About
Research & Development
SiD-DiT: Bridging Diffusion and Flow Matching for Faster Image Synthesis
TLDR: The research paper introduces SiD-DiT, a novel method that extends Score identity Distillation (SiD) to text-to-image flow-matching models with Diffusion Transformer (DiT) backbones....
Research & Development
MGM-Omni: Advancing AI for Extended Speech Interaction
TLDR: MGM-Omni is a new AI model that unifies understanding across text, images, video, and audio, and can generate expressive, long-duration speech in personalized...
Research & Development
Targeted Exploration for Enhanced Reasoning in AI Models
TLDR: SIREN (SelectIve entRopy rEgularizatioN) is a novel method designed to overcome entropy collapse and premature convergence in large reasoning models (LRMs) trained with...
Research & Development
GLASS Flows: A New Approach to Efficient Stochastic Sampling in Generative AI
TLDR: GLASS Flows introduces a novel sampling method for flow matching and diffusion models that allows for efficient, ODE-based simulation of stochastic Markov transitions....
Research & Development
NAIPv2: A Scalable Framework for Automated Paper Quality Estimation
TLDR: NAIPv2 is a new framework for efficiently estimating scientific paper quality. It uses debiased pairwise learning within domain-year groups and a Review Tendency...
Research & Development
InfoAgent: An Autonomous AI for Complex Information Seeking
TLDR: InfoAgent is a new deep research agent powered by Large Language Models (LLMs) that excels at complex information-seeking tasks. It uses an innovative...