Qwen
PulseAugur coverage of Qwen — every cluster mentioning Qwen across labs, papers, and developer communities, ranked by signal.
- developed by Alibaba Group 95%
- instance of Qwen 3.6 95%
- developed Alibaba Cloud 90%
- developed by Qwen 2.5 90%
- developed by Qwen3.6-Plus 90%
- instance of generative pre-trained transformer 90%
- employed by Lin Chun-yang 90%
- founded Lin Chun-yang 90%
- employed by HongShan 90%
- instance of Qwen3.7 Max 90%
- instance of Qwen 3.7 90%
- founded HongShan 90%
- 2026-05-23 product_launch Alibaba Cloud releases Qwen 3.6 and Qwen 2.5 models with enhanced features. 来源
- 2026-05-21 product_launch Alibaba integrated its Qwen AI model with the Taobao e-commerce platform to enable AI-powered shopping.
- 2026-05-19 product_launch Alibaba's Qwen team released preview versions of its Qwen 3.7 Max and Qwen 3.7 Plus models. 来源
- 2026-05-19 product_launch Qwen released version 3.7 of its language model, featuring a tunable censorship circuit. 来源
- 2026-05-18 product_launch Alibaba's Qwen team released previews of their Qwen3.7-Max and Qwen3.7-Plus models. 来源
- 2026-05-16 research_milestone Qwen team developed a new Variational Autoencoder model. 来源
- 2026-05-11 research_milestone Researchers achieved high accuracy in a Ukrainian document understanding task using a retrieval-augmented system powered by Qwen models. 来源
- 2026-05-11 product_launch Alibaba integrated its Qwen AI model with Taobao to create an end-to-end AI shopping experience.
- 2026-05-10 product_launch Alibaba fully integrated its Qwen AI assistant with Taobao and Tmall, enabling conversational shopping.
- 2026-05-10 product_launch Alibaba launched an AI shopping assistant by integrating its Qwen AI with Taobao and Tmall.
- 2026-04-30 research_milestone Qwen released Qwen-Scope, an interpretability toolkit for LLMs.
- 2026-04-15 product_launch Alibaba's Qwen team released new multimodal models Qwen3.6-27B and Qwen3.6-35B-A3B.
22 天有情绪数据
-
Developer shares checklist for vetting LLM gateways
A developer shared a concise checklist for evaluating new LLM gateways, emphasizing auditable first calls over pricing alone. The process involves verifying API keys, checking logs for model usage and costs, and testing…
-
New benchmark IdioLink tests language models on idiom comprehension
Researchers have introduced IdioLink, a new benchmark designed to evaluate language models' ability to understand idiomatic expressions. The benchmark consists of over 10,000 documents and 2,000 queries, covering 107 id…
-
Airbnb CEO defends Chinese AI use amid US Congress probe
Airbnb CEO Brian Chesky is facing scrutiny from U.S. lawmakers regarding the company's use of Chinese AI models, specifically Alibaba's Qwen. Chesky defended the practice, stating that Airbnb primarily uses open-source …
-
Alibaba targets 30B yuan AI revenue by 2026 with commercialization push
Alibaba is transitioning its AI efforts from initial investment to full-scale commercialization, aiming to become China's leading full-stack AI provider. The company projects 30 billion yuan in AI revenue by 2026, with …
-
模型外监督微调通过强制不熟悉的推理风格降低AI能力
研究人员发现，使用不同AI模型的输出来进行监督微调（SFT）会显著降低所训练模型的能力。这种能力下降似乎与模型采纳了它难以有效利用的不熟悉推理风格有关。问题不一定是因为模仿了一个能力较差的教师模型，因为即使教师模型更优越，也会发生能力下降。幸运的是，这种性能下降似乎是一个浅层属性，因为只需少量训练即可恢复原始推理风格，从而挽回大部分损失的性能。
-
AI 云平台 Modal 获 3.55 亿美元融资，估值 46.5 亿美元
Modal 已成功完成 3.55 亿美元的 C 轮融资，公司投后估值为 46.5 亿美元。公司经历了显著增长，年化收入已超过 3 亿美元，自 9 月以来规模扩大了五倍。本轮融资将支持 Modal 的使命，即提供专为 AI 工作负载设计的云基础设施，为各种应用程序提供弹性计算、安全隔离和程序化控制。
-
LLM提供商调整定价，增删模型
多家LLM提供商调整了定价和模型可用性。Qwen出现混合变化，部分变体价格上涨，部分价格下跌，并推出了Qwen3.7 Max等新模型。Google的Gemini Flash Latest价格大幅上涨，而Z.ai的GLM 5.1则免费。此外，阿里巴巴的Tongyi DeepResearch 30B A3B模型已从目录中移除，促使用户寻找替代方案。
