Junyang Lin
Lead engineer on Alibaba's Qwen LLM family; first/corresponding author on most Qwen technical reports.
- Role
- researcher
- Currently at
- Alibaba Qwen (Tongyi Qianwen)
- twitter.com/JustinLin610
- GitHub
- github.com/JustinLin610
- Scholar
- scholar.google.com/citations
- Papers
- 57
Cite
Notes
Only stored in your browser.
Authored papers
57Qwen3-TTS Technical Report
arXiv 2026
CodePercept: Code-Grounded Visual STEM Perception for MLLMs
arXiv 2026
From Narrow to Panoramic Vision: Attention-Guided Cold-Start Reshapes Multimodal Reasoning
arXiv 2026
Overcoming Joint Intractability with Lossless Hierarchical Speculative Decoding
arXiv 2026
HLE-Verified: A Systematic Verification and Structured Revision of Humanity's Last Exam
arXiv 2026
Qwen3-ASR Technical Report
arXiv 2026
DeepPlanning: Benchmarking Long-Horizon Agentic Planning with Verifiable Constraints
arXiv 2026
Qwen3-Coder-Next Technical Report
arXiv 2026
Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking
arXiv 2026
CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents
arXiv 2026
Outcome Accuracy is Not Enough: Aligning the Reasoning Process of Reward Models
arXiv 2026
Qwen-Image Technical Report
arXiv 2025
Qwen3-Omni Technical Report
arXiv 2025
Qwen2.5-VL Technical Report
arXiv 2025
Qwen3 Technical Report
preprint
Qwen3-VL Technical Report
arXiv 2025
PolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts
arXiv 2025
WorldPM: Scaling Human Preference Modeling
arXiv 2025
Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition
arXiv 2025
Soft Adaptive Policy Optimization
arXiv 2025
Qwen3Guard Technical Report
arXiv 2025
CoRT: Code-integrated Reasoning within Thinking
arXiv 2025
A^2Search: Ambiguity-Aware Question Answering with Reinforcement Learning
arXiv 2025
SWE-Flow: Synthesizing Software Engineering Data in a Test-Driven Manner
arXiv 2025
Qwen2.5-Omni Technical Report
arXiv 2025
Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
arXiv 2025
Parallel Scaling Law for Language Models
arXiv 2025
Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control Is Easier Than You Think
arXiv 2025
WavReward: Spoken Dialogue Models With Generalist Reward Evaluators
arXiv 2025
RealCritic: Towards Effectiveness-Driven Evaluation of Language Model Critiques
arXiv 2025
START: Self-taught Reasoner with Tools
arXiv 2025
Rationales Are Not Silver Bullets: Measuring the Impact of Rationales on Model Performance and Reliability
arXiv 2025
MARGE: Improving Math Reasoning for LLMs with Guided Exploration
arXiv 2025
OpenHands: An Open Platform for AI Software Developers as Generalist Agents
arXiv 2024
Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
arXiv 2024
ProcessBench: Identifying Process Errors in Mathematical Reasoning
arXiv 2024
Rethinking Data Selection at Scale: Random Selection is Almost All You Need
arXiv 2024
Aligning Large Language Models via Self-Steering Optimization
arXiv 2024
Confidence v.s. Critique: A Decomposition of Self-Correction Capability for LLMs
arXiv 2024
Qwen2.5 Technical Report
arXiv 2024
Qwen2 Technical Report
arXiv 2024
Evaluating and Aligning CodeLLMs on Human Preference
arXiv 2024
Qwen2-Audio Technical Report
arXiv 2024
An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models
arXiv 2024
Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey
arXiv 2024
Language Models can Self-Lengthen to Generate Long Texts
arXiv 2024
A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image Generation
arXiv 2024
ExpertPrompting: Instructing Large Language Models to be Distinguished Experts
arXiv 2023
Qwen Technical Report
arXiv 2023
Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
arXiv 2023
Self-Evolved Diverse Data Sampling for Efficient Instruction Tuning
arXiv 2023
TouchStone: Evaluating Vision-Language Models by Language Models
arXiv 2023
#InsTag: Instruction Tagging for Analyzing Supervised Fine-tuning of Large Language Models
arXiv 2023
ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities
arXiv 2023
Transferring General Multimodal Pretrained Models to Text Recognition
arXiv 2022
Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese
arXiv 2022
CogView: Mastering Text-to-Image Generation via Transformers
NeurIPS 2021 12
Affiliations
Previously
Frequent co-authors
10from 57 papers