AI Research Papers Daily

SNOOPI: Supercharged One-step Diffusion Distillation with Proper Guidance

Imagine360: Immersive 360 Video Generation from Perspective Anchor

Distilling Diffusion Models to Efficient 3D LiDAR Scene Completion

PaliGemma 2: A Family of Versatile VLMs for Transfer

TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation

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

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

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

CleanDIFT: Diffusion Features without Noise

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

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

Mimir: Improving Video Diffusion Models for Precise Text Understanding

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

Weighted-Reward Preference Optimization for Implicit Model Fusion

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