// radar de ia

Dados & Embeddings

Papers, modelos e datasets em alta no Hugging Face, além do blog oficial — com leitura editorial em português.

todas LLMs & Texto Geração de Imagem Visão Computacional Áudio & Voz Multimodal Dados & Embeddings Robótica & RL
Blog Dados & Embeddings

ReLoop-UME: Recurrent Depth with Learnable Retrieval Registers for Universal Multimodal Embedding

arXiv:2607.28751v1 Announce Type: new Abstract: Universal multimodal embedding (UME) maps heterogeneous multimodal inputs into a shared embedding space. Existing UME models either form embeddings through single forward encoding or add computation through explicit rationale tokens and latent autoregressive states. Although token expansion can improve complex matching, serial generation increases retrieval latency and makes the final embedding depend on generated intermediate states. This raises a...

03.08.2026
Blog LLMs & Texto

Parameter-Efficient Fine-Tuning for Spiking Point Cloud Models

arXiv:2607.29048v1 Announce Type: new Abstract: Spiking Neural Networks (SNNs) offer energy-efficient solutions for point cloud analysis on resource-constrained devices through event-driven computation. However, existing pre-trained spiking point cloud models rely on full fine-tuning for downstream task adaptation, incurring substantial parameter and storage overhead. Furthermore, binary spike propagation suppresses task-relevant sub-threshold information. To address these issues, we propose Spi...

03.08.2026
Blog Dados & Embeddings

SEDR-Seq2P: A Lightweight Dilated Residual Sequence-to-Point Network for Multi-Task Industrial NILM

arXiv:2607.28693v1 Announce Type: new Abstract: Industrial NILM remains challenging because measurement noise and widespread concurrent machine operation reduce the generalization of models tuned on residential data. This work adopts a one-to-many, multi-task disaggregation setting, in which a single network estimates multiple industrial machine loads from aggregate power. Under a unified evaluation protocol on IMDELD, we benchmark Seq2Seq, Seq2SubSeq, Seq2Point, GRU, and WaveNet using energy-es...

03.08.2026
Blog LLMs & Texto

Guarantees on Dynamical System Distinguishability for LLM Token Generation

arXiv:2607.28667v1 Announce Type: new Abstract: Recent work has shown that classifying large language models (LLMs)' responses can be distinguished by modeling token embeddings as trajectories of a black-box dynamical system (DS) and comparing prediction residuals of two DSs. Despite the empirical success of this dynamical approach, a theoretical understanding of why it works, how well it scales as a function of the token sequence, and when it transfers across embedding models remains lacking. W...

03.08.2026
Blog Dados & Embeddings

Flow Matching with Missing Data

arXiv:2607.28698v1 Announce Type: new Abstract: Flow matching assumes fully observed training data, which many real-world applications rarely provide. We propose Missing-Data Flow Matching, which treats the missing coordinates of training samples as latent variables and averages the flow matching loss over the values they could take. We first prove the correction is exact rather than approximate. Under missing completely at random with true completions, the incomplete-data objective equals the c...

03.08.2026
Blog LLMs & Texto

BLADE: Boundary-Expanded and Layer-Adaptive Dynamic Exit for Efficient LLM Reasoning

arXiv:2607.28966v1 Announce Type: new Abstract: Large language models often improve task performance by generating long reasoning traces, but the resulting computation is frequently wasted on redundant verification and revision. Existing probe-based early-exit approaches mainly inspect explicit self-doubt expressions, leaving many earlier termination opportunities undetected. Expanding inspection to ordinary reasoning boundaries improves coverage, but also exposes highly diverse intermediate sta...

03.08.2026
Blog Dados & Embeddings

M3-DuplexBench: A Multi-Turn, Multilingual, Multidomain Benchmark for Full-Duplex Spoken Dialogue Models

arXiv:2607.29125v1 Announce Type: new Abstract: Full-duplex spoken dialogue systems (FDSDSs) can listen while speaking, enabling natural behaviors such as smooth turn-taking, backchannel handling, and user barge-in handling. However, fair comparisons in multi-turn conversations remain a challenge. In addition, existing benchmarks provide limited coverage of languages and dialogue domains. We propose M3-DuplexBench, a multi-turn, multilingual, multidomain benchmark for FDSDSs. M3-DuplexBench supp...

03.08.2026
Blog Visão Computacional

LegoQ: Density-Matrix Representation Learning with Spectral-Spatial State Transitions for Hyperspectral Classification

arXiv:2607.28970v1 Announce Type: new Abstract: Hyperspectral image classification is complicated by mixed pixels, spectral ambiguity, class imbalance, and limited annotations. Most current classifiers encode a pixel or patch as a deterministic vector and apply a linear or multilayer softmax head. Although effective for discrimination, this representation does not directly expose how mixed or uncertain a sample is. This paper presents \method, a classical density-matrix representation learning f...

03.08.2026
Blog Dados & Embeddings

Onton Releases Ontology 1: A Neurosymbolic Search Model That is 2.7x More Accurate than the World’s Best E-commerce Search Engines

Onton, a San Francisco-based search and discovery company, has released Ontology 1, a neurosymbolic model for complex, conversational, multimodal product search. On a 90-query benchmark scored by three independent LLM judges, Ontology 1 reached a mean precision@10 of 0.630, against 0.543 for Google Shopping and 0.469 for Amazon. It did this while indexing roughly 1% […] The post Onton Releases Ontology 1: A Neurosymbolic Search Model That is 2.7x More Accurate than the World’s Best E-commerc...

03.08.2026
Blog Dados & Embeddings

A Tutorial on GeoAI: Designing Footprint Extraction from NAIP Imagery Using U-Net, Grounding DINO, SAM, and Mask R-CNN

In this tutorial, we design a complete GeoAI workflow for extracting building footprints from high-resolution NAIP aerial imagery. We begin by configuring the geospatial deep learning environment, downloading raster imagery and vector labels, and inspecting their spatial properties before generating georeferenced image chips and segmentation masks. We then train a U-Net model with a ResNet-34 […] The post A Tutorial on GeoAI: Designing Footprint Extraction from NAIP Imagery Using U-Net, Ground...

02.08.2026
Meta AI uses a second AI agent as a memory coach to keep long tasks on track
Blog LLMs & Texto

Meta AI uses a second AI agent as a memory coach to keep long tasks on track

Meta AI wants to stop AI agents from forgetting errors they've already diagnosed and repeating failed steps during complex tasks. A separate memory agent maintains a structured memory bank and decides when to remind the main agent and when to stay silent. The system improved scores by up to 8.3 percentage points across two benchmarks. The article Meta AI uses a second AI agent as a memory coach to keep long tasks on track appeared first on The Decoder .

02.08.2026
← anterior 4 / 94 próxima →
1124 itens no radar