Qwen

company

https://qwen.ai/

AI & ML interests

None defined yet.

Recent Activity

chujiezheng authored a paper about 10 hours ago

Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding

SaylorTwift new activity about 12 hours ago

Qwen/Qwen3.6-27B:Update Terminal Bench 2.0 evaluation notes with methodology details

XUANMINGZHANG submitted a paper about 17 hours ago

Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding

View all activity

Papers

Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding

Native Active Perception as Reasoning for Omni-Modal Understanding

View all Papers

Qwen 's papers 41

Submitted by

XUANMING ZHANG

Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding

Qwen

Submitted by

Zhenghao Xing

Native Active Perception as Reasoning for Omni-Modal Understanding

Qwen

Submitted by

taesiri

Unified Multimodal Autoregressive Modeling with Shared Context-Visual Tokenizer is Key to Unification

Qwen

Submitted by

taesiri

Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation

Qwen

Submitted by

xianghao

Verifiable Environments Are LEGO Bricks: Recursive Composition for Reasoning Generalization

Qwen

Submitted by

taesiri

Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling

Qwen

4

Submitted by

Tianhe Wu

Qwen-Image-Flash: Beyond Objective Design

Qwen

6

Submitted by

taesiri

Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments

Qwen

Submitted by

Bowen Wang

CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents

Qwen

Submitted by

Jiang Lihan

Qwen-Image-VAE-2.0 Technical Report

Qwen

Submitted by

Jiang Lihan

Qwen-Image-2.0 Technical Report

Qwen

Submitted by

huxiaomeng

OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language World Models

Qwen

Submitted by

zjj

RealChart2Code: Advancing Chart-to-Code Generation with Real Data and Multi-Task Evaluation

Qwen

Submitted by

taesiri

Sparse but Critical: A Token-Level Analysis of Distributional Shifts in RLVR Fine-Tuning of LLMs

Qwen

Submitted by

taesiri

On the Direction of RLVR Updates for LLM Reasoning: Identification and Exploitation

Qwen

Submitted by

Kexin Huang

FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization

Qwen

Submitted by

Shenzhi Wang

HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning

Qwen

5

Submitted by

TongkunGuan

CodePercept: Code-Grounded Visual STEM Perception for MLLMs

Qwen

Submitted by

Ruilin

From Narrow to Panoramic Vision: Attention-Guided Cold-Start Reshapes Multimodal Reasoning

Qwen

Submitted by

KaShun SHUM

Qwen3-Coder-Next Technical Report

Qwen

Submitted by

taesiri

WebWorld: A Large-Scale World Model for Web Agent Training

Qwen

Submitted by

Xuan Ouyang

OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration

Qwen

3

Submitted by

wang binghai

Outcome Accuracy is Not Enough: Aligning the Reasoning Process of Reward Models

Qwen

Submitted by

Liangyu Wang

Canzona: A Unified, Asynchronous, and Load-Balanced Framework for Distributed Matrix-based Optimizers

Qwen

3

Submitted by

Mouxiang Chen

SWE-Universe: Scale Real-World Verifiable Environments to Millions

Qwen

3

Submitted by

taesiri

Qwen3-ASR Technical Report

Qwen

Submitted by

Adina Yakefu

DeepPlanning: Benchmarking Long-Horizon Agentic Planning with Verifiable Constraints

Qwen

Submitted by

taesiri

Qwen3-TTS Technical Report

Qwen

From Completion to Editing: Unlocking Context-Aware Code Infilling via Search-and-Replace Instruction Tuning

Qwen

MegaFlow: Large-Scale Distributed Orchestration System for the Agentic Era

Qwen

Submitted by

Dingkun Long

Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking

Qwen

Submitted by

Bowen Yu

Stabilizing Reinforcement Learning with LLMs: Formulation and Practices

Qwen

Submitted by

shuai bai

Qwen3-VL Technical Report

Qwen

Submitted by

shuai bai

Soft Adaptive Policy Optimization

Qwen

Submitted by

XuejingLiu

Revisiting Multimodal Positional Encoding in Vision-Language Models

Qwen

Submitted by

taesiri

Qwen3Guard Technical Report

Qwen

PlotCraft: Pushing the Limits of LLMs for Complex and Interactive Data Visualization

Qwen

Submitted by

Ningyu Zhang

Scaling Generalist Data-Analytic Agents

Qwen

2

Submitted by

taesiri

Qwen3-Omni Technical Report

Qwen

Submitted by

Chujie Zheng

Group Sequence Policy Optimization

Qwen

Submitted by

Chujie Zheng

Qwen3 Technical Report

Qwen