Knowledge catalogue
arXiv:2606.05743v1 Announce Type: cross Abstract: Despite advances in safety alignment, large language models remain vulnerable to continuously evolving jailbreaks. Existing fine-tuned safety classifi
arXiv:2606.05917v1 Announce Type: cross Abstract: Long-video question answering remains challenging for Vision-Language Models (VLMs), as answer-relevant evidence is often sparse, transient, and tempo
arXiv:2606.06011v1 Announce Type: new Abstract: In this work, we propose a framework that combines multi-agent reinforcement learning (MARL) with model-based control to achieve safe, dynamically feasi
arXiv:2606.06312v1 Announce Type: new Abstract: Successful robot automation requires accurate global localization to support repeatability, task planning, goal specification, and safe operation. Howev
arXiv:2606.05443v1 Announce Type: cross Abstract: The rapid pace of scientific publishing has made the identification and synthesis of high-impact work an increasingly urgent challenge. We introduce M
arXiv:2606.06473v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly applied to long-horizon tasks such as scientific discovery and machine learning engineering (MLE),
A mocap actress demonstrated real-time teleoperation of six robots simultaneously during an AMD-sponsored event, showcasing advanced motion capture technology and remote robotic control capabilities.
arXiv:2606.05407v1 Announce Type: new Abstract: This work addresses sequentially grasping multiple objects with a single dexterous hand without releasing those already held. Most dexterous grasping me
arXiv:2606.05581v1 Announce Type: cross Abstract: Intrinsic methods fill the default toolbox for geometry processing on meshes. Intrinsic operators, in particular the Laplacian, underlie methods that
More than half of Cognition's first 50 employees were former founders. @ScottWu46 sat down with @breeves08 and @lux_capital to talk about correctness over comfort, staying focused on our mission, and
arXiv:2606.06139v1 Announce Type: new Abstract: We present MotionDisco, a framework that discovers contact-rich, long-horizon humanoid loco-manipulation motions from scratch, without relying on teleop
arXiv:2606.06245v1 Announce Type: new Abstract: Vision-Language-Action (VLA) policies remain brittle in long-horizon and high-uncertainty control, where one-pass action decoding provides limited infer
arXiv:2606.06103v1 Announce Type: new Abstract: Medical image segmentation is often framed as a search for stronger architectures, but this can obscure a more fundamental question: what does the datas
arXiv:2606.05181v1 Announce Type: new Abstract: Natural Language Inference (NLI) is a fundamental task in natural language understanding that requires determining the logical relationship between a pr
arXiv:2606.06281v1 Announce Type: new Abstract: Touch sensing is beneficial for solving a wide variety of manipulation tasks. While there exists a wide range of tactile sensors with different properti
arXiv:2606.05641v1 Announce Type: new Abstract: Reliable crack assessment requires not only accurate pixel-level masks but also connected crack geometry and confidence estimates that remain stable und
arXiv:2606.06065v1 Announce Type: new Abstract: Second-language (L2) speech recognition often requires transcriptions of pronunciations and intended meanings. Multi-task learning (MTL) is a natural ap
arXiv:2606.05444v1 Announce Type: new Abstract: Coreference resolution is a core NLP task, having a broad range of downstream applications, e.g.~machine translation, question answering, document summa
arXiv:2606.05545v1 Announce Type: new Abstract: The development of multilingual Alzheimer's Disease Dementia (AD) detection models presents significant challenges due to the resource-intensive and tim
arXiv:2606.05997v1 Announce Type: new Abstract: We present the AILS-NTUA submission to the EXIST 2026 Lab at CLEF, addressing multimodal sexism identification and characterization in memes (Task 2) an
arXiv:2606.05724v1 Announce Type: new Abstract: Long-form narrative QA requires reasoning over evolving story worlds rather than isolated passages: answers may depend on earlier goals, changing charac
arXiv:2606.06031v1 Announce Type: new Abstract: Masked diffusion language models generate text by iteratively unmasking many tokens in parallel, but this speed comes with a correction problem: tokens
A discussion on building an AI-powered article generator using CrewAI and Ollama with specialized AI agents for research and writing to generate comprehensive articles on any topic. The solution runs
Nvidia's Nemotron 3 Ultra, an open-source model designed for long-context tasks, is now available to Pro and Max subscribers on Perplexity and Computer. This new model represents Nvidia's latest contr
The New York State legislature passed a one-year moratorium on new large data centers, the first statewide ban of its kind if Democratic Governor Kathy Hochul signs it into law. Lawmakers behind the b
arXiv:2606.05785v1 Announce Type: new Abstract: Real-Time License Plate Detection and Recognition (LPDR) forms the backbone of modern smart cities. Although the YOLOV5-PDLPR model substantially improv
Pinecone presents early access customer results and benchmarks for Nexus, their vector database or search product, demonstrating real-world performance metrics and use cases from initial deployments.
