Search:
Sources
ArXiv CS.AI
ArXiv CS.LG
Bluesky
Dev.to
GitHub Trending
Google DeepMind Blog
Hacker News
HuggingFace Papers
LinkedIn
Lobsters
OpenAI Blog
Twitter/X
YouTube
Topics
llms 98
research 97
code 68
agents 53
training 46
products 41
tutorials 40
open-source 28
inference 25
computer-vision 20
rag 19
infrastructure 16
safety 8
Entities
Claude 38
OpenAI 31
Anthropic 24
Google 19
Gemini 16
MCP 15
Claude Code 13
GitHub 13
AI systems 12
Codex 11
GPT-5 10
Docker 9
NVIDIA 9
DeepSeek 9
Llama 9
EU 8
Hugging Face 7
Transformers 7
Perplexity 5
Microsoft 5
Ax Shiyi Zhang, Yiji Cheng, Tiankai Hang, Zijin Yin, Runze He, Yu Xu, Wenxun Dai, Yunlong Lin, Chunyu Wang, Qinglin Lu, Yansong Tang 4/28/2026

Meta-CoT: Enhancing Granularity and Generalization in Image Editing

arXiv paper on XGRAG framework for explaining knowledge graph-based retrieval-augmented generation systems with interpretability methods.

Ax Simon Axelrod, Miroslav Ka\v{s}par, Krist\'yna Jel\'inkov\'a, Mark\'eta \v{S}m\'idkov\'a, Erika Bart\r{u}\v{n}kov\'a, Sille \v{S}t\v{e}p\'anov\'a, Eugene Shakhnovich, V\'aclav Ka\v{s}i\v{c}ka, Martin Dra\v{c}\'insk\'y, Zlatko Janeba, Rafael G\'omez-Bombarelli 4/28/2026

Computational Design and Experimental Validation of Photoactive PARP1 Inhibitors

arXiv paper proposing Meta-CoT, a two-level decomposition paradigm for improving chain-of-thought reasoning in image editing models.

Ax Parsa Ashrafi Fashi, Utkarsh Saxena, Mehdi Rezagholizadeh, Aref Jafari, Akash Haridas, Mingyu Yang, Vansh Bhatia, Guihong Li, Vikram Appia, Emad Barsoum 4/28/2026

Long-Context Aware Upcycling: A New Frontier for Hybrid LLM Scaling

Method to convert pretrained Transformer LLMs into hybrid architectures combining Transformers with linear sequence modeling blocks, preserving short-context quality while improving long-context capability.

Ax Peiyu Yu, Dinghuai Zhang, Hengzhi He, Xiaojian Ma, Sirui Xie, Ruiyao Miao, Yifan Lu, Yasi Zhang, Deqian Kong, Ruiqi Gao, Jianwen Xie, Guang Cheng, Ying Nian Wu 4/28/2026

"Noisier" Noise Contrastive Eestimation is (Almost) Maximum Likelihood

Investigation of noise distribution magnitude in Noise Contrastive Estimation for improved distribution ratio estimation.

Ax Nils Graef, Filip Makraduli, Andrew Wasielewski, Matthew Clapp 4/28/2026

FlashNorm: Fast Normalization for Transformers

FlashNorm: Reformulation of RMSNorm that eliminates computation bottlenecks in LLM inference and training.

HN teleforce 4/27/2026

What is physical AI?

DeepSeek V4 prices 97% below OpenAI GPT-5.5, targeting enterprise and agent developers, potentially triggering market price war.

HN simonpure 4/27/2026

How My RLM Tool Works

Nirvanic AI explores continuous learning and present-moment processing for humanoid robotics and AGI development.

HN latchkey 4/27/2026

AMD used AI to reimplement slurm in Rust

AMD used AI to reimplement Slurm job scheduler in Rust with GPU-first scheduling, WireGuard mesh networking, and modern state management.

HN dalemyers 4/27/2026

LLMs and the Adversarial Loop

OlmoEarth platform now exports embedding vectors from open-source Earth observation foundation models; code and weights publicly available.