Learned Shallow

INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge

WF-VAE: Enhancing Video VAE by Wavelet-Driven Energy Flow for Latent Video Diffusion Model

VLSBench: Unveiling Visual Leakage in Multimodal Safety

Long Video Diffusion Generation with Segmented Cross-Attention and Content-Rich Video Data Curation

Art-Free Generative Models: Art Creation Without Graphic Art Knowledge

VisOnlyQA: Large Vision Language Models Still Struggle with Visual Perception of Geometric Information

PhysGame: Uncovering Physical Commonsense Violations in Gameplay Videos

A Simple and Provable Scaling Law for the Test-Time Compute of Large Language Models

Collaborative Instance Navigation: Leveraging Agent Self-Dialogue to Minimize User Input

World-consistent Video Diffusion with Explicit 3D Modeling

Exploring the Abilities of Large Language Models to Solve Proportional Analogies via Knowledge-Enhanced Prompting

HUGSIM: A Real-Time, Photo-Realistic and Closed-Loop Simulator for Autonomous Driving

AMO Sampler: Enhancing Text Rendering with Overshooting

Towards Cross-Lingual Audio Abuse Detection in Low-Resource Settings with Few-Shot Learning

Improving speaker verification robustness with synthetic emotional utterances