Reading list 2024/2025

Introduction

My reading list for easy access

Reading list

• LLM Research Papers: The 2024 List
• Phi-4 Technical Report
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Evolving Deeper LLM Thinking
• Qwen2.5 Technical Report
• Beating cuBLAS in Single-Precision General Matrix Multiplication
• Triton resources
• A Survey on Deep Neural Network Pruning
• Starting with TK
• 1.58-bit FLUX
• Noteworthy AI Research Papers of 2024 (Part One)
• Noteworthy AI Research Papers of 2024 (Part Two)
• Monolith: Real Time Recommendation System With Collisionless Embedding Table
• Titans: Learning to Memorize at Test Time
• Spanner: Google’s Globally-Distributed Database
• Mamba2D: A Natively Multi-Dimensional State-Space Model for Vision Tasks
• Converting a From-Scratch GPT Architecture to Llama 2
• Scaling Reinforcement Learning with LLMS
• HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs
• Preference Discerning with LLM-Enhanced Generative Retrieval
• THE LOTTERY TICKET HYPOTHESIS: FINDING SPARSE, TRAINABLE NEURAL NETWORKS
• Memory Layers at Scale
• Large Concept Models: Language Modeling in a Sentence Representation Space
• WHAT MATTERS IN TRANSFORMERS? NOT ALL ATTENTION IS NEEDED
• Coalescence: making LLM inference 5x faster
• Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
• Training Large Language Models to Reason in a Continuous Latent Space
• ELASTICTOK: ADAPTIVE TOKENIZATION FOR IMAGE AND VIDEO
• JETFORMER: AN AUTOREGRESSIVE GENERATIVE MODEL OF RAW IMAGES AND TEXT
• Theoretical Analysis of Byte-Pair Encoding
• Training-free Diffusion Model Adaptation for Variable-Sized Text-to-Image Synthesis
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• DeepSeek-V3 Technical Report
• Hymba: A Hybrid-head Architecture for Small Language Models
• When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training
• Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning
• Towards Large Reasoning Models: A Survey on Scaling LLM Reasoning Capabilities
• Language Model Can Listen While Speaking
• Multi-megabase scale genome interpretation with genetic language models
• MiniMax-01: Scaling Foundation Models with Lightning Attention
• Modeling the hallucinatory effects of classical psychedelics in terms of replay-dependent plasticity mechanisms
• Transformer 2 : Self-adaptive LLMs
• LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs
• Titans: Learning to Memorize at Test Time (v1)
• Jasper and Stella: distillation of SOTA embedding models
• GROKKING AT THE EDGE OF NUMERICAL STABILITY
• The GAN is dead; long live the GAN! A Modern GAN Baseline
• rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking
• Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling
• Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective
• DIFFERENTIAL TRANSFORMER
• Large Concept Models: Language Modeling in a Sentence Representation Space (Duplicate)
• The State of Generative Models
• Augmented Neural ODEs
• Some Math behind Neural Tangent Kernel