发布日期：2026-03-31
收录条目：20
1. Microsoft AI Releases Harrier-OSS-v1: A New Family of Multilingual Embedding Models Hitting SOTA on Multilingual MTEB v2
- 来源：MarkTechPost
- 发布时间：2026-03-30 22:22 UTC
- 链接：https://www.marktechpost.com/2026/03/30/microsoft-ai-releases-harrier-oss-v1-a-new-family-of-multilingual-embedding-models-hitting-sota-on-multilingual-mteb-v2/
摘要：Microsoft has announced the release of Harrier-OSS-v1, a family of three multilingual text embedding models designed to provide high-quality semantic representations across a wide range of languages. The release includes
2. How Ring scales global customer support with Amazon Bedrock Knowledge Bases
- 来源：AWS ML Blog
- 发布时间：2026-03-30 15:29 UTC
- 链接：https://aws.amazon.com/blogs/machine-learning/how-ring-scales-global-customer-support-with-amazon-bedrock-knowledge-bases/
摘要：In this post, you'll learn how Ring implemented metadata-driven filtering for Region-specific content, separated content management into ingestion, evaluation and promotion workflows, and achieved cost savings while scal
3. Reimagine marketing at Volkswagen Group with generative AI
- 来源：AWS ML Blog
- 发布时间：2026-03-30 15:24 UTC
- 链接：https://aws.amazon.com/blogs/machine-learning/reimagine-marketing-at-volkswagen-group-with-generative-ai/
摘要：In this post, we explore the challenges that Volkswagen Group faced in producing brand-compliant marketing assets at scale. We walk through how we built a generative AI solution that generates photorealistic vehicle imag
4. Build a solar flare detection system on SageMaker AI LSTM networks and ESA STIX data
- 来源：AWS ML Blog
- 发布时间：2026-03-30 15:20 UTC
- 链接：https://aws.amazon.com/blogs/machine-learning/build-a-solar-flare-detection-system-on-sagemaker-ai-lstm-networks-and-esa-stix-data/
摘要：In this post, we show you how to use Amazon SageMaker AI to build and deploy a deep learning model for detecting solar flares using data from the European Space Agency's STIX instrument.
5. Deliver hyper-personalized viewer experiences with an agentic AI movie assistant using Amazon Bedrock AgentCore and Amazon Nova Sonic 2.0
- 来源：AWS ML Blog
- 发布时间：2026-03-30 15:17 UTC
- 链接：https://aws.amazon.com/blogs/machine-learning/deliver-hyper-personalized-viewer-experiences-with-an-agentic-ai-movie-assistant-using-amazon-bedrock-agentcore-and-amazon-nova-sonic-2-0/
摘要：In this post, we walk through two use cases that help enhance the user viewing experience using agentic AI tools and frameworks including Strands Agents SDK, Amazon Bedrock AgentCore, and Amazon Nova Sonic 2.0. This agen
6. Okta’s CEO is betting big on AI agent identity
- 来源：The Verge AI
- 发布时间：2026-03-30 15:15 UTC
- 链接：https://www.theverge.com/podcast/902264/oktas-ceo-is-betting-big-on-ai-agent-identity
摘要：Today, I’m talking with Todd McKinnon, who is co-founder and CEO of Okta, a platform that lets big companies manage security and identity across all the apps and services their employees use. Think of it like login manag
7. Salesforce AI Research Releases VoiceAgentRAG: A Dual-Agent Memory Router that Cuts Voice RAG Retrieval Latency by 316x
- 来源：MarkTechPost
- 发布时间：2026-03-30 09:56 UTC
- 链接：https://www.marktechpost.com/2026/03/30/salesforce-ai-research-releases-voiceagentrag-a-dual-agent-memory-router-that-cuts-voice-rag-retrieval-latency-by-316x/
摘要：In the world of voice AI, the difference between a helpful assistant and an awkward interaction is measured in milliseconds. While text-based Retrieval-Augmented Generation (RAG) systems can afford a few seconds of ‘thin
8. BeSafe-Bench: Unveiling Behavioral Safety Risks of Situated Agents in Functional Environments
- 来源：arXiv cs.AI
- 发布时间：2026-03-30 04:00 UTC
- 链接：https://arxiv.org/abs/2603.25747
摘要：arXiv:2603.25747v1 Announce Type: new Abstract: The rapid evolution of Large Multimodal Models (LMMs) has enabled agents to perform complex digital and physical tasks, yet their deployment as autonomous decision-makers i
9. AutoB2G: A Large Language Model-Driven Agentic Framework For Automated Building-Grid Co-Simulation
- 来源：arXiv cs.AI
- 发布时间：2026-03-30 04:00 UTC
- 链接：https://arxiv.org/abs/2603.26005
摘要：arXiv:2603.26005v1 Announce Type: new Abstract: The growing availability of building operational data motivates the use of reinforcement learning (RL), which can learn control policies directly from data and cope with th
