Details the development and release of DeepCoder-14B-Preview, a 14B parameter code reasoning model achieving performance comparable to o3-mini through reinforcement learning, along with the dataset, code, and system optimizations used in its creation.
This article details a method for training large language models (LLMs) for code generation using a secure, local WebAssembly-based code interpreter and reinforcement learning with Group Relative Policy Optimization (GRPO). It covers the setup, training process, evaluation, and potential next steps.
Newsweek interview with Yann LeCun, Meta's chief AI scientist, detailing his skepticism of current LLMs and his focus on Joint Embedding Predictive Architecture (JEPA) as the future of AI, emphasizing world modeling and planning capabilities.
This article examines the dual nature of Generative AI in cybersecurity, detailing how it can be exploited by cybercriminals and simultaneously used to enhance defenses. It covers the history of AI, the emergence of GenAI, potential threats, and mitigation strategies.
This article provides a beginner-friendly explanation of attention mechanisms and transformer models, covering sequence-to-sequence modeling, the limitations of RNNs, the concept of attention, and how transformers address these limitations with self-attention and parallelization.
This study demonstrates that neural activity in the human brain aligns linearly with the internal contextual embeddings of speech and language within large language models (LLMs) as they process everyday conversations.
ByteDance Research has released DAPO (Dynamic Sampling Policy Optimization), an open-source reinforcement learning system for LLMs, aiming to improve reasoning abilities and address reproducibility issues. DAPO includes innovations like Clip-Higher, Dynamic Sampling, Token-level Policy Gradient Loss, and Overlong Reward Shaping, achieving a score of 50 on the AIME 2024 benchmark with the Qwen2.5-32B model.
The attention mechanism in Large Language Models (LLMs) helps derive the meaning of a word from its context. This involves encoding words as multi-dimensional vectors, calculating query and key vectors, and using attention weights to adjust the embedding based on contextual relevance.
The article delves into how large language models (LLMs) store facts, focusing on the role of multi-layer perceptrons (MLPs) in this process. It explains the mechanics of MLPs, including matrix multiplication, bias addition, and the Rectified Linear Unit (ReLU) function, using the example of encoding the fact that Michael Jordan plays basketball. The article also discusses the concept of superposition, which allows models to store a vast number of features by utilizing nearly perpendicular directions in high-dimensional spaces.
The article explores the architectural changes that enable DeepSeek's models to perform well with fewer resources, focusing on Multi-Head Latent Attention (MLA). It discusses the evolution of attention mechanisms, from Bahdanau to Transformer's Multi-Head Attention (MHA), and introduces Grouped-Query Attention (GQA) as a solution to MHA's memory inefficiencies. The article highlights DeepSeek's competitive performance despite lower reported training costs.
