Qian Liu's picture

Qian Liu

SivilTaram

·

http://siviltaram.github.io/

AI & ML interests

Cooking cool things

Articles

RegMix: Data Mixture as Regression for Language Model Pre-training

BigCodeBench: Benchmarking Large Language Models on Solving Practical and Challenging Programming Tasks

Efficient Table Pre-training without Real Data: An Introduction to TAPEX

Organizations

SivilTaram's activity

upvoted a paper 4 days ago

Diving into Self-Evolving Training for Multimodal Reasoning

Paper • 2412.17451 • Published 7 days ago • 37

upvoted a paper 11 days ago

Qwen2.5 Technical Report

Paper • 2412.15115 • Published 11 days ago • 331

upvoted a paper 21 days ago

MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale

Paper • 2412.05237 • Published 24 days ago • 46

upvoted 4 collections 27 days ago

Sailor2 Models

6 items • Updated 26 days ago • 4

Sailor2 Post-training Datasets

3 items • Updated 27 days ago • 5

Sailor2 Pre-training Datasets

8 items • Updated 26 days ago • 4

🔱 Sailor2 Language Models

Sailing in South-East Asia with Inclusive Multilingual LLMs • 9 items • Updated 27 days ago • 22

upvoted a paper 28 days ago

Yi-Lightning Technical Report

Paper • 2412.01253 • Published 28 days ago • 25

upvoted 2 papers about 1 month ago

When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training

Paper • 2411.13476 • Published Nov 20 • 15

Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?

Paper • 2407.10956 • Published Jul 15 • 6

upvoted a paper about 2 months ago

OmniEdit: Building Image Editing Generalist Models Through Specialist Supervision

Paper • 2411.07199 • Published Nov 11 • 46

upvoted 3 collections about 2 months ago

OpenCoder Model

OpenCoder Models • 9 items • Updated Nov 19 • 9

OpenCoder Datasets

OpenCoder datasets! • 6 items • Updated Nov 15 • 37

OpenCoder

OpenCoder is an open and reproducible code LLM family which matches the performance of top-tier code LLMs. • 8 items • Updated Nov 23 • 78

upvoted 2 papers about 2 months ago

OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models

Paper • 2411.04905 • Published Nov 7 • 111

How Far is Video Generation from World Model: A Physical Law Perspective

Paper • 2411.02385 • Published Nov 4 • 33

upvoted a collection 2 months ago

🫐 ProX Projects

Collection for: "Programming Every Example: Lifting Pre-training Data Quality like Experts at Scale" • 18 items • Updated 18 days ago • 2

upvoted a paper 3 months ago

Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates

Paper • 2410.07137 • Published Oct 9 • 7

upvoted a collection 3 months ago

ProX Dataset

a collection of pre-training corpora refined by ProX • 5 items • Updated Oct 18 • 5

upvoted a paper 3 months ago

Programming Every Example: Lifting Pre-training Data Quality like Experts at Scale

Paper • 2409.17115 • Published Sep 25 • 60