-
Alibaba Qwen3.5 model offers real-time translation with voice cloning
Alibaba's Qwen team has released Qwen3.5-LiveTranslate-Flash, a real-time multimodal translation model that significantly reduces latency to 2.8 seconds. This new model expands language support to 60 input languages and…
-
小型LLM使用位置复制捷径进行算术，绕过CoT逻辑
一篇新的研究论文揭示了小型语言模型在使用链式思考（CoT）提示执行算术任务时存在一个重要的捷径。这些模型倾向于复制答案分隔符之前的位置数字，而不是依赖逻辑排序，即使中间的推理步骤不正确或被打乱，这种位置复制也能解释其准确性的很大一部分，这突显了评估CoT忠实度时潜在的故障模式。
-
Google AI Edge Gallery enables on-device agents with MCP support
Google has updated its AI Edge Gallery app to support the Model Context Protocol (MCP) on Android devices, enabling on-device AI agents. This update allows LLMs like Gemma 4 to run entirely locally, enhancing privacy an…
-
开发者优化本地Qwen大语言模型，使其速度媲美Claude 3.5 Sonnet
一位开发者详细介绍了他们为生产环境优化本地大语言模型（LLM）的经验，目标是复制像Claude 3.5 Sonnet这样的云端模型的性能。他们发现，某些Qwen模型虽然功能强大，但表现出一种无益的“大声思考”行为，这阻碍了他们生成干净JSON的特定用例。在尝试了不同版本的Qwen和提示工程技术后，他们选择了Qwen2.5-32B-Instruct-fp8，该模型在处理常规任务时，响应速度明显快于Claude 3.5 Sonnet。
-
AI safety research explores emotional nudges for aligned behavior
A researcher explored AI safety by investigating the potential for emotional nudges to influence model behavior, drawing parallels to human psychology. The study suggests that models, like humans, exhibit internal state…
-
Alibaba Qwen 3.7 previews top Chinese models in text and vision benchmarks
Alibaba's Qwen team has released preview versions of its Qwen 3.7 Max and Qwen 3.7 Plus models, showcasing rapid iteration cycles. The Qwen 3.7 Max model has achieved top rankings among Chinese models in text-based benc…
-
Qwen 3.7 released; Arrow 1.1 converts sketches to SVG; Renoise Canvas targets asset management
Qwen 3.7 has been released, marking an update to the Qwen model series, though specific performance details are not yet available. Separately, QuiverAI's Arrow 1.1 can convert fashion sketches into editable SVGs, focusi…
-
Qwen 3.7 支持可调式审查，NVIDIA 微调机器人视频生成
Qwen 发布了其语言模型 3.7 版本，该版本包含一个可修改的政治审查专用电路，且修改后不损失事实知识。NVIDIA 的 Cosmos Predict 2.5 模型现在可以使用高效的 LoRA/DoRA 方法进行机器人视频生成的微调。此外，新的 HRM-Text 模型为预训练基础模型提供了更易于访问且成本效益更高的方法。
-
Alibaba's Qwen previews new 3.7 series models on Arena
Alibaba's Qwen team has released previews of their Qwen3.7-Max and Qwen3.7-Plus models. These new models are now available on the Arena platform for evaluation. The release positions Alibaba as a top-tier lab in both te…
-
Local LLM inference boosted by Qwen optimizations and new UI
Recent developments in local LLM inference focus on optimizing performance and VRAM usage for models like Qwen 3.6 and 3.5. One approach involves detailed backend comparisons for Qwen 3.6 27B on consumer GPUs, identifyi…
-
SpatioRoute boosts VLM spatial reasoning with dynamic prompt routing
Researchers have developed SpatioRoute, a novel method for enhancing zero-shot spatial reasoning in Vision-Language Models (VLMs). This approach dynamically routes incoming questions to tailored prompt templates without…
-
New AI API offers OpenAI compatibility with diverse models
A new AI API service is offering OpenAI-compatible access to several models, including DeepSeek-Chat, GLM-4, and Qwen variants, at a price point 2.5 times the official OpenAI rate. The service emphasizes stability and g…
-
Qwen teases new partner for Alibaba Cloud Summit; Tencent launches Ardot
Qwen, a large language model, is teasing the arrival of a significant new partner at the upcoming Alibaba Cloud Summit on May 20th. The announcement hints at enhanced capabilities, describing the new addition as more ve…