AI Onderzoekspapers Dagelijks

PaliGemma 2: A Family of Versatile VLMs for Transfer

SNOOPI: Supercharged One-step Diffusion Distillation with Proper Guidance

TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation

Imagine360: Immersive 360 Video Generation from Perspective Anchor

Distilling Diffusion Models to Efficient 3D LiDAR Scene Completion

VideoICL: Confidence-based Iterative In-context Learning for Out-of-Distribution Video Understanding

One Shot, One Talk: Whole-body Talking Avatar from a Single Image

VARCO-VISION: Expanding Frontiers in Korean Vision-Language Models

MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation

NVComposer: Boosting Generative Novel View Synthesis with Multiple Sparse and Unposed Images

NitroFusion: High-Fidelity Single-Step Diffusion through Dynamic Adversarial Training

Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding

U-MATH: A University-Level Benchmark for Evaluating Mathematical Skills in LLMs

Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models

CleanDIFT: Diffusion Features without Noise

Weighted-Reward Preference Optimization for Implicit Model Fusion

Mimir: Improving Video Diffusion Models for Precise Text Understanding

Inst-IT: Boosting Multimodal Instance Understanding via Explicit Visual Prompt Instruction Tuning

LumiNet: Latent Intrinsics Meets Diffusion Models for Indoor Scene Relighting