Канал: Data Science Gems

LLMLingua: Compressing Prompts for Accelerated Inference of LLMs

LLMLingua: Compressing Prompts for Accelerated Inference of LLMs

LaMP: Personalization Benchmark for LLMs

LaMP: Personalization Benchmark for LLMs

LaMini-LM: A diverse herd of distilled models from large-scale instructions

LaMini-LM: A diverse herd of distilled models from large-scale instructions

Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Mamba: Linear-Time Sequence Modeling with Selective State Spaces

CircuitVQA: A VQA Dataset for Electrical Circuit Images

CircuitVQA: A VQA Dataset for Electrical Circuit Images

OAK: Enriching Doc Representations using Auxiliary Knowledge for XC

OAK: Enriching Doc Representations using Auxiliary Knowledge for XC

OLMo

OLMo

OpenAI's gpt4o

OpenAI's gpt4o

Apple's OpenELM models

Apple's OpenELM models

Supporting Infinite Context Length using TransformerFAM

Supporting Infinite Context Length using TransformerFAM

Infini attention and Infini Transformer

Infini attention and Infini Transformer

MEGALODON: Efficient LLM Pretraining and Inference with Unlimited Context Length

MEGALODON: Efficient LLM Pretraining and Inference with Unlimited Context Length

Microsoft VASA-1: Lifelike Audio Driven Talking Faces Generated in Real Time

Microsoft VASA-1: Lifelike Audio Driven Talking Faces Generated in Real Time

Microsoft Phi-3

Microsoft Phi-3

Meta Llama 3

Meta Llama 3

DAC: Detoxifying Query Auto-Completions

DAC: Detoxifying Query Auto-Completions

BitNet b1.58: The era of 1-bit LLMs

BitNet b1.58: The era of 1-bit LLMs

BitNet: Scaling 1-bit Transformers for LLMs

BitNet: Scaling 1-bit Transformers for LLMs

Zephyr

Zephyr

GritLM: Generative Representational Instruction Tuning

GritLM: Generative Representational Instruction Tuning

OpenAI's SORA

OpenAI's SORA

Direct Preference Optimization

Direct Preference Optimization

Google Deepmind's Gemma

Google Deepmind's Gemma

AlphaGeometry: An Olympiad-level AI system for geometry

AlphaGeometry: An Olympiad-level AI system for geometry

Scaling Laws for Data Constrained LLM Training

Scaling Laws for Data Constrained LLM Training

Are Emergent Abilities of Large Language Models a Mirage?

Are Emergent Abilities of Large Language Models a Mirage?

When to show a suggestion on Github Copilot?

When to show a suggestion on Github Copilot?

LEVER: Enhancing Tail Perf In XC By Label Variance Reduction

LEVER: Enhancing Tail Perf In XC By Label Variance Reduction

DQAC: Detoxifying Query Auto-Completion with Adapters

DQAC: Detoxifying Query Auto-Completion with Adapters

Lumiere: A Space-Time Diffusion Model for Video Generation

Lumiere: A Space-Time Diffusion Model for Video Generation

Emu: Foundation Model for Multimodal Generation

Emu: Foundation Model for Multimodal Generation

ControlNet: Adding Conditional Control to Text-to-Image Diffusion Models

ControlNet: Adding Conditional Control to Text-to-Image Diffusion Models

Microsoft's LongVIT: Image Represention using long sequences for Computational Pathology

Microsoft's LongVIT: Image Represention using long sequences for Computational Pathology

Purple Llama CyberSecEval from Meta AI

Purple Llama CyberSecEval from Meta AI

Overview of Small Language Models

Overview of Small Language Models

Google Gemini: Multimodal LLMs

Google Gemini: Multimodal LLMs

SOLAR 10.7B: Scaling LLMs with Depth Up-Scaling

SOLAR 10.7B: Scaling LLMs with Depth Up-Scaling

Microsoft's Orca 2: Teaching Small Language Models How to Reason

Microsoft's Orca 2: Teaching Small Language Models How to Reason

Orca: Progressive Learning from Complex Explanation Traces of GPT-4

Orca: Progressive Learning from Complex Explanation Traces of GPT-4

Z-Code++: Pretrained language model for Abstractive Summarization

Z-Code++: Pretrained language model for Abstractive Summarization

Microsoft Phi-2: The surprising power of small language models (SLMs)

Microsoft Phi-2: The surprising power of small language models (SLMs)

