tokestermw (Motoki Wu)

upvoted a collection 18 days ago

MobileLLM

Optimizing Sub-billion Parameter Language Models for On-Device Use Cases (ICML 2024) https://arxiv.org/abs/2402.14905 • 8 items • Updated 12 days ago • 95

upvoted a collection 25 days ago

C4AI Aya Expanse

Collection

Aya Expanse is an open-weight research release of a model with highly advanced multilingual capabilities. • 3 items • Updated 26 days ago • 26

upvoted a paper 25 days ago

Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs

Paper • 2404.05719 • Published Apr 8 • 80

upvoted an article about 1 month ago

Article

Our Transformers Code Agent beats the GAIA benchmark!

Jul 1

• 46

upvoted a paper about 2 months ago

Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation

Paper • 2409.12941 • Published Sep 19 • 22

upvoted a collection about 2 months ago

Moshi v0.1 Release

Collection

MLX, Candle & PyTorch model checkpoints released as part of the Moshi release from Kyutai. Run inference via: https://github.com/kyutai-labs/moshi • 13 items • Updated Sep 18 • 218

upvoted an article about 2 months ago

Article

Document Similarity Search with ColPali

By

•

Sep 21

• 47

upvoted a paper about 2 months ago

Training Language Models to Self-Correct via Reinforcement Learning

Paper • 2409.12917 • Published Sep 19 • 134

upvoted 5 papers 2 months ago

OneGen: Efficient One-Pass Unified Generation and Retrieval for LLMs

Paper • 2409.05152 • Published Sep 8 • 30

How Do Your Code LLMs Perform? Empowering Code Instruction Tuning with High-Quality Data

Paper • 2409.03810 • Published Sep 5 • 30

Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning

Paper • 2402.10110 • Published Feb 15 • 3

Hermes 3 Technical Report

Paper • 2408.11857 • Published Aug 15 • 38

LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA

Paper • 2409.02897 • Published Sep 4 • 44

upvoted 2 papers 3 months ago

Writing in the Margins: Better Inference Pattern for Long Context Retrieval

Paper • 2408.14906 • Published Aug 27 • 138

Leveraging Open Knowledge for Advancing Task Expertise in Large Language Models

Paper • 2408.15915 • Published Aug 28 • 19

upvoted 2 articles 3 months ago

Article

Improving Hugging Face Training Efficiency Through Packing with Flash Attention

Aug 21

• 22

Article

Perspectives for first principles prompt engineering

By

•

Aug 18

• 16

upvoted a paper 3 months ago

BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts

Paper • 2408.08274 • Published Aug 15 • 12

upvoted an article 3 months ago

Article

Tool Use, Unified

Aug 12

• 63

upvoted a paper 3 months ago

ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Paper • 2408.04682 • Published Aug 8 • 14

Motoki Wu

AI & ML interests

Organizations

tokestermw's activity

MobileLLM

C4AI Aya Expanse

Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs

Our Transformers Code Agent beats the GAIA benchmark!

Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation

Moshi v0.1 Release

Document Similarity Search with ColPali

Training Language Models to Self-Correct via Reinforcement Learning

OneGen: Efficient One-Pass Unified Generation and Retrieval for LLMs

How Do Your Code LLMs Perform? Empowering Code Instruction Tuning with High-Quality Data

Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning

Hermes 3 Technical Report

LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA

Writing in the Margins: Better Inference Pattern for Long Context Retrieval

Leveraging Open Knowledge for Advancing Task Expertise in Large Language Models

Improving Hugging Face Training Efficiency Through Packing with Flash Attention

Perspectives for first principles prompt engineering

BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts

Tool Use, Unified

ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities