Paper

Dawn of Practical Quantum Chemistry: ByteQC Toolkit by ByteDance Research

Accelerate quantum chemistry with ByteQC – ByteDance Research’s GPU-powered toolkit delivering gold standard accuracy for large-scale molecular…

Mar 6 •

2024 Turing Award Honors Reinforcement Learning Father Richard Sutton and Mentor Andrew Barto

Reinforcement Learning pioneers Andrew Barto and Richard Sutton win the 2024 ACM Turing Award for groundbreaking contributions in AI.

Mar 5 •

DeepSeek R1 Technology Successfully Migrates to the Multimodal Domain, Fully Open Sourced

Discover Visual-RFT—an open-source breakthrough that extends DeepSeek-R1’s rule-based reinforcement learning to vision-language models for efficient…

Mar 4 •

DeepSeek's GRPO: Complete From-Scratch Implementation

Discover how to implement GRPO from scratch using Qwen2.5-1.5B-Instruct in this comprehensive distributed RL tutorial to boost model performance and…

Mar 2 •

Muon Optimizer: 48% Less Compute Than AdamW, Compatible with DeepSeek

Discover how Dark Side of the Moon's improved Muon optimizer cuts computational requirements by 48% over AdamW, scales to larger models, and is…

Feb 23 •

MoBA Attention by Kimi Yang: DeepSeek NSA Collision & Code Release

Discover the MoBA attention mechanism, an advanced approach combining MoE and FlashAttention for efficient long-sequence processing in large language…

Feb 20 •

OpenAI Launches Million-Dollar AI Programming Test: Claude 3.5 Tops the Benchmark!

OpenAI introduces SWE-Lancer, a million-dollar AI benchmark testing real-world software engineering tasks. Claude 3.5 leads the way, setting new…

Feb 19 •

DeepSeek's Liang Wenfeng Unveils NSA: A Game-Changing Attention Architecture

DeepSeek's NSA introduces a fast, hardware-aligned sparse attention mechanism for efficient long-context training and inference in large models.

Feb 18 •

DeepSeek Launches CODEI/O: Enhancing Large Model Inference with Thought Chains

DeepSeek's CODEI/O dataset enhances model reasoning by transforming code into natural language thought chains, improving performance across various…

Feb 17 •

MakeAnything Unlocks Multi-task Process Generation with Diffusion Transformer

MakeAnything combines Diffusion Transformer and asymmetric LoRA to unlock cross-domain, high-quality multi-task process generation, achieving…

Feb 16 •

Apple Discovers Model Distillation Scaling Law! Stronger Teacher Models Aren't Always Better

Apple researchers uncover a new distillation scaling law, optimizing computational resources for better model performance. Learn how to improve AI…

Feb 14 •

ByteDance Proposes Dense Video Multimodal Large Model Sa2VA

Sa2VA, developed by ByteDance and Peking University, integrates SAM-2 and LLaVA to achieve advanced spatiotemporal video and image understanding…

Feb 12 •

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts