Daily Papers of 2025-02-06

1. SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model 158 upvotes, #1 of 2025-02-06
2. Demystifying Long Chain-of-Thought Reasoning in LLMs 49 upvotes, #2 of 2025-02-06
3. LIMO: Less is More for Reasoning 47 upvotes, #3 of 2025-02-06
4. TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets 31 upvotes, #4 of 2025-02-06
5. Boosting Multimodal Reasoning with MCTS-Automated Structured Thinking 19 upvotes, #5 of 2025-02-06
6. LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer 16 upvotes, #6 of 2025-02-06
7. On Teacher Hacking in Language Model Distillation 15 upvotes, #7 of 2025-02-06
8. Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning 11 upvotes, #8 of 2025-02-06
9. A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods 8 upvotes, #9 of 2025-02-06
10. Large Language Model Guided Self-Debugging Code Generation 8 upvotes, #9 of 2025-02-06
11. Jailbreaking with Universal Multi-Prompts 7 upvotes, #11 of 2025-02-06
12. Activation-Informed Merging of Large Language Models 5 upvotes, #12 of 2025-02-06
13. Riddle Me This! Stealthy Membership Inference for Retrieval-Augmented Generation 4 upvotes, #13 of 2025-02-06
14. HackerRank-ASTRA: Evaluating Correctness & Consistency of Large Language Models on cross-domain multi-file project problems 0 upvotes, #14 of 2025-02-06

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.