Papersby GlyphAlibaba (Qwen) research papers
A company publishing mostly on agents and evaluation, best known here for Qwen3 Technical Report.78 papers · 17,119 citations · latest Oct 2026
Co-Design Bench: Multimodal Collaborative Coding Evaluation for Agentic ModelsCo-Design Bench evaluates how effectively coding agents update software applications based on user requests with text, images, and other media.
Alibaba (Qwen)23 upvotesRead →Qwen-Image-PE: Learning Visual Design for Text-to-Image Prompt EnhancementQwen-Image-PE improves text-to-image prompts via two-stage training with caption-based reverse distillation and groupwise design rewards, scaling across data, model size, and information density.Alibaba (Qwen)23 upvotesRead →World-in-Context: Interactive Video World Modeling with In-Context ConditioningWorld-in-Context unifies view, action, and camera controls via explicit tokens and interaction-aware positional encoding to improve interactive video generation and navigation.Alibaba (Qwen)22 upvotesRead →Beyond Watching and Searching: Benchmarking Agents for Video-centered Deep Research ReportsThis benchmark evaluates how well AI agents can research and synthesize information from videos to produce interactive reports.Alibaba (Qwen)19 upvotesRead →UserArena: Benchmarking Interactive User Simulation for Long-Horizon Shopping AgentsUserArena introduces a real-world interactive benchmark with long-horizon shopping trajectories and an evaluation framework, alongside On-Policy Trajectory Distillation to improve simulator fidelity for agentic recommendations.Alibaba (Qwen)55 upvotesRead →SWIFT: Self-guided Weak-to-strong dIFfusion models via Target extrapolationThis training method uses a smaller, frozen model to guide the training of a larger diffusion model, improving quality without increasing inference costs.Alibaba (Qwen)30 upvotesRead →BlenderWorld: Benchmarking Visual Agents for 3D Creation from Real-World ReferencesThis benchmark evaluates how well AI models can perform complex 3D creation and editing tasks within the Blender software.Alibaba (Qwen)23 upvotesRead →CommerceGen-Studio: An End-to-End Framework for Commercial-Grade Main-Image GenerationThis paper presents an end-to-end framework for generating commercial-grade e-commerce product images by combining metadata extraction, layout planning, and multi-condition generation.Alibaba (Qwen)25 upvotesRead →Urbex: Agentic Spatial Grounding for City-Scale 3D ScenesThis paper presents an agentic framework that treats city-scale 3D scene grounding as an active search task rather than a simple candidate ranking problem.Alibaba (Qwen)134 upvotesRead →Last Secure Code Benchmark: Is the Code You Vibe Secure?This paper introduces a benchmark showing that current coding agents frequently produce functional but insecure code, highlighting significant security risks in automated coding.Alibaba (Qwen)77 upvotesRead →Learning Representations to Guide Pixel Diffusion TransformersThis paper introduces a guidance method for diffusion transformers that uses compact internal representations to improve image generation quality and efficiency.Alibaba (Qwen)34 upvotesRead →Scaling Agentic Data for Long-Horizon Terminal IntelligenceThis paper introduces a system to automatically generate high-quality training data for long-horizon terminal agents to improve their autonomous problem-solving capabilities.Alibaba (Qwen)1 citations147 upvotesRead →TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language ModelsTRACE improves reinforcement learning for large language models by aligning quantization during training and rollout to reduce performance loss in low-precision execution.Alibaba (Qwen)1 citations92 upvotesRead →VisionWeave: Weaving Elastic Visual Representations as a Native Capability of MLLMsThis paper introduces a method for multimodal models to adaptively allocate visual detail, reducing token usage while maintaining performance.Alibaba (Qwen)1 citations71 upvotesRead →Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief StatesPoS improves long-horizon agent performance by maintaining explicit belief states that track world status and unresolved task requirements.Alibaba (Qwen)1 citations91 upvotesRead →OmniReasoning: Pushing the Limits of Audio-Visual Joint ReasoningOmniReasoning improves audio-visual joint reasoning through a new benchmark, a data engine, and a self-distillation method for credit assignment.Alibaba (Qwen)27 upvotesRead →QwenGyre: An Elastic Reinforcement Learning Framework for Training xLong-Horizon AgentsQwenGyre is an online reinforcement learning framework that elastically manages GPU resources to train agents on extremely long-horizon tasks.Alibaba (Qwen)2 citations43 upvotesRead →HappyWorld-BenchHappyWorld-Bench evaluates the reliability and consistency of generated worlds as agents interact with them over time.Alibaba (Qwen)57 upvotesRead →One to More, More to One: Category-Aware Iterative Expert Training for Software Engineering AgentsThis framework improves software engineering agents by training category-specific experts and consolidating them into a single