9 21 16

Huiqiang Jiang PRO

iofu728

https://www.microsoft.com/en-us/research/people/hjiang/

AI & ML interests

None yet

Recent Activity

liked a model 30 days ago

moonshotai/Moonlight-16B-A3B

upvoted a paper about 2 months ago

Optimizing Large Language Model Training Using FP4 Quantization

liked a model about 2 months ago

Qwen/Qwen2.5-14B-Instruct-1M

View all activity

Organizations

iofu728's activity

upvoted 2 papers about 2 months ago

Optimizing Large Language Model Training Using FP4 Quantization

Paper • 2501.17116 • Published Jan 28 • 36

Sigma: Differential Rescaling of Query, Key and Value for Efficient Language Models

Paper • 2501.13629 • Published Jan 23 • 46

upvoted a paper 2 months ago

rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking

Paper • 2501.04519 • Published Jan 8 • 265

upvoted 3 papers 3 months ago

upvoted a paper 6 months ago

Differential Transformer

Paper • 2410.05258 • Published Oct 7, 2024 • 173

upvoted an article 6 months ago

Article

Fine-tuning LLMs to 1.58bit: extreme quantization made easy

Sep 18, 2024

• 227

upvoted a paper 6 months ago

RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval

Paper • 2409.10516 • Published Sep 16, 2024 • 42

upvoted a paper 7 months ago

MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding

Paper • 2408.11049 • Published Aug 20, 2024 • 13

upvoted an article 7 months ago

Article

A failed experiment: Infini-Attention, and why we should keep trying?

Aug 14, 2024

• 60

upvoted a paper 9 months ago

MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention

Paper • 2407.02490 • Published Jul 2, 2024 • 25

upvoted 3 papers about 1 year ago

LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Paper • 2403.12968 • Published Mar 19, 2024 • 25

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

Paper • 2402.17764 • Published Feb 27, 2024 • 611

Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning

Paper • 2402.06619 • Published Feb 9, 2024 • 55

upvoted 3 papers over 1 year ago

Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time

Paper • 2310.17157 • Published Oct 26, 2023 • 14

LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models

Paper • 2310.05736 • Published Oct 9, 2023 • 4

LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression

Paper • 2310.06839 • Published Oct 10, 2023 • 3