Mathematicians and physicists alike will jump on this Representation theory primer by Etingof, Hensel, Golberg++

📕 Paper


@Machine_learn

Titans: Transformer v.2?
📃🖋Read the paper.

@Machine_learn

📃Understanding When and Why Graph Attention Mechanisms Work via Node Classification


📎 Study the paper

@Machine_learn

دوستان این مقاله هم If اش بالاست و هم یک کار بنیادیه. جزئیات کار داخل گیت هست.

LatentSync: Audio Conditioned Latent Diffusion Models for Lip Sync

Paper: https://arxiv.org/pdf/2412.09262v1.pdf

Code: https://github.com/bytedance/LatentSync

@Machine_learn

Top 10 Machine Learning Algorithms

@Machine_learn

Mathematics of Backpropagation Through Time.

📕 Paper


@Machine_learn

Foundations of Large Language Models

📝 Table of Contents:
● Pre-training
● Generative Models
● Prompting
● Alignment

Tong Xiao and Jingbo Zhu
January 17, 2025

📃 Download from arXiv.

@Machine_learn

تنها دو روز تا شروع اين پروژه باقي مونده دوستاني كه مايل به همكاري هستن به ايدي بنده پيام بدن
@Raminmousa

Evolutionary Computation in the Era of Large Language Model: Survey and Roadmap

Large language models (LLMs) have not only revolutionized natural language processing but also extended their prowess to various domains, marking a significant stride towards artificial general intelligence. The interplay between LLMs and evolutionary algorithms (EAs), despite differing in objectives and methodologies, share a common pursuit of applicability in complex problems. Meanwhile, EA can provide an optimization framework for LLM's further enhancement under black-box settings, empowering LLM with flexible global search capacities. On the other hand, the abundant domain knowledge inherent in LLMs could enable EA to conduct more intelligent searches. Furthermore, the text processing and generative capabilities of LLMs would aid in deploying EAs across a wide range of tasks. Based on these complementary advantages, this paper provides a thorough review and a forward-looking roadmap, categorizing the reciprocal inspiration into two main avenues: LLM-enhanced EA and EA-enhanced #LLM. Some integrated synergy methods are further introduced to exemplify the complementarity between LLMs and EAs in diverse scenarios, including code generation, software engineering, neural architecture search, and various generation tasks. As the first comprehensive review focused on the EA research in the era of #LLMs, this paper provides a foundational stepping stone for understanding the collaborative potential of LLMs and EAs. The identified challenges and future directions offer guidance for researchers and practitioners to unlock the full potential of this innovative collaboration in propelling advancements in optimization and artificial intelligence.

Paper: https://arxiv.org/pdf/2401.10034v3.pdf

Code: https://github.com/wuxingyu-ai/llm4ec

https://www.tg-me.com/deep_learning_proj

📽 Accelerating Drug Discovery With a Biomedical Knowledge Graph

🎞 Watch

@Machine_learn

DeepSeek-V3 Technical Report

We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. To achieve efficient inference and cost-effective training, DeepSeek-V3 adopts Multi-head Latent Attention (MLA) and DeepSeekMoE architectures, which were thoroughly validated in #DeepSeek V2. Furthermore, DeepSeek-V3 pioneers an auxiliary-loss-free strategy for load balancing and sets a multi-token prediction training objective for stronger performance. We pre-train DeepSeek-V3 on 14.8 trillion diverse and high-quality tokens, followed by Supervised Fine-Tuning and Reinforcement Learning stages to fully harness its capabilities. Comprehensive evaluations reveal that DeepSeek-V3 outperforms other open-source models and achieves performance comparable to leading closed-source models. Despite its excellent performance, DeepSeek-V3 requires only 2.788M H800 GPU hours for its full training. In addition, its training process is remarkably stable. Throughout the entire training process, we did not experience any irrecoverable loss spikes or perform any rollbacks. The model checkpoints are available at https://github.com/deepseek-ai/DeepSeek-V3.

Paper: https://arxiv.org/pdf/2412.19437v1.pdf

Code: https://github.com/deepseek-ai/deepseek-v3

@Machine_learn