Mixtral of Experts

Mixtral of Experts

Mistral-7B

Mistral-7B

XLGen: Cluster Guided Label Generation in XC

XLGen: Cluster Guided Label Generation in XC

Open Vocabulary XC Using Generative Models

Open Vocabulary XC Using Generative Models

ICXML: In-Context Learning Framework for XC

ICXML: In-Context Learning Framework for XC

PINA: Leveraging Side Information in XC via Predicted Instance Neighborhood Aggregation

PINA: Leveraging Side Information in XC via Predicted Instance Neighborhood Aggregation

DEXA: Deep Encoders with Auxiliary Parameters for XC

DEXA: Deep Encoders with Auxiliary Parameters for XC

InceptionXML: A Lightweight Framework with Synchronized Negative Sampling for Short Text Extreme C

InceptionXML: A Lightweight Framework with Synchronized Negative Sampling for Short Text Extreme C

Renée: Multi-GPU end-to-end of XC models

Renée: Multi-GPU end-to-end of XC models

NGAME: Negative Mining aware Mini batching for XC

NGAME: Negative Mining aware Mini batching for XC

CascadeXML: Transformers for End to end Multi resolution Training in XC

CascadeXML: Transformers for End to end Multi resolution Training in XC

XRTransformer: Fast Multi-Resolution Transformer Fine-tuning for XC

XRTransformer: Fast Multi-Resolution Transformer Fine-tuning for XC

LightXML: Transformer with Dynamic Negative Sampling for XC

LightXML: Transformer with Dynamic Negative Sampling for XC

MUFIN: Multi modal XC

MUFIN: Multi modal XC

GZXML/ZestXML: Generalized Zero Shot Extreme Multi label Learning

GZXML/ZestXML: Generalized Zero Shot Extreme Multi label Learning

SiameseXML: Siamese Networks meet XC with 100M Labels

SiameseXML: Siamese Networks meet XC with 100M Labels

GalaXC: Graph Neural Networks with Labelwise Attention for XC

GalaXC: Graph Neural Networks with Labelwise Attention for XC

ECLARE: XC with Label Graph Correlations

ECLARE: XC with Label Graph Correlations

DECAF: Deep Extreme Classification with Label Features

DECAF: Deep Extreme Classification with Label Features

DeepXML: An XC Framework and ASTEC: A DeepXML Algorithm

DeepXML: An XC Framework and ASTEC: A DeepXML Algorithm

Searching for "Numbat digging in the ground"? CSTBIR: Composite Sketch+Text Based Image Retrieval

Searching for "Numbat digging in the ground"? CSTBIR: Composite Sketch+Text Based Image Retrieval

AttentionXML: Label Tree based Attention Aware Deep Model for High Performance XC

AttentionXML: Label Tree based Attention Aware Deep Model for High Performance XC

XML-CNN: Deep Learning for Extreme Multi label Text Classification

XML-CNN: Deep Learning for Extreme Multi label Text Classification

Deep Networks With Large Output Spaces: Softmax using hashing

Deep Networks With Large Output Spaces: Softmax using hashing

Parabel: Partitioned Label Trees for XC

Parabel: Partitioned Label Trees for XC

DiSMEC: Distributed Sparse Machines for Extreme Multi label Classification

DiSMEC: Distributed Sparse Machines for Extreme Multi label Classification

Representation Learning for Dialog Systems

Representation Learning for Dialog Systems

Tree based methods for Extreme Classification

Tree based methods for Extreme Classification

Introduction to Extreme Classification

Introduction to Extreme Classification

Flamingo: Visual Language Model for Few-Shot Learning

Flamingo: Visual Language Model for Few-Shot Learning

Vision Transformers

Vision Transformers

LAION-5B: Dataset for training image-text models

LAION-5B: Dataset for training image-text models

mPLUG-2: Multi-modal Foundation Model Across Text, Image and Video

mPLUG-2: Multi-modal Foundation Model Across Text, Image and Video

mPLUG: Vision-Language Learning by Cross-modal Skip-connections

mPLUG: Vision-Language Learning by Cross-modal Skip-connections

Florence-2: Foundation Model for Vision and Vision-Language Tasks

Florence-2: Foundation Model for Vision and Vision-Language Tasks

VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding

VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding

InstructBLIP: Vision-Language Models with Instruction Tuning

InstructBLIP: Vision-Language Models with Instruction Tuning

BLIP2: BLIP with frozen image encoders and LLMs

BLIP2: BLIP with frozen image encoders and LLMs

BLIP: LLM for vision-language tasks

BLIP: LLM for vision-language tasks

MiniGPT 4

MiniGPT 4

Visual Instruction Tuning using LLaVA

Visual Instruction Tuning using LLaVA

Video-to-video translation, video object tracking, video super-resolution using CoDeF

Video-to-video translation, video object tracking, video super-resolution using CoDeF

ReConcile: Round-table conference with LLMs

ReConcile: Round-table conference with LLMs

MADLAD 400: Clean Multilingual Dataset with 400+ languages

MADLAD 400: Clean Multilingual Dataset with 400+ languages

How to do moment retrieval, highlight detection and video summarization in videos?

