Transforming Instruction-Based Editing Through Rectified Guidance and Contrastive Learning
SuperEdit introduces a groundbreaking approach to instruction-based image editing by rectifying editing instructions and aligning them...
Exploring the Hidden Flaws in UQ Evaluation and the Promise of LM-as-a-Judge
Uncertainty Quantification (UQ) in Language Models (LMs) is vital for safety and reliability,...
How Language Models Like Claude Reveal Their Values in Real-World Conversations
AI models like Claude, developed by Anthropic, are trained to reflect specific values such...
How a Memory-Based Framework Ensures Long-Term Consistency in World Simulation
WORLDMEM introduces a groundbreaking framework for world simulation, utilizing a memory bank to store past...
The First Open-Source, Native 1-Bit LLM at Scale
BitNet b1.58 2B4T is the first open-source, native 1-bit Large Language Model (LLM) at the 2-billion parameter...
Harnessing Video Diffusion for Temporally Consistent Surface Normals
NormalCrafter introduces a groundbreaking approach to surface normal estimation in videos, leveraging video diffusion priors to ensure...
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...
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...
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...
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...
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...
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...