10. Semi-Automated Knowledge Engineering and Process Mapping for Total Airport Management
- 来源：arXiv cs.AI
- 发布时间：2026-03-30 04:00 UTC
- 链接：https://arxiv.org/abs/2603.26076
摘要：arXiv:2603.26076v1 Announce Type: new Abstract: Documentation of airport operations is inherently complex due to extensive technical terminology, rigorous regulations, proprietary regional information, and fragmented com
11. GUIDE: Resolving Domain Bias in GUI Agents through Real-Time Web Video Retrieval and Plug-and-Play Annotation
- 来源：arXiv cs.AI
- 发布时间：2026-03-30 04:00 UTC
- 链接：https://arxiv.org/abs/2603.26266
摘要：arXiv:2603.26266v1 Announce Type: new Abstract: Large vision-language models have endowed GUI agents with strong general capabilities for interface understanding and interaction. However, due to insufficient exposure to
12. AIRA_2: Overcoming Bottlenecks in AI Research Agents
- 来源：arXiv cs.AI
- 发布时间：2026-03-30 04:00 UTC
- 链接：https://arxiv.org/abs/2603.26499
摘要：arXiv:2603.26499v1 Announce Type: new Abstract: Existing research has identified three structural performance bottlenecks in AI research agents: (1) synchronous single-GPU execution constrains sample throughput, limiting
13. CADSmith: Multi-Agent CAD Generation with Programmatic Geometric Validation
- 来源：arXiv cs.AI
- 发布时间：2026-03-30 04:00 UTC
- 链接：https://arxiv.org/abs/2603.26512
摘要：arXiv:2603.26512v1 Announce Type: new Abstract: Existing methods for text-to-CAD generation either operate in a single pass with no geometric verification or rely on lossy visual feedback that cannot resolve dimensional
14. Stabilizing Rubric Integration Training via Decoupled Advantage Normalization
- 来源：arXiv cs.AI
- 发布时间：2026-03-30 04:00 UTC
- 链接：https://arxiv.org/abs/2603.26535
摘要：arXiv:2603.26535v1 Announce Type: new Abstract: We propose Process-Aware Policy Optimization (PAPO), a method that integrates process-level evaluation into Group Relative Policy Optimization (GRPO) through decoupled adva
15. DesignWeaver: Dimensional Scaffolding for Text-to-Image Product Design
- 来源：arXiv cs.AI
- 发布时间：2026-03-30 04:00 UTC
- 链接：https://arxiv.org/abs/2502.09867
摘要：arXiv:2502.09867v2 Announce Type: cross Abstract: Generative AI has enabled novice designers to quickly create professional-looking visual representations for product concepts. However, novices have limited domain knowle
16. A Lightweight, Transferable, and Self-Adaptive Framework for Intelligent DC Arc-Fault Detection in Photovoltaic Systems
- 来源：arXiv cs.AI
- 发布时间：2026-03-30 04:00 UTC
- 链接：https://arxiv.org/abs/2603.25749
摘要：arXiv:2603.25749v1 Announce Type: cross Abstract: Arc-fault circuit interrupters (AFCIs) are essential for mitigating fire hazards in residential photovoltaic (PV) systems, yet achieving reliable DC arc-fault detection u
17. Sommelier: Scalable Open Multi-turn Audio Pre-processing for Full-duplex Speech Language Models
- 来源：arXiv cs.AI
- 发布时间：2026-03-30 04:00 UTC
- 链接：https://arxiv.org/abs/2603.25750
摘要：arXiv:2603.25750v1 Announce Type: cross Abstract: As the paradigm of AI shifts from text-based LLMs to Speech Language Models (SLMs), there is a growing demand for full-duplex systems capable of real-time, natural human-
18. A-SelecT: Automatic Timestep Selection for Diffusion Transformer Representation Learning
- 来源：arXiv cs.AI
- 发布时间：2026-03-30 04:00 UTC
- 链接：https://arxiv.org/abs/2603.25758
摘要：arXiv:2603.25758v1 Announce Type: cross Abstract: Diffusion models have significantly reshaped the field of generative artificial intelligence and are now increasingly explored for their capacity in discriminative repres
19. CANGuard: A Spatio-Temporal CNN-GRU-Attention Hybrid Architecture for Intrusion Detection in In-Vehicle CAN Networks
- 来源：arXiv cs.AI
- 发布时间：2026-03-30 04:00 UTC
- 链接：https://arxiv.org/abs/2603.25763
摘要：arXiv:2603.25763v1 Announce Type: cross Abstract: The Internet of Vehicles (IoV) has become an essential component of smart transportation systems, enabling seamless interaction among vehicles and infrastructure. In rece
20. Consistency Amplifies: How Behavioral Variance Shapes Agent Accuracy
- 来源：arXiv cs.AI
- 发布时间：2026-03-30 04:00 UTC
- 链接：https://arxiv.org/abs/2603.25764
摘要：arXiv:2603.25764v1 Announce Type: cross Abstract: As LLM-based agents are deployed in production systems, understanding their behavioral consistency (whether they produce similar action sequences when given identical tas