How to do moment retrieval, highlight detection and video summarization in videos?

Prompt2Model: How can I generate deployable models using prompt engineering?

Prompt2Model: How can I generate deployable models using prompt engineering?

On Robustness of Finetuned Transformer-based NLP Models

On Robustness of Finetuned Transformer-based NLP Models

Frugal Prompting for Dialog Models

Frugal Prompting for Dialog Models

AutoGen: Enabling Next Gen LLM Applications via Multi Agent Conversation Framework

AutoGen: Enabling Next Gen LLM Applications via Multi Agent Conversation Framework

Query-Dependent Video Representation for Moment Retrieval and Highlight Detection

Query-Dependent Video Representation for Moment Retrieval and Highlight Detection

The Belebele Benchmark

The Belebele Benchmark

The Reversal Curse for LLMs

The Reversal Curse for LLMs

MusicGen: Simple and Controllable Music Generation

MusicGen: Simple and Controllable Music Generation

AudioGen: Textually Guided Audio Generation

AudioGen: Textually Guided Audio Generation

DeciLM: 15x higher throughput than Llama 2

DeciLM: 15x higher throughput than Llama 2

Video LLaMA: An Instruction tuned Audio Visual Language Model for Video Understanding

Video LLaMA: An Instruction tuned Audio Visual Language Model for Video Understanding

