Visão Computacional

Horizon3D: Sparse Radar-Camera Fusion for Long-Range 3D Perception in Autonomous Driving

arXiv:2606.31096v1 Announce Type: new Abstract: Long-range 3D object detection is critical for safe autonomous driving at highway speeds, yet existing radar-camera fusion methods remain limited at extended ranges. BEV-based methods capture scene-level context but incur rapidly growing computation and often lose fine-grained object detail, while query-based methods are efficient but provide limited scene-level context. Temporal fusion further requires both multi-frame accumulation for sparse dist...

No Adaptation Without Observation: Observability-Constrained Test-Time Prompt Tuning for LiDAR Semantic Segmentation

arXiv:2606.30937v1 Announce Type: new Abstract: LiDAR semantic segmentation often degrades under real-world deployment due to evolving sensing conditions, while collecting new annotations for retraining is impractical. Test-time adaptation (TTA) updates model parameters online using pseudo-label supervision, but directly applying standard TTA strategies to LiDAR data is challenging. Because pseudo-label reliability is spatially heteroscedastic under range-dependent sparsity and occlusion, unifor...

TAPE: Tether-Aware Path Planning for Autonomous Exploration of Unknown 3D Cavities Using a Tangle-Compatible Tethered Aerial Robot

arXiv:2606.30817v1 Announce Type: new Abstract: This letter presents the first method for autonomous exploration of unknown cavities in three dimensions (3D) that focuses on minimizing the distance traveled and the length of tether unwound. Considering that the tether entanglements are little influenced by the global path, our approach employs a 2-level hierarchical architecture. The global frontier-based planning solves a Traveling Salesman Problem (TSP) to minimize the distance. The local plan...

Dual Sparse Aggregation Transformer for Multispectral Object Detection

arXiv:2606.31015v1 Announce Type: new Abstract: Transformer-based approaches have obtained excellent performance in multispectral object detection tasks due to their ability to model long-range dependencies and capture complementary information. However, previous transformer-based multispectral detection methods tend to use all available tokens for similarity calculation, which results in redundant information interaction from irrelevant areas, leading to degraded detection performance. To overc...

Claude Science is Anthropic’s newest flagship product

At an event for pharmaceutical executives, biotech founders, and researchers on Tuesday, Anthropic announced Claude Science, a major new product intended to support scientific research in the same way that Claude Code supports software engineering. Like Claude Code, Claude Science can autonomously carry out meaningful work when given concise, high-level instructions, and it has access…

New attack provides one more reason why AI browsers are a bad idea

Telling an LLM that 2 + 2 = 5 is enough to make it follow forbidden instructions.

NVIDIA BioNeMo Agent Toolkit Brings Accelerated AI to Life Sciences Researchers in Claude Science

Life sciences has entered an era of computational scale, and for more than a decade, NVIDIA has built the full GPU-accelerated computing stack — spanning hardware, frameworks, libraries, models, microservices and domain-specific tools — to help researchers run more sophisticated workflows and iterate faster. This week, Anthropic announced Claude Science, an AI workbench for science […]

How NVIDIA’s Inference Software Stack Powers the Lowest Token Cost

As organizations move from AI pilots to production AI factories, infrastructure decisions have shifted from peak chip specifications to cost per token: how many useful tokens they can deliver per dollar, per watt and within required latency targets. Codesigned with NVIDIA GPUs, CPUs, networking and systems, and strengthened by a broad open source ecosystem, NVIDIA’s […]

Why Specialization Is Inevitable

US campaigns now run on AI at nearly every step, and Europe is drawing a harder line

Republican and Democratic campaigns now run on AI at nearly every step, from vetting opponents to micro-targeting voters, according to a New York Times report. But the technology is still a political minefield, and Europe is taking a very different approach. The article US campaigns now run on AI at nearly every step, and Europe is drawing a harder line appeared first on The Decoder .

Unlimited-OCR: a Baidu derruba o muro da memória na leitura de documentos

Com 3 bilhões de parâmetros e apenas 500 milhões ativos, o modelo aberto da Baidu lê dezenas de páginas num único passe mantendo o cache de memória constante — e passa o DeepSeek OCR em precisão e velocidade.

Unlocking Britain’s next era of productivity: Building a nation of AI trailblazers

Google UK shares its latest Economic Impact Report and how to enable more people to unlock the benefits of AI-powered technologies.