Tutte le pagine
- AI2 Reasoning Challenge (Arc C)
- A Comprehensive Overview of Large Language Models
- A Few Brief Notes on DeepImpact, COIL, and a Conceptual Framework for Information Retrieval Techniques
- A Focused Backpropagation Algorithm for Temporal Pattern Recognition
- A Large-Scale Document-Level Relation Extraction Dataset
- A Neural Algorithm of Artistic Style (2015)
- A Neural Probabilistic Language Model
- A Theory for Emergence of Complex Skills in Language Models (2023)
- Ablation (Intelligenza Artificiale)
- Adding Conditional Control to Text-to-Image Diffusion Models
- Adversarial Endings
- Adversarial Filtering (AF)
- AlexNet
- Alex Krizhevsky
- Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Models
- Allineamento dell'Intelligenza Artificiale
- Allucinazione
- Alpaca
- Alpaca: A Strong, Replicable Instruction-Following Model
- AlphaFold
- An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction (CLINC150)
- An algorithm for suffix stripping
- Andrej Karpathy
- Andrew NG
- Apprendimento Auto-Supervisionato
- Apprendimento Per Rinforzo
- Apprendimento per rinforzo da feedback umano
- Arc C
- Are Large Language Models Geospatially Knowledgeable?
- Are Sixteen Heads Really Better than One?
- Are We Done with MMLU?
- Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models
- Attention (Machine Learning)
- Attention Is All You Need (2017)
- Autoencoder
- Automa Cellulare Convoluzionale
- Automatic Stylistic Composition of Bach Chorales With Deep LSTM (2017)
- BABILong
- BART
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
- BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models
- BERT
- BERT Rediscovers the Classical NLP Pipeline
- BERT for Classification: Beyond the Next Sentence Prediction Task
- BLEU: a method for automatic evaluation of machine translation
- Backpropagation
- Biaxial LSTM
- Biaxial LSTM (DeepJ - musica)
- Bilingual Evaluation Understudy (BLEU)
- BoolQ
- Byte-Pair Encoding (BPE)
- CAMEL (Agent Framework)
- CLINC150
- COIL: Revisit exact lexical match in information retrieval with contextualized inverted list
- Capacità Emergenti
- Causal Language Modeling (CLM)
- Chain of Density Prompting
- Chain of Thought
- Chain of Thought Prompting Elicits Reasoning in Large Language Models
- Classifier-Free Diffusion Guidance
- Clip Skip
- Come creare un tensore su Pytorch
- Come creare una RNN da zero con PyTorch
- Computer Vision
- ConceptNet
- Confabulazione
- Connessionismo
- Contamination Testing
- Contatti
- Context-Aware Term Weighting For First Stage Passage Retrieval
- Contrastive Language-Image Pretraining (CLIP)
- Contriever
- ControlNet
- Convinzione (Belief)
- Convolutional Neural Networks for Sentence Classification
- Crawling the Internal Knowledge-Base of Language Models
- Cross-lingual Transfer Evaluation of Multilingual Encoders (XTREME)
- DROP
- Dall-e 3 (2023)
- Daphne Koller
- Dasdasdasdas
- Dataset MIDI per addestrare modelli generativi di Musica
- Dataset di Preferenze
- Decoding Intelligence: A Framework for Certifying Knowledge Comprehension in LLMs
- DeepDream
- DeepJ: Style-Specific Music Generation (2018)
- Deep Contextualized Word Representations
- Deep Convolutional Neural Networks (AlexNet)
- Deep Reinforcement Learning from Human Preferences
- Deep Residual Learning for Image Recognition
- Deep Unsupervised Learning using Nonequilibrium Thermodynamics
- Deleteme 1
- Demis Hassabis
- Dense Passage Retrieval for Open-Domain Question Answering
- Detection Transformer
- Dialogflow CX
- Dialogue State Tracking
- Diffusion Models Beat GANs on Image Synthesis
- Discrete Reasoning Over Paragraphs (DROP)
- Distillazione Della Conoscenza
- DocRED: A Large-Scale Document-Level Relation Extraction Dataset
- Document Deduplication with Locality Sensitive Hashing
- Downstream Tasks, Addestramento e Capacità Emergenti dei Modelli di Linguaggio di Grandi Dimensioni
- Dropout (Reti Neurali)
- Effetto Dunning-Kruger
- Efficient Estimation of Word Representations in Vector Space
- Elaborazione del Linguaggio Naturale (NLP)
- Eliezer Yudkowsky
- Embeddings
- Emergent Abilities of Large Language Models
