Dados & Embeddings

Blog Visão Computacional

Mirage: a Clean-Label Backdoor against LiDAR 3D Object Detection

arXiv:2606.20752v1 Announce Type: new Abstract: Deep neural network-based LiDAR 3D object detection serves as a critical perception component in safety-critical autonomous systems. However, recent studies have revealed its vulnerability to backdoor attacks. Existing attacks typically require white-box access or label modification and focus on geometric attacks such as object disappearance or bounding-box manipulation. In this paper, we present Mirage, a black-box and clean-label backdoor attack ...

23.06.2026

Blog LLMs & Texto

Sakana AI Launches Sakana Fugu: An Orchestration Model That Routes Tasks Across a Swappable Pool of Frontier LLMs

Fugu and Fugu Ultra route tasks across a swappable model pool, leading most coding, reasoning, and agentic benchmarks. The post Sakana AI Launches Sakana Fugu: An Orchestration Model That Routes Tasks Across a Swappable Pool of Frontier LLMs appeared first on MarkTechPost .

22.06.2026

Blog LLMs & Texto

Mitigating vendor lock-in with Sakana AI Fugu multi-agent models

Sakana AI launched Fugu to orchestrate multi-agent operations and mitigate single-vendor dependency risks in enterprise deployments. Enterprises face operational vulnerabilities when relying entirely on monolithic AI APIs. Japanese AI firm Sakana AI designed Fugu as a response to these concentration risks by creating an orchestration language model that calls upon a pool of varied models […] The post Mitigating vendor lock-in with Sakana AI Fugu multi-agent models appeared first on AI News .

22.06.2026

Blog LLMs & Texto

NAIRR Science Program Reshapes Scientific Research, Powered by NVIDIA AI Infrastructure

For the past two years, the U.S. National Science Foundation’s National Artificial Intelligence Research Resource (NAIRR) pilot program has driven innovative research across the U.S. for over 700 projects — spanning protein prediction and infectious disease outbreak management. NVIDIA contributed to the NAIRR pilot through a cloud-based resource that gives researchers dedicated access to a […]

22.06.2026

Blog LLMs & Texto

Sakana AI's Fugu orchestrates multiple LLMs to match Anthropic's Fable and Mythos benchmarks

Japanese AI startup Sakana AI is launching Fugu, a system that coordinates multiple AI models on the fly to compete with leaders like Anthropic's Fable 5. The approach also aims to cut dependence on any single AI provider. The article Sakana AI's Fugu orchestrates multiple LLMs to match Anthropic's Fable and Mythos benchmarks appeared first on The Decoder .

22.06.2026

Blog Dados & Embeddings

MoonMath AI Open-Sources a HIP Attention Kernel for AMD MI300X That Beats AITER v3 on Every Shape and Rounding Mode

The HIP kernel uses one-instruction asm wrappers and an eight-wave pipeline to outperform AMD's AITER v3 on MI300X. The post MoonMath AI Open-Sources a HIP Attention Kernel for AMD MI300X That Beats AITER v3 on Every Shape and Rounding Mode appeared first on MarkTechPost .

22.06.2026

Blog LLMs & Texto

How to Design Python-First Interactive Dashboards with Prefab Reactive UI Components and Static HTML Export

In this tutorial, we build a Prefab application that creates interactive dashboards entirely in Python. We design an operations dashboard with reactive state, charts, tables, filters, forms, tabs, and metrics. We generate synthetic pipeline monitoring data and connect it to live UI controls. We then export the app as static HTML and preview it directly inside Google Colab. The post How to Design Python-First Interactive Dashboards with Prefab Reactive UI Components and Static HTML Export appeare...

22.06.2026

Paper Dados & Embeddings

KaLM-Reranker-V1: Fast but Not Late Interaction for Compressed Document Reranking

KaLM-Reranker-V1 is a fast reranker that decouples query and passage computation using encoder-decoder architecture with Matryoshka embedding pooling and cross-attention for effici…

22.06.2026 ·▲ 38

Paper LLMs & Texto

EnterpriseClawBench: Benchmarking Agents from Real Workplace Sessions

EnterpriseClawBench presents a benchmark for enterprise agents based on real-world sessions with 852 reproducible tasks, emphasizing comprehensive evaluation metrics beyond single…

22.06.2026 ·▲ 55

Paper Dados & Embeddings

HAKARI-Bench: A Lightweight Benchmark for Comparing Retrieval Architectures and Efficiency Settings under Unified Conditions

HAKARI-Bench provides a lightweight benchmark for comparing retrieval methods across multiple configurations and languages, enabling efficient model selection and performance analy…

22.06.2026

Paper LLMs & Texto

CLI-Universe: Towards Verifiable Task Synthesis Engine for Terminal Agents

A principled synthesis engine generates high-quality terminal-agent tasks through multi-dimensional capability taxonomy and evidence-guided research, creating a distilled dataset t…

22.06.2026 ·▲ 24

Blog LLMs & Texto

The 7 Types of Agent Memory: A Technical Guide for AI Engineers

LLMs are stateless by default. Agent memory fixes that. This guide breaks down all 7 types — working, semantic, episodic, procedural, retrieval, parametric, and prospective. It covers what each stores, where it lives, and when to build it. Includes a comparison table and working Python code. The post The 7 Types of Agent Memory: A Technical Guide for AI Engineers appeared first on MarkTechPost .

21.06.2026