Daily Papers of 2025-01-14

1. The Lessons of Developing Process Reward Models in Mathematical Reasoning 83 upvotes, #1 of 2025-01-14
2. Tensor Product Attention Is All You Need 73 upvotes, #2 of 2025-01-14
3. Transformer^2: Self-adaptive LLMs 49 upvotes, #3 of 2025-01-14
4. BIOMEDICA: An Open Biomedical Image-Caption Archive, Dataset, and Vision-Language Models Derived from Scientific Literature 46 upvotes, #4 of 2025-01-14
5. MinMo: A Multimodal Large Language Model for Seamless Voice Interaction 38 upvotes, #5 of 2025-01-14
6. VideoAuteur: Towards Long Narrative Video Generation 31 upvotes, #6 of 2025-01-14
7. O1 Replication Journey -- Part 3: Inference-time Scaling for Medical Reasoning 29 upvotes, #7 of 2025-01-14
8. WebWalker: Benchmarking LLMs in Web Traversal 19 upvotes, #8 of 2025-01-14
9. SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training 15 upvotes, #9 of 2025-01-14
10. UnCommon Objects in 3D 13 upvotes, #10 of 2025-01-14
11. ChemAgent: Self-updating Library in Large Language Models Improves Chemical Reasoning 8 upvotes, #11 of 2025-01-14
12. Evaluating Sample Utility for Data Selection by Mimicking Model Weights 5 upvotes, #12 of 2025-01-14

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.