Pai 的 AI 雷达

模型与评测

今天：AIGC Video Detection（arXiv:2609），Introducing Gemini 3.8（Google's new Gemini 3）。并行还有 Accelerating vision-、AIBuildAI-2.5、NVIDIA 联合 Google。

日期
2026/09/25
今日条目
93
当前类目
30
往期2026/09/25
全部93编码代理8Agent与工具9个人助理3模型与评测30创作成片13开发与开源9产品接入21
领域机器人具身1硬件边缘2生信医疗2法律合规1金融2设计UI1游戏1安全治理2行业观察4创业者3
#25

A Hybrid AI Framework for Academic Advising: Integrating Ensemble-Based Grade Prediction and a Rule-Based Expert System

arXiv:2609.26243v1 Announce Type: new Abstract: The rapidly increasing student population has posed serious challenges to the traditional academic advising process. This study designs and implements a multi-purpose intelligent system to support students' academic progress, based

推荐理由A Hybrid AI Framework for Academic：arXiv:2609.26243v1 Announce Type: new Abstract: The rapidly increasing student。
模型与评测arXiv cs.AI 官方
arxiv.org打开原文
#26

A2M: Trace-Optimized Agent Hijacking in the MCP Ecosystem

arXiv:2609.26761v1 Announce Type: cross Abstract: Agents using the Model Context Protocol (MCP) rely on semantic matching to select tools from third-party servers, exposing a semantic supply-chain risk through attacker-controlled metadata and outputs. We introduce A2M (Attraction

推荐理由A2M: Trace-Optimized Agent Hijacking：arXiv:2609.26761v1 Announce Type: cross Abstract: Agents using the Model Context。
模型与评测arXiv cs.AI 官方
arxiv.org打开原文
#27

AstraLOD3: Zero-shot multimodal agentic reconstruction of LOD3 building models

arXiv:2609.28061v1 Announce Type: new Abstract: Automated LOD3 building modeling typically relies on purpose-built geometric or learning-based pipelines, limiting flexibility across heterogeneous buildings and input evidence conditions. This study investigates whether Astra, a ge

推荐理由AstraLOD3: Zero-shot multimodal agentic：arXiv:2609.28061v1 Announce Type: new Abstract: Automated LOD3 building modeling。
模型与评测arXiv cs.CV 官方
arxiv.org打开原文
#28

Beyond Mean Foils: Auditing Worst-Foil Specificity in Frozen CLIP Region Explanations

arXiv:2609.27356v1 Announce Type: new Abstract: A region can overlap a target object yet contribute more to another class. We test regions selected by Cluster-based Concept Importance (CCI) in frozen CLIP. Across COCO and VOC with two checkpoints, 41.08-64.78% of regions that pas

推荐理由Beyond Mean Foils: Auditing Worst-Foil：arXiv:2609.27356v1 Announce Type: new Abstract: A region can overlap a target object。
模型与评测arXiv cs.CV 官方
arxiv.org打开原文