HomeAI Papers

AI Papers

EMOAGENT: GUARDING MINDS IN THE AGE OF AI CONVERSATION

Human-AI Interaction for Mental Health Safety The rise of LLM-driven AI characters, like those on platforms such as Character.AI, has created new opportunities for emotional...

FlexIP: Mastering Image Generation with Precision and Creativity

Balancing Identity Preservation and Personalized Editing in 2D Generative Models FlexIP introduces a groundbreaking framework that decouples identity preservation and stylistic manipulation in 2D image...

Realistic Talking Portraits: The FantasyTalking Approach

Unleashing the Power of Coherent Motion Synthesis in Avatar Animation FantasyTalking introduces a novel framework that leverages a pretrained video diffusion transformer model to generate...

LIVEVQA: Can AI Keep Up with the Fast-Paced World of Visual News?

A New Benchmark Tests AI’s Ability to Answer Real-Time Visual Questions Introducing LIVEVQA – A groundbreaking dataset of 3,602 visual questions sourced from live news, designed...

GeometryCrafter: Revolutionizing 3D Reconstruction from Open-World Videos

Unleashing the Power of Diffusion Priors for Consistent Geometry Estimation GeometryCrafter introduces a novel framework that recovers high-fidelity point map sequences with temporal coherence from...

Unleashing Instant 3D Creation: The Power of Progressive Rendering Distillation

Transforming Text into Meshes in Seconds with Stable Diffusion PRD enables the adaptation of SD into a native 3D generator, eliminating the need for 3D...

Ultra-Resolution Adaptation with Ease: High-Resolution Image Generation

How URAE is Redefining Text-to-Image Diffusion Models with Data and Parameter Efficiency Synthetic Data as a Game-Changer: URAE leverages synthetic data from teacher models to significantly...

3D Body Fitting: How ETCH is Shaping the Future of Digital Humans

A Breakthrough in Equivariant Tightness Fitting for Clothed Humans Promises Unprecedented Accuracy and Generalization ETCH introduces a novel pipeline that leverages equivariant tightness vectors to map...

Huawei’s Breakthrough Method Balances Speed, Quality, and Efficiency in Diffusion Models

Revolutionizing AI-Generated Content: Trajectory Distribution Matching for Few-Step Diffusion Models A Unified Paradigm for Diffusion Models: Huawei’s Trajectory Distribution Matching (TDM) bridges the gap between distribution...

Motion Anything From Google: Motion Generation with Multimodal Control

How Attention-Based Mask Modeling and a New Dataset Are Redefining the Future of Motion Synthesis Motion Anything introduces an Attention-Based Mask Modeling approach, enabling fine-grained...

AI Unlocks Quantum Entanglement: A Leap Toward the Quantum Internet

How Artificial Intelligence Simplified Einstein’s ‘Spooky Action’ and Paved the Way for Next-Gen Communication AI-Powered Breakthrough: Researchers used PyTheus, an AI tool, to design a...

EgoLife: The AI Assistant That Sees the World Through Your Eyes

How Wearable Glasses and Multimodal Data Are Pioneering the Future of Personal Efficiency A 300-Hour Window into Daily Life: The EgoLife Dataset captures six participants’...