Microsoft's KOSMOS-2.5: A Multimodal Model for image to markdown

Microsoft's KOSMOS-2.5: A Multimodal Model for image to markdown

Interpreting Stable Diffusion Using Cross Attention

Interpreting Stable Diffusion Using Cross Attention

Unfairness in Computer Vision Models

Unfairness in Computer Vision Models

Multimodal Persona Based Generation of Comic Dialogs

Multimodal Persona Based Generation of Comic Dialogs

Hateful Comment Detection and Hate Target Type Prediction for Video Comments

Hateful Comment Detection and Hate Target Type Prediction for Video Comments

Unfairness in NLP models

Unfairness in NLP models

Do Androids Laugh at Electric Sheep? Humor understanding in LLMs

Do Androids Laugh at Electric Sheep? Humor understanding in LLMs

Backpack Language Models

Backpack Language Models

Multimodal Chain of Thought Reasoning in Language Models

Multimodal Chain of Thought Reasoning in Language Models

Tree of Thoughts

Tree of Thoughts

Code Llama from MetaAI

Code Llama from MetaAI

SeamlessM4T: Massively Multilingual Multimodal Machine Translation

SeamlessM4T: Massively Multilingual Multimodal Machine Translation

Part-2 of our IJCAI tutorial on deep learning for Brain Encoding and Decoding

Part-2 of our IJCAI tutorial on deep learning for Brain Encoding and Decoding

Part-4 of our IJCAI tutorial on deep learning for Brain Encoding and Decoding

Part-4 of our IJCAI tutorial on deep learning for Brain Encoding and Decoding

Part-3 of our IJCAI tutorial on deep learning for Brain Encoding and Decoding

Part-3 of our IJCAI tutorial on deep learning for Brain Encoding and Decoding

Part-1 of our IJCAI tutorial on deep learning for Brain Encoding and Decoding

Part-1 of our IJCAI tutorial on deep learning for Brain Encoding and Decoding

Visual Chain of Thought Bridging Logical Gaps with Multimodal Infillings

Visual Chain of Thought Bridging Logical Gaps with Multimodal Infillings

RARR: Researching and Revising What Language Models Say Using Language Models

RARR: Researching and Revising What Language Models Say Using Language Models

Active Retrieval Augmented Generation

Active Retrieval Augmented Generation

Llama Adapter

Llama Adapter

Eleuther AI Pythia

Eleuther AI Pythia

OpenAssistant Conversations

OpenAssistant Conversations

Google UL2 and Flan UL2

Google UL2 and Flan UL2

Any to Any Generation via Composable Diffusion

Any to Any Generation via Composable Diffusion

Meta Transformer: A Unified Framework for Multimodal Learning

Meta Transformer: A Unified Framework for Multimodal Learning

Multimodality with ImageBind from MetaAI

Multimodality with ImageBind from MetaAI

Multimodal Pretraining with Microsoft’s BEiT-3

Multimodal Pretraining with Microsoft’s BEiT-3

Speech Taskonomy

Speech Taskonomy

Rotary Positional Embeddings

Rotary Positional Embeddings

Retrieval Augmented Multimodal Language Modeling

Retrieval Augmented Multimodal Language Modeling

Google Med PaLM M: Towards Generalist Biomedical AI

Google Med PaLM M: Towards Generalist Biomedical AI

Google Med-PaLM

Google Med-PaLM

CM3Leon from MetaAI

CM3Leon from MetaAI

Flash Attention 2: Faster Attention with Better Parallelism and Work Partitioning

Flash Attention 2: Faster Attention with Better Parallelism and Work Partitioning

Flash Attention

Flash Attention

Vicuna from LmSys

Vicuna from LmSys

Stanford Alpaca

Stanford Alpaca

Retentive Network: A Successor to Transformer for Large Language Models

Retentive Network: A Successor to Transformer for Large Language Models

Llama 2: Open Foundation and Fine Tuned Chat Models

Llama 2: Open Foundation and Fine Tuned Chat Models

Baize: An Open Source Chat Model with Parameter Efficient Tuning on Self Chat Data

Baize: An Open Source Chat Model with Parameter Efficient Tuning on Self Chat Data

RefinedWeb Dataset for Falcon LLM

RefinedWeb Dataset for Falcon LLM

Falcon LLM

Falcon LLM

Answer Mining from a Pool of Images: Towards Retrieval Based Visual Question Answering

Answer Mining from a Pool of Images: Towards Retrieval Based Visual Question Answering

TrieNLG: Trie Context Augmentation for Personalized Auto Completion for Short and Unseen Prefixes

TrieNLG: Trie Context Augmentation for Personalized Auto Completion for Short and Unseen Prefixes

REVEAL: Retrieval Augmented Visual Language Pre Training with Multi Source Multimodal Knowledge Me

REVEAL: Retrieval Augmented Visual Language Pre Training with Multi Source Multimodal Knowledge Me

KAT: A Knowledge Augmented Transformer for Vision and Language

KAT: A Knowledge Augmented Transformer for Vision and Language

Internet augmented language models through few shot prompting for open domain question answering

Internet augmented language models through few shot prompting for open domain question answering

Atlas: Few shot Learning with Retrieval Augmented Language Models

Atlas: Few shot Learning with Retrieval Augmented Language Models

Retrieval Enhanced Transformer RETRO: Improving Lang Models by Retrieving from Trillions of Tokens

Retrieval Enhanced Transformer RETRO: Improving Lang Models by Retrieving from Trillions of Tokens

Retrieval Augmented Generation for Knowledge Intensive NLP Tasks

Retrieval Augmented Generation for Knowledge Intensive NLP Tasks

REALM: Retrieval-Augmented Language Model Pre-Training

REALM: Retrieval-Augmented Language Model Pre-Training

Visual ChatGPT: Talking Drawing and Editing with Visual Foundation Models

Visual ChatGPT: Talking Drawing and Editing with Visual Foundation Models

Sparks of Artificial General Intelligence: Early experiments with GPT 4

Sparks of Artificial General Intelligence: Early experiments with GPT 4

QLORA: Efficient Finetuning of Quantized LLMs

QLORA: Efficient Finetuning of Quantized LLMs

Self Instruct: Aligning Language Model with Self Generated Instructions

Self Instruct: Aligning Language Model with Self Generated Instructions

Textbooks Are All You Need: Phi-1 Model for code

Textbooks Are All You Need: Phi-1 Model for code

Chain-of-Thought Prompting Elicits Reasoning in LLMs

Chain-of-Thought Prompting Elicits Reasoning in LLMs

Google Flan PALM Flan T5 and Flan U PALM

Google Flan PALM Flan T5 and Flan U PALM

Google Flan: Finetuned Language Models are zero shot learners

Google Flan: Finetuned Language Models are zero shot learners

LoRA: Low Rank Adaptation of Large Language Models

LoRA: Low Rank Adaptation of Large Language Models

Google Glam: Efficient Scaling of Language Models with Mixture of Experts

Google Glam: Efficient Scaling of Language Models with Mixture of Experts

Introduction to LangChain

Introduction to LangChain

OPT IML from Meta AI: Scaling Language Model Instruction Meta Learning through the Lens of General

