MichaelBarryUK (Michael Barry)

upvoted 2 papers 1 day ago

LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via Hybrid Architecture

Paper • 2409.02889 • Published 2 days ago • 40

Arctic-SnowCoder: Demystifying High-Quality Data in Code Pretraining

Paper • 2409.02326 • Published 3 days ago • 15

upvoted a paper 2 days ago

OLMoE: Open Mixture-of-Experts Language Models

Paper • 2409.02060 • Published 3 days ago • 57

upvoted 2 papers 3 days ago

Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming

Paper • 2408.16725 • Published 8 days ago • 39

VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters

Paper • 2408.17253 • Published 7 days ago • 34

upvoted a paper 7 days ago

WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling

Paper • 2408.16532 • Published 8 days ago • 42

upvoted 4 papers 8 days ago

Efficient LLM Scheduling by Learning to Rank

Paper • 2408.15792 • Published 9 days ago • 14

Distribution Backtracking Builds A Faster Convergence Trajectory for One-step Diffusion Distillation

Paper • 2408.15991 • Published 9 days ago • 15

Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders

Paper • 2408.15998 • Published 9 days ago • 76

BaichuanSEED: Sharing the Potential of ExtensivE Data Collection and Deduplication by Introducing a Competitive Large Language Model Baseline

Paper • 2408.15079 • Published 10 days ago • 51

upvoted a paper 9 days ago

The Mamba in the Llama: Distilling and Accelerating Hybrid Models

Paper • 2408.15237 • Published 10 days ago • 35

upvoted 4 papers 10 days ago

upvoted a paper 11 days ago

Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time

Paper • 2408.13233 • Published 14 days ago • 20

upvoted 2 papers 13 days ago

Sapiens: Foundation for Human Vision Models

Paper • 2408.12569 • Published 15 days ago • 81

Show-o: One Single Transformer to Unify Multimodal Understanding and Generation

Paper • 2408.12528 • Published 15 days ago • 49

upvoted 2 papers 15 days ago

Backward-Compatible Aligned Representations via an Orthogonal Transformation Layer

Paper • 2408.08793 • Published 21 days ago • 3

FocusLLM: Scaling LLM's Context by Parallel Decoding

Paper • 2408.11745 • Published 16 days ago • 23

upvoted 4 papers 18 days ago

Automated Design of Agentic Systems

Paper • 2408.08435 • Published 22 days ago • 37

TurboEdit: Instant text-based image editing

Paper • 2408.08332 • Published 23 days ago • 16

JPEG-LM: LLMs as Image Generators with Canonical Codec Representations

Paper • 2408.08459 • Published 22 days ago • 44

xGen-MM (BLIP-3): A Family of Open Large Multimodal Models

Paper • 2408.08872 • Published 21 days ago • 95

upvoted 3 papers 23 days ago

Amuro & Char: Analyzing the Relationship between Pre-Training and Fine-Tuning of Large Language Models

Paper • 2408.06663 • Published 24 days ago • 14

Layerwise Recurrent Router for Mixture-of-Experts

Paper • 2408.06793 • Published 24 days ago • 30

OpenResearcher: Unleashing AI for Accelerated Scientific Research

Paper • 2408.06941 • Published 24 days ago • 28

upvoted 3 papers 24 days ago

ControlNeXt: Powerful and Efficient Control for Image and Video Generation

Paper • 2408.06070 • Published 25 days ago • 52

Med42-v2: A Suite of Clinical LLMs

Paper • 2408.06142 • Published 25 days ago • 50

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery

Paper • 2408.06292 • Published 25 days ago • 111

upvoted 3 papers 25 days ago

UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling

Paper • 2408.04810 • Published 28 days ago • 22

Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2

Paper • 2408.05147 • Published 28 days ago • 36

VITA: Towards Open-Source Interactive Omni Multimodal LLM

Paper • 2408.05211 • Published 28 days ago • 46

upvoted 2 papers 28 days ago

Transformer Explainer: Interactive Learning of Text-Generative Models

Paper • 2408.04619 • Published 29 days ago • 149

Better Alignment with Instruction Back-and-Forth Translation

Paper • 2408.04614 • Published 29 days ago • 14

upvoted 13 papers about 1 month ago

ReSyncer: Rewiring Style-based Generator for Unified Audio-Visually Synced Facial Performer

Paper • 2408.03284 • Published about 1 month ago • 9

CoverBench: A Challenging Benchmark for Complex Claim Verification

Paper • 2408.03325 • Published about 1 month ago • 14

MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models

Paper • 2408.02718 • Published Aug 5 • 60

LLaVA-OneVision: Easy Visual Task Transfer

Paper • 2408.03326 • Published about 1 month ago • 56

Diffusion Models as Data Mining Tools

Paper • 2408.02752 • Published Jul 20 • 13

Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Paper • 2408.03314 • Published about 1 month ago • 28

An Object is Worth 64x64 Pixels: Generating 3D Object via Image Diffusion

Paper • 2408.03178 • Published about 1 month ago • 34

Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models

Paper • 2408.02085 • Published Aug 4 • 17

Language Model Can Listen While Speaking

Paper • 2408.02622 • Published Aug 5 • 33

Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Paper • 2408.02657 • Published Aug 5 • 32

MiniCPM-V: A GPT-4V Level MLLM on Your Phone

Paper • 2408.01800 • Published Aug 3 • 74

ReLiK: Retrieve and LinK, Fast and Accurate Entity Linking and Relation Extraction on an Academic Budget

Paper • 2408.00103 • Published Jul 31 • 15

POA: Pre-training Once for Models of All Sizes

Paper • 2408.01031 • Published Aug 2 • 26

upvoted an article about 1 month ago

Article

Memory-efficient Diffusion Transformers with Quanto and Diffusers

Jul 30

• 48

upvoted 11 papers about 1 month ago

MM-Vet v2: A Challenging Benchmark to Evaluate Large Multimodal Models for Integrated Capabilities

Paper • 2408.00765 • Published Aug 1 • 12

Data Contamination Report from the 2024 CONDA Shared Task

Paper • 2407.21530 • Published Jul 31 • 8

TAROT: Task-Oriented Authorship Obfuscation Using Policy Optimization Methods

Paper • 2407.21630 • Published Jul 31 • 8

MoMa: Efficient Early-Fusion Pre-training with Mixture of Modality-Aware Experts

Paper • 2407.21770 • Published Jul 31 • 19

Towards Achieving Human Parity on End-to-end Simultaneous Speech Translation via LLM Agent

Paper • 2407.21646 • Published Jul 31 • 18

JaColBERTv2.5: Optimising Multi-Vector Retrievers to Create State-of-the-Art Japanese Retrievers with Constrained Resources

Paper • 2407.20750 • Published Jul 30 • 21

ThinK: Thinner Key Cache by Query-Driven Pruning

Paper • 2407.21018 • Published Jul 30 • 30

Harvesting Textual and Structured Data from the HAL Publication Repository

Paper • 2407.20595 • Published Jul 30 • 21

Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge

Paper • 2407.19594 • Published Jul 28 • 19

MindSearch: Mimicking Human Minds Elicits Deep AI Searcher

Paper • 2407.20183 • Published Jul 29 • 37

SeaLLMs 3: Open Foundation and Chat Multilingual Large Language Models for Southeast Asian Languages

Paper • 2407.19672 • Published Jul 29 • 53

Michael Barry

AI & ML interests

Organizations

MichaelBarryUK's activity

Memory-efficient Diffusion Transformers with Quanto and Diffusers