Knowledge catalogue
arXiv:2512.04085v2 Announce Type: replace Abstract: We introduce the 'single-life' learning paradigm, where we train a distinct vision model exclusively on egocentric videos captured by one individual
arXiv:2605.26646v1 Announce Type: new Abstract: LLM-based multi-agent systems decompose complex tasks into interacting roles, but most remain manually orchestrated by prompts, tools, and control rules
arXiv:2605.27139v1 Announce Type: cross Abstract: Electron tomography (ET) plays an important role in the three-dimensional (3D) characterization of nanomaterials. However, under limited-angle and spa
arXiv:2605.26501v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have transformed multi-modal understanding, excelling in tasks like image captioning and visual question answerin
arXiv:2312.02694v2 Announce Type: replace Abstract: Existing optical character recognition (OCR) methods rely on task-specific designs with divergent paradigms, architectures, and training strategies,
U.S. law enforcement agencies are monitoring growing backlash to AI and have begun classifying anti-technology sentiment as an extremism threat, with unpublished reports from the Department of Homelan
ABC News: US prosecutors charge Google engineer Michele Spagnuolo with using inside information to make $1.2M on Polymarket bets about Google's Year in Search results — Michele Spagnuolo allegedly pla
The U.S. Space Force awarded SpaceX a $2.29 billion contract to build a secure, high-speed satellite communications network to connect military sensors and weapons platforms across the globe. The Spac
Ollama v0.30.0-rc27 is a pre-release version that changes the architecture to directly support llama.cpp instead of building on top of GGML, and allows for compatibility with GGUF file format. MLX is
arXiv:2504.07853v2 Announce Type: replace Abstract: Light field microscopy (LFM) has gained significant attention due to its ability to capture snapshot-based, large-scale 3D fluorescence images. Howe
Jay Peters / The Verge: Valve raises Steam Deck OLED prices due to “rising memory and storage costs”; the 512GB model is now 789, up from 549, and the 1TB model is 949, up from 649 — The 1TB OLED mode
Valve's Steam Deck OLED models are finally back in stock after months of shortages, but buyers are now facing much steeper prices than before. The 512GB Steam Deck OLED now costs 789, up from 549, whi
arXiv:2605.26477v1 Announce Type: new Abstract: While Deep Neural Networks (DNNs) achieve remarkable performance, their tendency to produce overconfident predictions. Evidential Deep Learning (EDL) mi
arXiv:2602.21450v2 Announce Type: replace Abstract: Many robotic systems allow independent control of position and orientation (pose), including omnidirectional aerial vehicles, underwater robots, and
arXiv:2605.26433v1 Announce Type: new Abstract: Large language model (LLM) summarization systems may pass compact vector representations of private inputs to downstream retrieval, monitoring, audit, o
arXiv:2510.17759v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) extend large language models with visual reasoning, but their multimodal design also introduces new, underexplor
arXiv:2605.26498v1 Announce Type: new Abstract: Large language models (LLMs) have improved Verilog generation from natural-language specifications, but most pipelines still treat generation as isolate
arXiv:2605.26457v1 Announce Type: cross Abstract: AI coding agents are increasingly used to write real-world software, but ensuring that their outputs are correct remains a fundamental challenge. Form
arXiv:2605.26277v1 Announce Type: cross Abstract: Blood vessel segmentation is a core task in medical image analysis for the care of vascular diseases and surgical planning, yet the challenges of prov
Cognition Inc., a provider of artificial intelligence programming tools, today announced that it has raised more than 1 billion in funding. Lux Capital, General Catalyst and 8VC led the Series D round
arXiv:2605.26144v1 Announce Type: cross Abstract: We present VISTA (VIsual Spec-To-App Benchmark), a benchmark for evaluating the end-to-end web-app generation capabilities of LLM-based agents. Unlike
arXiv:2605.26380v1 Announce Type: cross Abstract: Frontier multimodal large language models (MLLMs) have been reported to achieve over 90% accuracy on fine-grained perception benchmarks. However, such
arXiv:2605.27141v1 Announce Type: new Abstract: Large language models (LLMs) have evolved into interactive agents that collaborate with users in real-world tasks. Effective collaboration in such setti
arXiv:2602.12833v2 Announce Type: replace-cross Abstract: Longitudinal clinical reasoning over electronic health records requires tracking evolving physiological measurements, laboratory results, and
Volvo Cars, majority owned by China's Geely Holding, received approval from the U.S. government allowing it to continue selling vehicles with Chinese 'connected technology' in the country. This exempt
arXiv:2605.27114v1 Announce Type: new Abstract: Learning from demonstrations is effective for robotic manipulation, but collecting sufficient task-specific data remains a major bottleneck. Under distr
Warp is making a significant investment in developing open source tools and integrations built on GPT-5.5, OpenAI's advanced language model. The initiative aims to leverage GPT-5.5's capabilities to c
we are a car We've created the world's fastest PDF parser ⚡️ And it's more accurate than any other open-source, model-free PDF parser out there (pymupdf, pypdf, markitdown, pdftotext, opendataloader,
We have crossed the uncanny valley of AI video. Introducing Project Luxo: a new initiative exploring how AI-generated video has crossed the uncanny valley. Over the past few weeks, we’ve shared a seri
We just hit a major milestone — @FireworksAI_HQ passed $800M annualized run rate and reached 4x revenue growth, apart from Cursor, in Q1. We invite curious and courageous minds to join us and define n
