模型与评测

开源 Skills 的商业闭环

📌 一句话摘要 作者以提问形式切入，探讨开源项目（特别是 Skills）背后的盈利逻辑与商业闭环。 📝 详细摘要 这是一条简短的提问式推文，核心意图是引导读者讨论或思考「开源 Skills」这一特定技术/产品形态是如何实现商业变现的。结合上下文（如前文提到的 GitHub star 与科普内容价值），该问题指向独立开发者如何利用开源工具构建可持续的商业模式。 📊 文章信息 AI 初评： 65 来源： dontbesilent(@dontbesilent12) 作者： dontbesilent 分类： 商业科技 语言： 中文 阅读时间： 1 分钟 字数：

星际中继站的医疗诊所

RAPID：从示范编程机器人

arXiv:2609.30249v1 Announce Type: cross Abstract: Coding agents have demonstrated enormous success in solving complex programming problems. To leverage their potential for robot systems, this work introduces Robot Agentic Programming from Demonstrations (RAPID), which automatical

DeepSeek 弹性计算

I'm the mom in that viral Giants clip. Let me tell you about my husband

Excel now supports multiple values in a single cell

Related: https://techcommunity.microsoft.com/blog/excelblog/excel-now...

GitHub Copilot weekly releases — September 21

This week’s releases add new models to Copilot, local sandboxing in the Copilot app, and updates to Copilot in Slack, Microsoft Teams, JetBrains, and VS Code. GitHub Copilot Claude Opus 5.5 is available to Copilot Pro+, Max, Business, and Enterprise plans. GPT-6 Sol is available

A Multimodal Dataset for Survival Prediction in Resected Pancreatic Ductal Adenocarcinoma

arXiv:2609.29726v1 Announce Type: new Abstract: Survival research in pancreatic ductal adenocarcinoma (PDAC) is limited by the scarcity of datasets linking whole-slide histology with clinical, molecular, and long-term outcome data. We present a retrospective single-centre cohort

AdaPilot: Towards Scene-Adaptive Policy Learning for Cross-Generator Text-to-Image Quality Optimization

arXiv:2609.29517v1 Announce Type: new Abstract: Existing methods for improving text-to-image generation quality have progressed from generator fine-tuning and prompt optimization to reinforcement learning with multi-turn visual feedback. However, existing strategies are deeply co

AgenticCADedit: A Stateful, Tool-Mediated Agentic Approach to Multimodal 3D CAD Editing

arXiv:2609.29621v1 Announce Type: new Abstract: Computer-aided design is central to industrial manufacturing, and much of a designer's daily work consists of editing existing models from multimodal requests involving speech, sketches, and model interaction. Existing neural CAD ap

Clinical Knowledge Graphs for Chest X-Ray Device Reasoning

arXiv:2609.29536v1 Announce Type: cross Abstract: Chest radiographs are routinely used to verify the position of catheters, tubes, and other support devices. Existing image models often return labels or segmentations, while report-processing systems structure text without access

Detecting Glaucoma Across Multi-ethnic Myopic and Non-Myopic Populations Using an Uncertainty-Aware Vision Transformer: A Multicentre Model Development and Validation Study

arXiv:2609.29433v1 Announce Type: new Abstract: Background: Artificial intelligence (AI)-based glaucoma detection from colour fundus photographs (CFP) offers scalable screening, but performance may decline on external datasets because of differences in ground-truth definitions, p

Domain Recentering and Confidence-Weighted Prior Calibration for Vision-Language Models

arXiv:2609.29358v1 Announce Type: new Abstract: Vision-language models such as CLIP achieve strong zero-shot classification, yet under distribution shift, visual embeddings drift from fixed text embeddings. Training-free calibration avoids the per-sample optimization of prompt le

DrGait: Biomechanically Grounded Visual Reasoning for Interpretable Clinical Gait Analysis

arXiv:2609.28796v1 Announce Type: new Abstract: Current automated gait analysis for clinical applications relies on uninterpretable black-box classifiers. Although Vision-Language Models (VLMs) offer strong reasoning capabilities, applying them directly to gait videos often leads

Evolve Vision-Language-Action Model into an Agent with On-the-fly Tool-use

arXiv:2608.14047v3 Announce Type: replace-cross Abstract: This paper integrates end-to-end Visual-Language-Action (VLA) models with agentic tool-use to propose Agentic Robot with Tool-use (ART). ART is a tool-injection framework that tunes any VLA model to leverage off-the-shelf

Hyperbolic Multimodal Continual Learning: A Closest-Admissible Solution

arXiv:2609.29329v1 Announce Type: new Abstract: Existing continual-learning methods protect parameters, replayed examples, or Euclidean feature subspaces. When applied to hyperbolic multimodal models, they do not explicitly preserve the Lorentz geometry that jointly encodes withi

Integrating Local Detail and Global Context: A Dual-Input Multi-Task Learning Framework for Bone Tumor Diagnosis

arXiv:2609.28732v1 Announce Type: cross Abstract: Primary bone tumors are rare but clinically aggressive neoplasms whose diagnosis from radiographs is challenged by heterogeneous morphology, subtle lesion margins, and overlapping bone structures. To address the limitations of exi

SALI: Shot-Aware Late Interaction for Cross-Shot Relation Matching in Text-to-Video Retrieval using Film-Grammar Knowledge

arXiv:2609.29721v1 Announce Type: new Abstract: Text-to-video retrieval usually represents a video clip by a single embedding. This embedding often loses important relations between people. E.g., an interaction "Anna confronts Mark" is regularly filmed as alternating shot and rev

Shadow Reduction in Ultrasound Imaging Using Differentiable Simulation and Radiance Field Decomposition

arXiv:2609.29373v1 Announce Type: new Abstract: Acoustic shadows from bone and other highly attenuating tissues obscure clinically important structures in ultrasound. In fetal brain imaging, skull-induced artefacts disproportionately degrade the hemisphere closer to the transduce

TrackEverything: Long Horizon Dense Tracking via De-Duplicating 3D Scene Representations

arXiv:2609.30222v1 Announce Type: new Abstract: Existing point tracking models face a fundamental tradeoff: they can either track a sparse set of query points over long horizons, or track all points across only short clips. We introduce TrackEverything, a 3D point tracker that br

Training-Free Hold-Usage Detection in Sport Climbing with Foundation Pose Models

arXiv:2609.30026v1 Announce Type: new Abstract: Detecting which holds a climber uses, and when, underpins automated scoring, movement analysis, and assistive systems for sport climbing. Existing approaches train task-specific models or repurpose 2D pose estimators whose hand keyp

Beneath the Scores: Rethinking Hallucination Evaluation for Video Understanding Models

arXiv:2609.28991v1 Announce Type: new Abstract: Video understanding is increasingly performed by multi-stage LLM agents that separate temporal grounding, visual observation, and reasoning. Yet these stages are typically evaluated on different benchmarks and distributions, making

Exploiting Target Knowledge from MLLMs for Robust Few-Shot Segmentation

arXiv:2609.28949v1 Announce Type: new Abstract: Few-shot segmentation (FSS) aims to segment unseen object categories with a few (e.g., one or five) labeled examples, enabling efficient adaptation to novel classes. Conventional models typically rely on appearance-based visual matc

Mind What Matters for Reasoning: Aligning Cross-Modal Attention via Selective Probability Mass Concentration

arXiv:2609.29940v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) achieve strong performance on visual reasoning tasks, yet remain prone to hallucinations and over-reliance on language priors, often generating answers without adequately using task-relevant