2025-01-17s

This survey paper explores the exciting new frontier of Large Reasoning Models (LRMs), focusing on how reinforcement learning and clever prompting techniques are boosting LLMs’ reasoning capabilities.

SynthLight: A novel diffusion model relights portraits realistically by learning to re-render synthetic faces, generalizing remarkably well to real photographs.

Scaling visual tokenizers dramatically improves image and video generation, achieving state-of-the-art results and outperforming existing methods with fewer computations by focusing on decoder scaling…

Boosting diffusion model performance at inference time, this research introduces a novel framework that goes beyond simply increasing denoising steps. By cleverly searching for better noise candidates…

FAST: A novel action tokenization method using discrete cosine transform drastically improves autoregressive vision-language-action models’ training and performance, enabling dexterous and high-freque…

AI-powered medical consultations often struggle with the inquiry phase. This paper presents a novel patient simulator trained on real interactions, revealing that effective inquiry significantly impac…

CaPa: Carve-n-Paint Synthesis generates hyper-realistic 4K textured meshes in under 30 seconds, setting a new standard for efficient 3D asset creation.

AnyStory: A unified framework enables high-fidelity personalized image generation for single and multiple subjects, addressing subject fidelity challenges in existing methods.

RLHS, a novel alignment algorithm, leverages simulated hindsight feedback to mitigate misalignment in RLHF, significantly improving AI’s alignment with human values and goals.

Generative video models struggle to understand physics despite producing visually realistic videos; Physics-IQ benchmark reveals this critical limitation, highlighting the need for improved physical r…