We launched Context Hub as a way to manage skills, AGENTS.md files, and other context files an agent might need You can easily use it as a virtual filesystem in deepagents See this video for more info
We spent a ton of time making worktrees actually work well for agent swarms and large repos. When you’re running 10s of agents that ship, you quickly realize you need worktree, but git’s defaults are
we will have the most science and math submissions ever in the next few years. but most ≠ best. to get to best, quality will have to beat slop Terence Tao: AI is creating a “traffic jam” in math If AI
We're hosting an event on June 16th in San Francisco. Compile is a one-day event that brings together engineers, researchers, designers, and builders of all kinds to discuss the future of software. ht
We're on a dangerous trajectory toward superintelligent AI that nobody controls. ControlAI's Adam Shimi (@epist_vigilance) and Connor Leahy (@NPCollapse) lay out the problem and how to tackle it, in a
We're open-sourcing the Unigram tokenizer we rebuilt to reduce CPU utilization by 5-6x. Small rerankers and embedders run in single-digit milliseconds on GPU, making CPU tokenization a meaningful shar
Anthropic has made improvements to Claude Code's responsiveness and reliability, with Thariq providing details on the enhancements implemented. The update likely covers performance optimizations, bug
We've created the world's fastest PDF parser ⚡️ And it's more accurate than any other open-source, model-free PDF parser out there (pymupdf, pypdf, markitdown, pdftotext, opendataloader, pymupdf4llm)
arXiv:2507.06513v3 Announce Type: replace Abstract: Advances in vision-based sensors and computer vision algorithms have significantly improved the analysis and understanding of traffic scenarios. To
What does JEPA actually learn? We can finally prove it 🌍 So excited to share our theory of identifiable World Models: LeJEPA recovers the latent variables of the world. Plan in the learned World Model
arXiv:2605.26795v1 Announce Type: new Abstract: Chain-of-thought (CoT) prompting reliably improves language-model accuracy, but which properties of a rationale text drive the improvement is poorly und
arXiv:2605.26183v1 Announce Type: cross Abstract: Graph Neural Networks (GNNs) have emerged as a structurally natural approach for molecular toxicity prediction, operating directly on atomic connectiv
NVIDIA DLSS 4.5 introduces Dynamic Multi Frame Generation and a second-generation transformer model for Super Resolution to enhance game image quality and frame rates for Unreal Engine 5. The new Tens
arXiv:2605.26350v1 Announce Type: cross Abstract: In-context learning (ICL) is often motivated by the intuition that demonstrations help because they provide correct input-output examples. However, we
arXiv:2605.26155v1 Announce Type: cross Abstract: Guided Soft Actor-Critic (GSAC) distills knowledge from a privileged full-state teacher to a partial-observation student for autonomous driving, but u
arXiv:2605.26418v1 Announce Type: cross Abstract: A properly calibrated rule-based autoscaler can beat every one of six mainstream deep reinforcement learning (DRL) algorithms on cost across every wor
arXiv:2605.27313v1 Announce Type: new Abstract: Demographic information is often used to model annotator perspectives in subjective tasks such as hate speech detection, but its benefit is inconsistent
arXiv:2605.26379v1 Announce Type: cross Abstract: A representation that scrambles the true degrees of freedom of the world cannot support reliable planning or compositional generalization. We prove th
arXiv:2605.27348v1 Announce Type: cross Abstract: Recent generative models have largely closed the gap on low-level artifacts - pixel fingerprints, frequency anomalies, upsampling traces - particularl
arXiv:2509.26600v2 Announce Type: replace-cross Abstract: As LLMs rapidly saturate existing benchmarks, automated benchmark creation using LLMs (LLM-as-a-benchmark) -- where a model generates test inp
arXiv:2605.26929v1 Announce Type: new Abstract: Adversarial training (AT) remains one of the most reliable empirical defenses against adversarial attacks. Its robustness critically depends on how the
arXiv:2605.26171v1 Announce Type: new Abstract: Many practical anomalies are not merely rare inputs, but violations of semantic constraints: objects co-occur in structured ways, actions imply precondi
When they write fiction, AIs are obsessed by things that take or give memories, contracts with sentient inanimate objects, sets of secretive rules that govern conduct & which no one can acknowledge ou
arXiv:2603.28345v2 Announce Type: replace-cross Abstract: LLM API calls are becoming a ubiquitous program construct, yet they create a boundary that no existing program analysis can cross: runtime val
arXiv:2605.24906v2 Announce Type: replace Abstract: Detecting AI-generated images (AIGI) remains challenging because detectors often fail to generalize to unseen generators. Although existing methods
arXiv:2605.26530v1 Announce Type: new Abstract: Legal reasoning requires distinguishing changes that matter from those that do not. Legal AI should remain stable under legally irrelevant perturbations
arXiv:2605.26362v1 Announce Type: cross Abstract: In many reasoning tasks, large language models (LLMs) rely on structured external knowledge, such as graphs and tables, which is typically linearized
arXiv:2605.26655v1 Announce Type: new Abstract: Automated prompt optimization methods (e.g., DSpy, TextGrad) can substantially improve the performance of large language model (LLM), however, their gen
arXiv:2605.26660v1 Announce Type: new Abstract: Quantization is an effective approach to reduce the memory footprint and inference cost of large language models (LLMs), yet maintaining performance in
Not content with its push into autonomous artificial intelligence workers, WisdomAI Inc. is bringing its comprehensive analytics capabilities to third-party software-as-a-service platforms with today’