OPT IML from Meta AI: Scaling Language Model Instruction Meta Learning through the Lens of General

Facebook OPT: Open Pre trained Transformer Language Models

Facebook OPT: Open Pre trained Transformer Language Models

Google PaLM-E: An Embodied Multimodal Language Model

Google PaLM-E: An Embodied Multimodal Language Model

Google PaLM: Scaling Language Modeling with Pathways

Google PaLM: Scaling Language Modeling with Pathways

Meta's LLaMA: Open and Efficient Foundation Language Models

Meta's LLaMA: Open and Efficient Foundation Language Models

Google BARD and LaMDA: Language Models for Dialog Applications

Google BARD and LaMDA: Language Models for Dialog Applications

Tips on Prompt Engineering

Tips on Prompt Engineering

OpenAI Whisper: Robust Speech Recognition via Large Scale Weak Supervision

OpenAI Whisper: Robust Speech Recognition via Large Scale Weak Supervision

OpenAI GPT-4

OpenAI GPT-4

Overview of Large Language Models

Overview of Large Language Models

Stable Diffusion High resolution image synthesis with latent diffusion models

Stable Diffusion High resolution image synthesis with latent diffusion models

Imagen: Photorealistic Text to Image Diffusion Models with Deep Language Understanding

Imagen: Photorealistic Text to Image Diffusion Models with Deep Language Understanding

OpenAI DALL·E 2: Hierarchical text conditional image generation with clip latents

OpenAI DALL·E 2: Hierarchical text conditional image generation with clip latents

OpenAI GLIDE: Towards Photorealistic Image Generation and Editing with Text Guided Diffusion Model

OpenAI GLIDE: Towards Photorealistic Image Generation and Editing with Text Guided Diffusion Model

OpenAI CLIP: Connecting Text and Images

OpenAI CLIP: Connecting Text and Images

Galactica: A Large Language Model for Science

Galactica: A Large Language Model for Science

LayoutXLM: Multimodal Pre training for Multilingual Visually rich Document Understanding

LayoutXLM: Multimodal Pre training for Multilingual Visually rich Document Understanding

LayoutLMv2: Multi modal Pre training for Visually Rich Document Understanding

LayoutLMv2: Multi modal Pre training for Visually Rich Document Understanding

DeltaLM: Encoder Decoder Pre training for Language Generation and Translation

DeltaLM: Encoder Decoder Pre training for Language Generation and Translation

Super Natural Instructions and Tk-Instruct: Generalization via Declarative Instructions on 1600+ N

Super Natural Instructions and Tk-Instruct: Generalization via Declarative Instructions on 1600+ N

Codex: Large Language Models Trained on Code

Codex: Large Language Models Trained on Code

T0, T0+, T0++, BLOOMZ and mT0: Multi-task Prompted Finetuning

T0, T0+, T0++, BLOOMZ and mT0: Multi-task Prompted Finetuning

DALL-E: Zero Shot Text to Image Generation

DALL-E: Zero Shot Text to Image Generation

Amazon Research Days presentation on Designing a Query Auto-Completion System

Amazon Research Days presentation on Designing a Query Auto-Completion System

DDPM: Denoising Diffusion Probabilistic Models

DDPM: Denoising Diffusion Probabilistic Models

OpenAI InstructGPT: Training language models to follow instructions with human feedback

OpenAI InstructGPT: Training language models to follow instructions with human feedback

Chain of thought prompting to solve Big Bench Hard tasks

Chain of thought prompting to solve Big Bench Hard tasks

Deep Learning for Brain Encoding and Decoding

Deep Learning for Brain Encoding and Decoding

BIG bench Beyond the Imitation Game benchmark

BIG bench Beyond the Imitation Game benchmark

Handling Defective Suggestions and Prefixes in Query Auto Completion Systems

Handling Defective Suggestions and Prefixes in Query Auto Completion Systems

Personalization for Query Auto Completion Systems

Personalization for Query Auto Completion Systems

Natural Language Generation for Query Auto Completion Systems

Natural Language Generation for Query Auto Completion Systems

Ranking in Query Auto Completion Systems

Ranking in Query Auto Completion Systems

Designing a Query Auto Completion System

Designing a Query Auto Completion System