NitroGen just won CVPR Best Paper Honorable Mention!! We are making strides towards general-purpose embodied agents that master not only the real world physics, but also all possible physics across a
arXiv:2606.05261v1 Announce Type: new Abstract: Variable fonts enable continuous variation of glyph geometry along semantic design axes such as weight, width, slant, and optical size. However, constru
arXiv:2601.08446v2 Announce Type: replace Abstract: The development of reliable methods for multi-label classification (MLC) has become a prominent research direction in remote sensing (RS). As the sc
arXiv:2606.05535v1 Announce Type: new Abstract: Medical visual question answering (Med-VQA) has strong potential for clinical decision support by enabling AI models to interpret medical images and ans
Not just foreseeable, but foreseen and called out. We ran a campaign to get them out of the first ever AI Safety Summit. We won that one. Yet most of the field kept licking the boot of the companies a
Gary Marcus expresses concerns that OpenAI's potential IPO performance could signal broader challenges for the company, suggesting their recent success may not be sustainable if market conditions turn
Audi has unveiled the Nuvolari, a limited-production mid-engined plug-in hybrid supercar that will begin deliveries in early 2027 with only 499 units made. The supercar features a twin-turbo 4.0-liter
arXiv:2602.05843v2 Announce Type: replace Abstract: The rapid advancement of Large Language Models (LLMs) has catalyzed the development of autonomous agents capable of navigating complex environments.
arXiv:2606.05255v1 Announce Type: cross Abstract: Oklab and its cylindrical representation Oklch are widely adopted in interpolation and design workflows as perceptually motivated color spaces, but th
arXiv:2606.05234v1 Announce Type: new Abstract: Wearable exoskeleton systems hold promise for restoring mobility in individuals with physical impairments, yet most existing controllers rely on static
arXiv:2606.06080v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards is widely used for post-training reasoning models, but sparse outcome rewards make exploration difficul
arXiv:2606.06260v1 Announce Type: cross Abstract: Generative recommendation models in the OneRec family have been widely deployed in many real-world services, such as short-video, live-streaming, adve
Michael Considine / CNBC: OpenAI confirms it will comply with President Trump's EO that asks AI companies to allow the US government to assess their models' capabilities before release — OpenAI has co
OpenAI Help: Lockdown Mode OpenAI first teased this in February, but now it's live and 'rolling out to eligible personal accounts, including Free, Go, Plus, and Pro, and self-serve ChatGPT Business ac
Igor Bonifacic / Engadget: OpenAI rolls out Lockdown Mode, an optional security setting designed to offer users advanced protection from prompt injection attacks by limiting some features — The compan
Government software is facing the same information management crisis as every other enterprise sector, and the knowledge graph is emerging as the architectural answer. Nickhil Tekwani (pictured, secon
arXiv:2606.06481v1 Announce Type: new Abstract: As AI writing assistants become increasingly integrated into real-world drafting and revision workflows, many documents are no longer purely human-writt
arXiv:2606.05460v1 Announce Type: new Abstract: Abdominal CT disease classification is challenging because each scan is a large 3D volume with many possible findings, while diagnostic evidence is ofte
arXiv:2606.06096v1 Announce Type: cross Abstract: Policy-gradient methods usually optimize expected return, but many real world applications care about distributional properties of returns: tail risk,
arXiv:2110.06847v3 Announce Type: replace Abstract: From work emerging through the middle of the 20th century, the essence of meaning has become widely accepted as being described by the three orthogo
arXiv:2606.06177v1 Announce Type: new Abstract: Speech translation (ST) is increasingly adopted in user applications, yet its evaluation largely focuses on decontextualized testbeds and holistic quali
Charlotte Tobitt / Press Gazette: Over 20 EU news publishers file a claim seeking €640M+ from Google following an EU decision that lets anyone harmed by Google's ad market abuse seek damages — Small p
arXiv:2606.06485v1 Announce Type: new Abstract: Recent advances in 3D multimodal large language models (3D-MLLMs) have enabled unified solutions for 3D scene understanding tasks, including visual ques
arXiv:2606.05703v1 Announce Type: new Abstract: Autoregressive (AR) models have demonstrated remarkable performance in generating high-fidelity images. However, their inherently sequential next-token
arXiv:2605.25970v2 Announce Type: replace Abstract: Clinical pathways are disseminated as visual flowcharts where spatial topology, arrow direction, colour coding, and font weight encode critical tria
arXiv:2503.14295v3 Announce Type: replace Abstract: Recent advancements in audio-driven talking face generation have made great progress in lip synchronization. However, current methods often lack suf
arXiv:2606.05176v1 Announce Type: new Abstract: While large language models (LLMs) show strong performance in natural language understanding and generation, their evaluation and adaptation to domain-s
arXiv:2606.05275v1 Announce Type: new Abstract: We study the personal camera roll visual question answering setting. In this setting, a conversational AI assistant can access a user's personal camera
arXiv:2510.26236v2 Announce Type: replace Abstract: Motion imitation is a promising approach for humanoid locomotion, enabling agents to acquire humanlike behaviors. Existing methods typically rely on
arXiv:2606.05759v1 Announce Type: new Abstract: Hyperspectral imaging provides rich spectral information for quantitative remote sensing, yet hyperspectral sensors remain costly and thus unavailable i
arXiv:2606.06361v1 Announce Type: new Abstract: Image-to-Video diffusion models leverage input images to generate visually stunning content, yet frequently produce motion that violates physical laws.
arXiv:2606.05773v1 Announce Type: new Abstract: Vision-language-action (VLA) policies operate in a closed loop in real-world robot tasks: a robot observes the scene, executes an action chunk, and cond
arXiv:2507.00460v3 Announce Type: replace Abstract: Open Large Language Model (LLM) benchmarks, such as HELM and BIG-Bench, provide standardized and transparent evaluation protocols that support compa