SivilTaram (Qian Liu)

upvoted a collection 9 days ago

PreSelect

Collection

2 items • Updated 23 days ago • 1

upvoted an article 13 days ago

Article

DualPipe could be better without the Dual

By

•

13 days ago

• 15

upvoted a paper 20 days ago

SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines

Paper • 2502.14739 • Published 20 days ago • 96

upvoted 2 papers 21 days ago

Craw4LLM: Efficient Web Crawling for LLM Pretraining

Paper • 2502.13347 • Published 22 days ago • 27

Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLMs

Paper • 2502.12982 • Published 23 days ago • 14

upvoted a collection 22 days ago

SimpleRL

Collection

The collection for the Project "Simple Reinforcement Learning for Reasoning" • 2 items • Updated 22 days ago • 5

upvoted 2 papers 29 days ago

Competitive Programming with Large Reasoning Models

Paper • 2502.06807 • Published Feb 3 • 67

CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction

Paper • 2502.07316 • Published 30 days ago • 47

upvoted 3 papers about 1 month ago

upvoted 2 collections about 1 month ago

Qwen2.5-1M

Collection

The long-context version of Qwen2.5, supporting 1M-token context lengths • 3 items • Updated 15 days ago • 106

Qwen2.5-VL

Collection

Vision-language model series based on Qwen2.5 • 8 items • Updated 17 days ago • 394

upvoted 2 papers about 2 months ago

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Paper • 2501.12948 • Published Jan 22 • 345

Learn-by-interact: A Data-Centric Framework for Self-Adaptive Agents in Realistic Environments

Paper • 2501.10893 • Published Jan 18 • 24

upvoted 4 papers 2 months ago

OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework

Paper • 2405.11143 • Published May 20, 2024 • 38

REINFORCE++: A Simple and Efficient Approach for Aligning Large Language Models

Paper • 2501.03262 • Published Jan 4 • 92

Long-context LLMs Struggle with Long In-context Learning

Paper • 2404.02060 • Published Apr 2, 2024 • 37

OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis

Paper • 2412.19723 • Published Dec 27, 2024 • 82

upvoted a paper 3 months ago

Diving into Self-Evolving Training for Multimodal Reasoning

Paper • 2412.17451 • Published Dec 23, 2024 • 43

Qian Liu

AI & ML interests

Organizations

SivilTaram's activity

PreSelect

DualPipe could be better without the Dual

SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines

Craw4LLM: Efficient Web Crawling for LLM Pretraining

Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLMs

SimpleRL

Competitive Programming with Large Reasoning Models

CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction

Demystifying Long Chain-of-Thought Reasoning in LLMs

SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model

s1: Simple test-time scaling

Qwen2.5-1M

Qwen2.5-VL

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Learn-by-interact: A Data-Centric Framework for Self-Adaptive Agents in Realistic Environments

OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework

REINFORCE++: A Simple and Efficient Approach for Aligning Large Language Models

Long-context LLMs Struggle with Long In-context Learning

OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis

Diving into Self-Evolving Training for Multimodal Reasoning