student model.Alibaba (Qwen)50 upvotesRead →OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual DialogueOmniVChat is a framework for native audio-visual dialogue that includes a data engine for synthesis and a reinforcement learning reward design.Alibaba (Qwen)1 citations149 upvotesRead →RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use AgentsRecreationWorld is a framework for training and evaluating hybrid computer-use agents that must discover and recreate software behavior.Alibaba (Qwen)2 citations78 upvotesRead →CORE: Improving Compositional Reasoning in MLLM Embedding via Reranker DistillationCORE distills compositional ranking judgments from a cross-attentive reranker into an embedding model via synthesized multi-level candidates and a Rank-KL objective, improving compositional retrieval without degrading standard performance.Alibaba (Qwen)26 upvotesRead →Terminal-Universe: Turning Agent Trajectories into Scalable Terminal EnvironmentsTerminal-Universe reconstructs executable workspaces from agent trajectories to synthesize diverse training tasks and improves post-training performance through supervised fine-tuning.Alibaba (Qwen)13 citations244 upvotesRead →On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training StabilityQwen3.8-Flash-Next: a 125B mixture-of-experts model with 6B active that nearly matches its 397B predecessor at 1/9 the training compute.Alibaba (Qwen)76 citations62 upvotesRead →Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous DrivingQwen-Drive-1.0 is a vision-language foundation model for autonomous driving that unifies 3D perception, visual question answering, and motion planning via shared representations and staged training.Alibaba (Qwen)18 citations313 upvotesRead →DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic ManipulationDreamX-Phi 1.0 is an action-conditioned video world model for robotic manipulation that uses geometric attention encoding, depth estimation, object masks with a frozen teacher, and distillation to generate faithful future observations.Alibaba (Qwen)8 citations61 upvotesRead →LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World TasksLongHorizon-Harness improves long-horizon agent performance by explicitly tracking verified task states outside context via a manage-execute-audit loop.Alibaba (Qwen)14 citations151 upvotesRead →UEmbed: Unified Sparse and Dense Multimodal EmbeddingsUEmbed is a decoder-only multimodal model that jointly produces dense and sparse embeddings in a single forward pass, extending sparse retrieval to unified text and multimodal inputs.Alibaba (Qwen)4 citations51 upvotesRead →MerchantBench: Benchmarking LLM Agents for Long-Term Coherence in E-Commerce OperationsMerchantBench evaluates long-term coherence of LLM agents in a year-long e-commerce simulation requiring persistent decision-making across sourcing, pricing, and cash-flow management with mixed feedback delays.Alibaba (Qwen)5 citations112 upvotesRead →Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI AgentsQwen-UI-Agent is a foundation GUI agent that integrates mobile, computer, web, and search environments with CLI execution, long-horizon online reinforcement learning, and autonomous data generation to achieve state-of-the-art real-world device performance.Alibaba (Qwen)18 citations156 upvotesRead →Qwen-Music Technical ReportQwen-Music is a music generation system that uses tokenized semantic representations, autoregressive language modeling with melody planning, and generative rendering to produce high-fidelity songs from text or reference audio.Alibaba (Qwen)4 citations32 upvotesRead →Qwen-Image-2.0-RL Technical ReportA reinforcement learning and on-policy distillation approach enhances the visual quality and instruction-following capabilities of a diffusion model for image generation and editing tasks.Alibaba (Qwen)10 citations54 upvotesRead →Qwen-Image-Agent: Bridging the Context Gap in Real-World Image GenerationA unified agentic framework called Qwen-Image-Agent is proposed to address the context gap in text-to-image generation by progressively constructing complete generation context through planning, reasoning, searching, and memory mechanisms.Alibaba (Qwen)18 citations55 upvotesRead →The Verification Horizon: No Silver Bullet for Coding Agent RewardsVerification challenges in AI agents arise from the difficulty of aligning proxy signals with human intent, requiring adaptive verification systems that evolve alongside generative capabilities.Alibaba (Qwen)11 citations53 upvotesRead →Qwen-AgentWorld: Language World Models for General AgentsLanguage-based world models enable agentic environment simulation across multiple domains and enhance general agent performance through scalable simulation and improved downstream task performance.Alibaba (Qwen)28 citations165 upvotesRead →Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer DecodingAutoregressive generation in large language models traditionally uses the final layer for token prediction, but a new decoding strategy dynamically selects more reliable intermediate layers based on entropy-guided search, improving