Tracked topic
Qwen3 is an AI model family developed by Alibaba, released as a set of large language models for natural-language tasks.
… A 0.6B Qwen3 interpreter executing PAW programs matches the performance of direct prompting of Qwen3-32B, while using roughly one fiftieth of the inference memory and running at 30 tokens/s on a MacBook M3. …
… Our findings suggest that carefully selected quantized SLMs, especially from the Qwen family, can be competitive RAG generators while enabling local, private, and GPU-free deployment. …
… Generated by Qwen/Qwen2.5-Coder-32B-Instruct Reinforcement learning RL post-training improves large language models LLMs on individual domains such as mathematical reasoning, code generation, question answering, and creative writing CW , but training on one domain often degrades performance on othe… …
Papers arxiv:2605.30265 LoMo: Local Modality Substitution for Deeper Vision-Language Fusion Published on May 28 Submitted by Zhixiong Zhang SII on May 29 Fudan University Authors: , Zhixiong Zhang , , Yibin Wang , Abstract Vision-language models suffer from modality sensitivity due to training data… …
… Generated by Qwen/Qwen2.5-Coder-32B-Instruct Modern image generation demands a single model that unifies diverse capabilities, including text-to-image T2I , local editing , and global editing . …
… Built on top of Qwen3-VL-Instruct-2B/4B/8B, P2R consistently improves performance across model scales. …
… Generated by Qwen/Qwen2.5-Coder-32B-Instruct Existing benchmarks for MLLM-generated web artifacts assess interaction through local evidence and miss the requirement-induced states and transitions that determine whether a page works. …
… Experiments on IA-Bench, Mindbench and WISE-Verified show that Qwen-Image-Agent outperforms strong baselines and achieves state-of-the-art performance. …
… Generated by Qwen/Qwen2.5-Coder-32B-Instruct Cross-view geo-localization estimates the geographic location of a ground image by matching it against an aerial image database. …
… A 7B agent beats the 10× larger Qwen2.5-VL-72B on LVBench 50.5 vs. 47.3 with ~73% fewer frames. Qwen3.7-Max is already live as a closed API — any plans for open-weight releases of the 3.7 family? like 3.6-35B-A3B / 3.6-27B alongside 3.6-Max Would love to run it locally via llama.cpp / GGUF. …