AI Native Daily Paper Digest – 20250214
1. InfiniteHiP: Extending Language Model Context Up to 3 Million Tokens on a Single GPU π Keywords: Long Context, LLM Inference, Token […]
AI Native Daily Paper Digest – 20250213
1. Fino1: On the Transferability of Reasoning Enhanced LLMs to Finance π Keywords: Large Language Models, Financial Reasoning, CoT Fine-Tuning, Reinforcement Learning, […]
AI Native Daily Paper Digest – 20250212
1. Expect the Unexpected: FailSafe Long Context QA for Finance π Keywords: LLM, Query Failure, Context Failure, Robustness, Financial Applications π‘ Category: […]
AI Native Daily Paper Digest – 20250211
1. SynthDetoxM: Modern LLMs are Few-Shot Parallel Detoxification Data Annotators π Keywords: multilingual text detoxification, parallel datasets, LLMs, SynthDetoxM, data scarcity π‘ […]
AI Native Daily Paper Digest – 20250207
1. Analyze Feature Flow to Enhance Interpretation and Steering in Language Models π Keywords: Sparse Autoencoder, Inter-layer Feature Links, Feature Evolution, Text […]
AI Native Daily Paper Digest – 20250206
1. SmolLM2: When Smol Goes Big — Data-Centric Training of a Small Language Model π Keywords: Large Language Models, SmolLM2, Multistage Training, […]
AI Native Daily Paper Digest – 20250205
1. VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models π Keywords: VideoJAM, motion coherence, generative video models, pixel reconstruction […]
AI Native Daily Paper Digest – 20250204
1. The Differences Between Direct Alignment Algorithms are a Blur π Keywords: Direct Alignment Algorithms, Reinforcement Learning, Supervised Fine-Tuning, Pointwise Objectives π‘ […]
AI Native Daily Paper Digest – 20250203
1. s1: Simple test-time scaling π Keywords: Test-time scaling, Language modeling, OpenAI, Reasoning performance, Budget forcing π‘ Category: Natural Language Processing π […]
AI Native Daily Paper Digest – 20250131
1. GuardReasoner: Towards Reasoning-based LLM Safeguards π Keywords: LLMs, GuardReasoner, reasoning, guard models, safety-critical applications π‘ Category: Knowledge Representation and Reasoning π […]
AI Native Daily Paper Digest – 20250130
1. Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate π Keywords: Supervised Fine-Tuning (SFT), Critique Fine-Tuning (CFT), GPT-4o, […]
AI Native Daily Paper Digest – 20250129
1. SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training π Keywords: supervised fine-tuning, reinforcement learning, model generalization, text-based rule […]