- End-to-End Object Detection with Transformers
- Estimating Knowledge in Large Language Models Without Generating a Single Token
- Extended Long Short-Term Memory
- Extras
- FANNG: Fast Approximate Nearest Neighbour Graphs
- Fast Inference from Transformers via Speculative Decoding
- Fei-Fei Li
- Few-shot learning
- Finding Structure in Time
- Fine-tuning
- Forward pass
- Frank Rosenblatt
- Function Calling
- Functional Benchmarks for Robust Evaluation of Reasoning Performance, and the Reasoning Gap
- Functional Decision Theory: A New Theory of Instrumental Rationality
- Funzione Obiettivo (loss)
- Funzione di attivazione
- GLoVe
- GPT
- GPT-4 Technical Report
- GPT e la Nuova Generazione di Modelli AI
- GSM8K
- General Language Understanding Evaluation (GLUE)
- Generalizzazione zero-shot
- Generating Sequences With Recurrent Neural Networks
- Generating Sequences With Recurrent Neural Networks (2014)
- Generative Adversarial Nets
- Generative Adversarial Networks (GAN)
- Generative Pretrained Transformer (GPT)
- Generazione di Testo
- Geoffrey Hinton
- GloVe: Global Vectors for Word Representation
- Going Deeper with Convolutions
- GoogLeNet
- Google Model Garden
- Gorilla: Large Language Model Connected with Massive APIs
- Gorilla OpenFunctions
- Gradio
- Gradio (Stable Diffusion)
- Grokking
- Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets
- Guiding Attention with Evidence for Improving Document-Level Relation Extraction (DREEAM)
- HMDB: a large human motion database
- Hallucinating Faces
- Harmonizing Music the Boltzmann Way (1994)
- HellaSwag
- HellaSwag: Can a Machine Really Finish Your Sentence?
- Hierarchical Attention Networks for Document Classification
- High-Resolution Image Synthesis with Latent Diffusion Models
- Highly accurate protein structure prediction with AlphaFold
- How Many Data Points is a Prompt Worth?
- How to Fine Tune Bert for Sequence Classification?
- HumanEval
- Hypernetworks
- IKEVA-HAI (IULM AI Lab)
- Ian Goodfellow
- Ilya Sutskever
- ImageNet Large Scale Visual Recognition Challenge
- Img2img
- In Search of Needles in a 11M Haystack:Recurrent Memory Finds What LLMs Miss
- InstructGPT
- InstructGPT: Training Language Models to Follow Instructions with Human Feedback
- InstructPix2Pix: Learning to Follow Image Editing Instructions
- Is Power-Seeking AI an Existential Risk?
- James McClelland
- Judging LLM-as-a-judge with MT-Bench and Chatbot Arena
- Jürgen Schmidhuber
- Kernel di convoluzione
- KeyBERT
- LAION-5B
- LAION-5B: An open large-scale dataset for training next generation image-text models
- LLM-as-a-judge
- LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models
- LLaMA: Open and Efficient Foundation Language Models
- LSTM
- Language Models are Few-Shot Learners
- Language Models are Few-Shot Learners (2020)
- Large Language Models as Zero-shot Dialogue State Tracker through Function Calling (16/02/2024)
- LayerNorm
- LeNet
- Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
- Learning Transferable Visual Models From Natural Language Supervision
- Learning long-term dependencies with gradient descent is difficult
- Libero Arbitrio
- Linee Guida della Wiki AI Lab
- Llama
- LoRA
- Logit (Reti Neurali)
- LongAlign
- LongAlign: A Recipe for Long Context Alignment of Large Language Models
- Long Short-Term Memory
- Long Short-Term Memory (LSTM)
- M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation
- MATH
- MBPP
- MMLU
- MS COCO
- Macchine di Boltzmann Restrittive (RBM)
- Magenta
- MarbleNet: Deep 1D Time-Channel Separable Convolutional Neural Network for Voice Activity Detection
- Masked-Language-Modeling (MLM)
- Massive Multitask Language Understanding
- Mean Reciprocal Rank
- MemGPT
- MemGPT: Towards LLMs as Operating Systems
- Metodi di Decoding
- MiDaS
- MiDaS v3.1 – A Model Zoo for Robust Monocular Relative Depth Estimation
- Microsoft Machine Reading Comprehension (MS MARCO)
- Mind2Web
- Mistral
- Mixture of Experts
- Model Garden
- Modello Generativo
- Modello di Diffusione Latente (LDM)
- Modello linguistico di grandi dimensioni
- Modello linguistico di grandi dimensioni per il linguaggio parlato
- MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training
- Musica e Audio
- NETtalk
- NaturalQuestions
- Natural language inference (NLI)
- Negative log-likelihood
- Neural Information Retrieval
- Neural Machine Translation by Jointly Learning to Align and Translate
- Neural networks and physical systems with emergent collective computational abilities
- Non-Maximum Suppression
- None
- Numero di Parametri nelle Reti Neurali
- O1
- Obiettivo di pre-training
- On the difficulty of training recurrent neural networks
- One-hot encodings
- Ontologia (Informatica)
- Ontologia della Wiki AI
- Open-Domain Question Answering (ODQA)
- OpenAI
- OpenAI o1
- Optimizer (Reti Neurali)
- Output Strutturato, Function Calling e Agenti
- PaLM
- Pagina principale
- Papers-in-100-Lines-of-Code
- Parallel Networks that Learn to Pronounce English Text
- Parameter-Efficient Fine-Tuning
- Persone Influenti Nel Settore Dell'Intelligenza Artificiale
- Physics in Next-token Prediction
- Pop Music Transformer: Beat-based Modeling and Generation of Expressive Pop Piano Compositions
- Porter Stemmer
- Povertà dello stimolo (Linguistica)
- Powers of 10: Modeling Complex information-seeking systems at multiple scales
- Pre-training of Deep Bidirectional Transformers for Language Understanding
- Prefix-Tuning
- Prefix-tuning: Optimizing continuous prompts for generation
- Problema difficile della coscienza
- Prompt Injection
- Prompting
- Proximal Policy Optimization
- Proximal Policy Optimization (PPO)
- PyTorch
- QuAC
- Quantizzazione
- Reading Comprehension Task (RC)
- Reading Wikipedia to Answer Open-Domain Questions
- Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index
- Reasoning Gap
- Reasoning and Acting (prompting)
- RecurrentGPT
- Recurrent Neural Network (RNN)
- Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
- Red Teaming
- Reinforcement Learning From Human Feedback (RLHF)
- Resource Description Framework (RDF)
- Rete Generativa Avversaria
- Rete Neurale Artificiale (ANN)
- Rete Neurale Feed-Forward (FNN)
- Rete Neurale Residua (ResNet)
- Rete Neurale Ricorrente (RNN)
- Reti Neurali Convoluzionali (CNN)
- Retrieval, Embeddings, RAG
- Retropropagazione
- Ricerca ANN
- RoBERTa: A Robustly Optimized BERT Pretraining Approach
- SOTA
- SPLADE
- SQuAD
- Sampling method (Stable Diffusion)
- Scaling Laws
- Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
- Schema di Winograd
- Semantic Textual Similarity (STS)
- Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
- SentencePiece
- Sepp Hochreiter
- Sequence to Sequence (seq2seq)
- Sequence to Sequence Learning with Neural Networks (12/12/2014)
- Set-of-Mark Prompting
- Sigmoide
- Sistemi di supporto alla ricerca di informazioni (ISSS)
- Softmax
- Speculative Decoding
- Stable Diffusion
- Stable Diffusion WebUI
- Step by Step
- StyleGAN
- Survey of Hallucination in Natural Language Generation
- Taming Transformers for High-Resolution Image Synthesis
- Teacher Forcing (Reti Neurali)
- Technical Report, Palm 2
- Temperatura (Apprendimento Automatico)
- Tensore (Informatica)
- Tensore (PyTorch)
- Test-Time Compute Scaling
- Test di Turing
- TextualInversion
- The Natural Language Decathlon: Multitask Learning as Question Answering
- The Schema-Guided Dialogue Dataset
- The Theory of Stochastic Processes, with Particular Reference to Applications
- The Unreasonable Effectiveness of Recurrent Neural Networks
- The perceptron: A probabilistic model for information storage and organization in the brain
- Tomáš Mikolov
- Topic Segmentation
- Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer
- Training Compute-Optimal Large Language Models
- Training language models to follow instructions with human feedback
- Transformer
- Transformer (Architettura di Deep Learning)
- Txt2img (Stable Diffusion)
- UCF101 - Action Recognition Data Set
- ULMFiT
- Unsupervised Dense Information Retrieval with Contrastive Learning
- Unsupervised Topic Segmentation of Meetings with BERT Embeddings
- Utilizzare le API di OpenAI
- VGG16 (ConvNet)
- ValueNet: A New Dataset for Human Value Driven Dialogue System