Daily Papers of 2025-01-27

1. Humanity's Last Exam 50 upvotes, #1 of 2025-01-27
2. Chain-of-Retrieval Augmented Generation 41 upvotes, #2 of 2025-01-27
3. RealCritic: Towards Effectiveness-Driven Evaluation of Language Model Critiques 29 upvotes, #3 of 2025-01-27
4. Redundancy Principles for MLLMs Benchmarks 25 upvotes, #4 of 2025-01-27
5. RL + Transformer = A General-Purpose Problem Solver 19 upvotes, #5 of 2025-01-27
6. Relightable Full-Body Gaussian Codec Avatars 8 upvotes, #6 of 2025-01-27
7. Question Answering on Patient Medical Records with Private Fine-Tuned LLMs 7 upvotes, #7 of 2025-01-27
8. Multiview Equivariance Improves 3D Correspondence Understanding with Minimal Feature Finetuning 5 upvotes, #8 of 2025-01-27
9. GeoPixel: Pixel Grounding Large Multimodal Model in Remote Sensing 5 upvotes, #8 of 2025-01-27
10. CatV2TON: Taming Diffusion Transformers for Vision-Based Virtual Try-On with Temporal Concatenation 4 upvotes, #10 of 2025-01-27
11. AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulation 3 upvotes, #11 of 2025-01-27
12. Denoising as Adaptation: Noise-Space Domain Adaptation for Image Restoration 2 upvotes, #12 of 2025-01-27

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.