reasoning performance with minimal computational overhead.Alibaba (Qwen)3 citations27 upvotesRead →Qwen-RobotNav Technical Report: A Scalable Navigation Model Designed for an Agentic Navigation SystemQwen-RobotNav is a scalable navigation model with a parameterized interface enabling dynamic task modes and observation parameters, achieving state-of-the-art performance through multi-task training and zero-shot generalization to real-world robotics.Alibaba (Qwen)23 citations29 upvotesRead →Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation ModelsA Vision-Language-Action foundation model for robotic manipulation achieves generalization through unified alignment across representation, motion, and behavior dimensions, enabling large-scale training on diverse data sources.Alibaba (Qwen)72 citations34 upvotesRead →Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video GenerationQwen-RobotWorld is a language-conditioned video world model that predicts future visual trajectories across multiple robotic domains using a double-stream diffusion transformer and embodied world knowledge corpus.Alibaba (Qwen)16 citations47 upvotesRead →Qwen-Image-Flash: Beyond Objective DesignFew-step distillation for visual generative models benefits from systematic investigation of training recipes beyond just distillation objectives, leading to improved student performance through optimized data composition, teacher guidance, and task mixture.Alibaba (Qwen)38 upvotesRead →Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot EmbodimentsA unified vision-language-action model is presented that integrates diverse embodied decision-making tasks through a shared architecture and training approach, demonstrating strong performance across manipulation, navigation, and trajectory prediction with generalization across different robot platforms and environments.Alibaba (Qwen)65 citations145 upvotesRead →CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use AgentsRLVR framework for computer-use agents addresses data scarcity through scalable generation pipeline and synthetic environments, achieving superior performance on verification and transfer benchmarks.Alibaba (Qwen)30 citations33 upvotesRead →Qwen-Image-VAE-2.0 Technical ReportQwen-Image-VAE-2.0 is a high-compression Variational Autoencoder suite that improves reconstruction fidelity and diffusability through enhanced architecture, large-scale training, and semantic alignment strategies.Alibaba (Qwen)2 citations61 upvotesRead →ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use AgentsToolCUA is an end-to-end agent that learns optimal GUI-tool path selection through staged training, achieving superior performance in hybrid action space environments.Alibaba (Qwen)12 citations26 upvotesRead →Qwen-Image-2.0 Technical ReportQwen-Image-2.0 is an advanced image generation model that combines high-fidelity synthesis with precise editing capabilities through a unified framework using Qwen3-VL as condition encoder and Multimodal Diffusion Transformer for joint modeling.Alibaba (Qwen)40 citations118 upvotesRead →OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language World ModelsOccuBench presents a comprehensive benchmark for evaluating AI agents across 100 professional domains using Language World Models to simulate real-world environments with controlled fault injection.Alibaba (Qwen)5 citations67 upvotesRead →RealChart2Code: Advancing Chart-to-Code Generation with Real Data and Multi-Task EvaluationVision-Language Models face significant challenges in generating complex multi-panel charts from real-world data, as demonstrated by a new large-scale benchmark that reveals performance gaps between proprietary and open-weight models.Alibaba (Qwen)5 citations27 upvotesRead →On the Direction of RLVR Updates for LLM Reasoning: Identification and ExploitationReinforcement learning with verifiable rewards improves language model reasoning by focusing on the direction of parameter updates rather than their magnitude, enabling better test-time extrapolation and training-time reweighting methods.Alibaba (Qwen)16 citations29 upvotesRead →FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy OptimizationFIPO enhances reinforcement learning for language models by using discounted future-KL divergence to improve credit assignment and extend reasoning chains, achieving better mathematical problem-solving performance.Alibaba (Qwen)31 citations104 upvotesRead →HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language ReasoningHopChain is a scalable framework that generates multi-hop vision-language reasoning data to enhance VLMs' long-chain reasoning capabilities across diverse benchmarks.Alibaba (Qwen)7 citations65 upvotesRead →
About and links
Topics: Agents and evaluation 21, Foundation models 16, Multimodal and robotics 14, Reasoning 10, Inference and efficiency 9, Alignment and safety 2, Architectures 2, Training and scaling 2, Applied AI 1, Retrieval and data 1
Alibaba (Qwen) lab profile on Labs (labs.fru.dev): leaders, models, landmarksAlibaba (Qwen) on Companies (companies.fru.dev)Also onQuarterly