Daily Papers of 2024-09-24

1. RACER: Rich Language-Guided Failure Recovery Policies for Imitation Learning 40 upvotes, #1 of 2024-09-24
2. A Preliminary Study of o1 in Medicine: Are We Closer to an AI Doctor? 33 upvotes, #2 of 2024-09-24
3. Phantom of Latent for Large Language and Vision Models 26 upvotes, #3 of 2024-09-24
4. PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language Instructions 21 upvotes, #4 of 2024-09-24
5. Beyond Fine-tuning: Unleashing the Potential of Continuous Pretraining for Clinical LLMs 20 upvotes, #5 of 2024-09-24
6. Reflecting Reality: Enabling Diffusion Models to Produce Faithful Mirror Reflections 14 upvotes, #6 of 2024-09-24
7. Style over Substance: Failure Modes of LLM Judges in Alignment Benchmarking 11 upvotes, #7 of 2024-09-24
8. MaterialFusion: Enhancing Inverse Rendering with Material Diffusion Priors 9 upvotes, #8 of 2024-09-24
9. Zero-shot Cross-lingual Voice Transfer for TTS 7 upvotes, #9 of 2024-09-24
10. MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting 7 upvotes, #9 of 2024-09-24
11. An adapted large language model facilitates multiple medical tasks in diabetes care 6 upvotes, #11 of 2024-09-24
12. A Case Study of Web App Coding with OpenAI Reasoning Models 4 upvotes, #12 of 2024-09-24
13. SpaceBlender: Creating Context-Rich Collaborative Spaces Through Generative 3D Scene Blending 4 upvotes, #12 of 2024-09-24
14. Self-Supervised Audio-Visual Soundscape Stylization 2 upvotes, #14 of 2024-09-24

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.