AI 연구 논문 데일리

RACER: Rich Language-Guided Failure Recovery Policies for Imitation Learning

A Preliminary Study of o1 in Medicine: Are We Closer to an AI Doctor?

Phantom of Latent for Large Language and Vision Models

PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language Instructions

Beyond Fine-tuning: Unleashing the Potential of Continuous Pretraining for Clinical LLMs

Reflecting Reality: Enabling Diffusion Models to Produce Faithful Mirror Reflections

MaterialFusion: Enhancing Inverse Rendering with Material Diffusion Priors

Style over Substance: Failure Modes of LLM Judges in Alignment Benchmarking

Zero-shot Cross-lingual Voice Transfer for TTS

MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting

An adapted large language model facilitates multiple medical tasks in diabetes care

SpaceBlender: Creating Context-Rich Collaborative Spaces Through Generative 3D Scene Blending

A Case Study of Web App Coding with OpenAI Reasoning Models

Self-Supervised Audio-Visual Soundscape Stylization