AI Research Papers Daily

DropletVideo: A Dataset and Approach to Explore Integral Spatio-Temporal Consistent Video Generation

Being-0: A Humanoid Robotic Agent with Vision-Language Models and Modular Skills

Personalize Anything for Free with Diffusion Transformer

DreamRenderer: Taming Multi-Instance Attribute Control in Large-Scale Text-to-Image Models

SPIN-Bench: How Well Do LLMs Plan Strategically and Reason Socially?

Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey

Edit Transfer: Learning Image Editing via Vision In-Context Relations

R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization

BlobCtrl: A Unified and Flexible Framework for Element-level Image Generation and Editing

MicroVQA: A Multimodal Reasoning Benchmark for Microscopy-Based Scientific Research

WideRange4D: Enabling High-Quality 4D Reconstruction with Wide-Range Movements and Scenes

reWordBench: Benchmarking and Improving the Robustness of Reward Models with Transformed Inputs

VideoMind: A Chain-of-LoRA Agent for Long Video Reasoning

V-STaR: Benchmarking Video-LLMs on Video Spatio-Temporal Reasoning

Free-form language-based robotic reasoning and grasping

MTV-Inpaint: Multi-Task Long Video Inpainting

Rewards Are Enough for Fast Photo-Realistic Text-to-image Generation

Long-Video Audio Synthesis with Multi-Agent Collaboration

Sightation Counts: Leveraging Sighted User Feedback in Building a BLV-aligned Dataset of Diagram Descriptions

Training Video Foundation Models with NVIDIA NeMo

Error Analyses of Auto-Regressive Video Diffusion Models: A Unified Framework

GenStereo: Towards Open-World Generation of Stereo Images and Unsupervised Matching

Investigating Human-Aligned Large Language Model Uncertainty

Using Mechanistic Interpretability to Craft Adversarial Attacks against Large Language Models

Basic Category Usage in Vision Language Models

WISA: World Simulator Assistant for Physics-Aware Text-to-Video Generation