AIAIAny
  • Search
  • Collection
  • Category
  • Tag
  • Daily AI
AIAIAny

Tag

Explore by tags

AIAIAny

Curated AI Resources for Everyone

[email protected]

Powered by airss.app

Product
  • Search
  • Collection
  • Category
  • Tag
Resources
  • Blog
Company
  • Privacy Policy
  • Terms of Service
  • Sitemap
Copyright © 2026 All Rights Reserved.
  • All

  • 30u30

  • ASR

  • ChatGPT

  • GNN

  • IDE

  • RAG

  • agent-skills

  • ai

  • ai-agent

  • ai-api

  • ai-api-management

  • ai-client

  • ai-coding

  • ai-demos

  • ai-deploy

  • ai-development

  • ai-framework

  • ai-image

  • ai-image-demos

  • ai-inference

  • ai-leaderboard

  • ai-library

  • ai-rank

  • ai-serving

  • ai-tools

  • ai-train

  • ai-video

  • ai-workflow

  • AIGC

  • algorithms

  • alibaba

  • amazon

  • android

  • anthropic

  • audio

  • aws

  • biology

  • blog

  • book

  • bytedance

  • chatbot

  • chatgpt

  • chemistry

  • claude

  • claude-code

  • cli

  • code

  • codex

  • copilot

  • course

  • cuda

  • cursor

  • deepmind

  • deepseek

  • depth

  • devops

  • diffusers

  • docker

  • drug-discovery

  • electron

  • embeddings

  • engineering

  • evaluation

  • facebook

  • finance

  • flow-matching

  • foundation

  • foundation-model

  • gemini

  • gemini-cli

  • gemma

  • genomics

  • gitHub

  • github

  • go

  • google

  • gradient-booting

  • grok

  • groq

  • huggingface

  • image

  • ios

  • java

  • javascript

  • json

  • kimi

  • llama.cpp

  • LLM

  • llm

  • lora

  • mLOps

  • math

  • mcp

  • mcp-client

  • mcp-server

  • meta-ai

  • meta-pytorch

  • metal

  • microsoft

  • mlops

  • mobile

  • multilingual

  • multimodal

  • mysql

  • NLP

  • nlp

  • nodejs

  • numpy

  • nvidia

  • ocr

  • ollama

  • openai

  • opencode

  • pandas

  • paper

  • physics

  • pi

  • plugin

  • polars

  • postgres

  • privacy

  • prompt-engineering

  • pwa

  • python

  • pytorch

  • qwen

  • react

  • reasoning

  • RL

  • robotics

  • rust

  • science

  • security

  • segmentation

  • shodan

  • skillkit

  • sora

  • speech

  • sqlite

  • ssh

  • stt

  • swe

  • tensorrt

  • terminal

  • transformers

  • translation

  • tts

  • tutorial

  • typescript

  • vibe-coding

  • video

  • vision

  • vllm

  • voice

  • windsurf

  • xAI

  • xai

Machine Learning Foundation Papers·2014

Recurrent Neural Network Regularization

Wojciech Zaremba, Ilya Sutskever +1·New York University, Google Brain

A one-line fix that finally made dropout work with LSTMs: apply it only to the non-recurrent connections, leaving the memory path untouched. This let researchers train much larger RNNs without the overfitting that had capped their size.

#foundation#30u30#paper
Natural Language Processing Papers·2014
Icon for item

Sequence to Sequence Learning with Neural Networks

Ilya Sutskever, Oriol Vinyals +1

End-to-end encoder–decoder using deep LSTMs to map variable-length input sequences to output sequences; demonstrated competitive English→French translation (BLEU 34.8) and improved optimization by reversing source sentences, showing strong handling of long sentences.

#paper#nlp#translation
Machine Learning Foundation Papers·2014

Neural Turing Machines

Alex Graves, Greg Wayne +1·Google DeepMind

Bolts a differentiable, addressable memory bank onto a neural network and trains the whole thing with gradient descent, letting it learn algorithms like copying, sorting, and recall from examples — a learned computer rather than a fixed circuit.

#foundation#30u30#paper
Machine Learning Foundation Papers·2015

Pointer Networks

Oriol Vinyals, Meire Fortunato +1·Google Brain, UC Berkeley

Repurposes attention as a pointer that selects positions in the input rather than blending them into a context vector, so the output vocabulary can grow with input length — handling sorting, convex hulls, and TSP that fixed seq2seq cannot.

#foundation#30u30#paper
Machine Learning Foundation Papers·2015

Order Matters Sequence to sequence for sets

Oriol Vinyals, Samy Bengio +1·Google Brain

Demonstrates that the order you feed inputs and outputs into a seq2seq model changes what it learns — even for sets that have no inherent order — and adds an attention-based set encoder plus a training loss that searches over output orderings.

#foundation#30u30#paper
Computer Vision Papers·2015

Multi-Scale Context Aggregation by Dilated Convolutions

Fisher Yu, Vladlen Koltun·Princeton University, Intel Labs

Introduced dilated (atrous) convolutions, which expand a filter's receptive field exponentially with no loss of resolution and no extra parameters — the trick that let dense-prediction networks see wide context while keeping per-pixel detail.

#30u30#paper#vision
Speech Technology Papers·2015

Deep Speech 2: End-to-End Speech Recognition in English and Mandarin

Dario Amodei, Rishita Anubhai +32·Baidu Research

Bet that one neural net, scaled with HPC, could transcribe both English and Mandarin without hand-built pipelines — reaching human-competitive accuracy by training fast enough to iterate on architecture in days, not weeks.

#30u30#paper#audio#ASR
Machine Learning Foundation Papers·2015

Deep Residual Learning for Image Recognition

Kaiming He, Xiangyu Zhang +2·Microsoft Research

Before residual connections, stacking more layers made networks worse, not better — this 2015 paper fixed that by having layers learn a residual F(x)=H(x)-x via shortcut connections, enabling 152-layer nets that won ILSVRC 2015.

#foundation#30u30#paper#vision
Reinforcement Learning Papers·2016

Mastering the game of Go with deep neural networks and tree search

David Silver, Aja Huang +18·Google DeepMind

Combines a policy network (to narrow move choices) and a value network (to score board positions) with Monte Carlo tree search, cutting Go's vast search space enough to beat top programs 99.8% of the time and the European champion 5-0.

#RL#deepmind#paper
Computer Vision Papers·2016

Identity Mappings in Deep Residual Networks

Kaiming He, Xiangyu Zhang +2·Microsoft Research

Re-examines residual blocks and shows that pure identity skip connections plus pre-activation (BN-ReLU before each conv) let gradients flow cleanly enough to train a 1001-layer ResNet, hitting 4.62% error on CIFAR-10.

#foundation#30u30#paper#vision
Machine Learning Foundation Papers·2016

Variational Lossy Autoencoder

Xi Chen, Diederik P. Kingma +6·OpenAI, UC Berkeley

Reframes the VAE's tendency to ignore its latent code as a controllable design choice: by limiting a PixelCNN decoder's receptive field and using autoregressive flow priors, the code is forced to keep only global structure and discard local texture.

#30u30#paper#vision
Machine Learning Foundation Papers·2017

Neural Message Passing for Quantum Chemistry

Justin Gilmer, Samuel S. Schoenholz +3·Google Brain, Google +1

Recasts a scatter of competing graph-network designs as one message-passing recipe — propagate, aggregate, read out — then proves it on QM9, hitting chemical accuracy on most molecular property targets without hand-built descriptors.

#foundation#30u30#paper#science#chemistry
  • Previous
  • 1
  • 2
  • 3
  • More pages
  • 18
  • 19
  • Next