Knowledge catalogue
arXiv:2605.22816v1 Announce Type: cross Abstract: Vision-and-Language Navigation (VLN) requires an agent to ground language instructions to its own movement within a visual environment. While state-of
This talk from an AWS User Group Malaysia event covers practical experience and insights on building an AI Agent Harness, likely discussing architecture patterns, implementation challenges, and best p
llama.cpp build b9276 introduces support for hybrid DNA tokenization with new pre-type dispatching and tokenizer implementations, alongside fixes for VRAM leaks in Multi-Token Prediction (MTP) models
Release b9283 of llama.cpp includes updates to the BPE tokenizer with new pre-type dispatch and Carbon-3B DNA tokenizer support, along with refactoring of tokenizer helpers to follow project conventio
B9286 introduces support for HybridDNATokenizer as its own vocabulary type (LLAMA_VOCAB_TYPE_HYBRIDDNA), enabling proper tokenization of DNA sequences by routing raw text through a DNA-aware splitter
Release b9292 of llama.cpp fixes a memory leak in the server context where speculative decoder, draft context, and draft model were not properly freed during destroy(), causing VRAM leaks on sleep/res
babyagi has ~200 citations, but 0 papers... i just published my first paper on arXiv 😆 'The Log is the Agent: Event-Sourced Reactive Graphs for Auditable, Forkable Agentic Systems' https://arxiv.org/a
arXiv:2605.22169v1 Announce Type: new Abstract: Deep learning models, including Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs), have achieved state-of-the-art performance on vario
NASA is in the early stages of identifying what small parts of the International Space Station to bring back to Earth before its scheduled deorbit around 2030 . As the station descends through the atm
arXiv:2605.21728v1 Announce Type: cross Abstract: Image captioning evaluation remains a significant challenge, as vision-language models evolve toward more challenging capabilities such as generating
arXiv:2605.22501v1 Announce Type: new Abstract: Despite recent progress, Biomedical Entity Linking (BEL) with large language models (LLMs) remains computationally inefficient and challenging to deploy
arXiv:2605.22344v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) and diffusion models have each reached remarkable maturity: MLLMs excel at reasoning over heterogeneous multimo
arXiv:2605.22732v1 Announce Type: cross Abstract: We investigate whether acoustic emotion recognition models can serve as proxies for the Pathos dimension in political speech analysis, as operationali
arXiv:2603.14987v2 Announce Type: replace Abstract: Agentic AI systems increasingly act through tool-augmented, multi-step workflows whose failures (unsafe tool use, unauthorised actions, social harm)
arXiv:2605.22578v1 Announce Type: new Abstract: Online map estimation is a crucial component of autonomous driving systems that reduces the reliance on costly high-definition maps. State-of-the-art (S
arXiv:2605.22164v1 Announce Type: cross Abstract: Latent world models can contain the state needed for control, yet their terminal-cost interface can expose the planner to the wrong decision-relevant
arXiv:2605.22123v1 Announce Type: new Abstract: Designing reward functions that generalize beyond controlled laboratory settings remains a fundamental challenge in reinforcement learning for robotics.
arXiv:2605.22579v1 Announce Type: new Abstract: Recent work has identified a counterintuitive phenomenon termed 'Hyperfitting', where fine-tuning Large Language Models (LLMs) to near-zero training los
Big fan of teaching more people the basics of using Claude Code in an accessible way. So much of the world has not yet used agents. There's a lot of opportunity to level the playing field and expand a
Bitwarden is a password manager and secrets management solution that integrates with Nous Research's systems, likely enabling secure storage and retrieval of credentials and sensitive information for
arXiv:2605.22001v1 Announce Type: cross Abstract: Injection detectors deployed to protect LLM agents are calibrated on static, template-based payloads that announce themselves as override directives.
United Kingdom-based Blockchain.com Group Holdings Inc., a cryptocurrency exchange and wallet service, announced Thursday that it has filed confidentially for an initial public offering in the United
arXiv:2605.21766v1 Announce Type: new Abstract: Being able to relight human performance is a fundamental task for post production and content creation. We present BodyReLux, a subject-specific video d
arXiv:2605.22643v1 Announce Type: new Abstract: Background. Traditional safety benchmarks for language models evaluate generated text: whether a model outputs toxic language, reproduces bias, or follo
arXiv:2605.22373v1 Announce Type: cross Abstract: Safety classifiers are essential safeguards within generative AI systems, filtering harmful content or identifying at-risk users when interacting with
arXiv:2605.21957v1 Announce Type: new Abstract: Video anomaly detection is critical for public safety and security, yet remains highly challenging despite extensive research due to large variations in
arXiv:2605.22600v1 Announce Type: new Abstract: Motion planning for autonomous driving must account for multi-modal uncertainty in both the intentions and trajectories of surrounding vehicles. Handlin
Brand new episode of Max Agency ⤵️ Great conversation on the Max Agency podcast with @cogent_security Co-Founder + CTO Geng Sng on building agents for autonomous cyber defense. Check out the full epis
BREAKING: @eliasxreyes just hit #1 on Unicorne's fastest-growing startups leaderboard with Dial Moments. +343% growth, backed by verified revenue data from TrustMRR (@marclou). Built with @Replit over
arXiv:2605.21712v1 Announce Type: new Abstract: Transportation safety analysis requires integrating crash records, roadway attributes, and geospatial data through GIS-based workflows, but access remai
arXiv:2605.22050v1 Announce Type: new Abstract: While diffusion models excel at generating high-quality images, their tendency to memorize training data poses significant privacy and copyright risks.
Bumblebee started as an internal tool. Making Perplexity products more secure for users starts with protecting the developer systems we use to build them. Read the full blog: https://www.perplexity.ai
California is trying to prepare itself for artificial intelligence job disruption ahead of time. Governor Gavin Newsom today ordered state officials to begin exploring a massive overhaul of its labor
arXiv:2605.22819v1 Announce Type: new Abstract: Camera pose matters. The position and orientation of each viewpoint define a shared spatial coordinate frame that relates observations across video fram
arXiv:2602.06676v4 Announce Type: replace Abstract: Fake Image Detection (FID), aiming at unified detection across four image forensic subdomains, is critical in real-world forensic scenarios. Compare
arXiv:2605.22547v1 Announce Type: new Abstract: Deep learning has brought significant progress to medical image classification, yet most existing methods still rely on isolated visual evidence and can
Validin, a data-intensive company, adopted Vultr's cloud infrastructure services to meet its high computational demands while achieving significant cost reductions of hundreds of thousands of dollars
The Dialogues stage at Google I/O 2026 brought together Google leaders, scientific minds and creative visionaries to discuss technological breakthroughs. Featured discussions included AI agents and pr
arXiv:2602.02214v3 Announce Type: replace Abstract: To achieve real-time interactive video generation, current methods distill pretrained bidirectional video diffusion models into few-step autoregress
arXiv:2605.20923v1 Announce Type: cross Abstract: Distributed LLM agent workflows should not be monitored as if they produced a single sequential log. In an asynchronous execution, a decision can only
This post from RC Lens celebrates their supporters or team achievements as an artistic masterpiece, using a French pun connecting 'Œuvre d'Art' (artwork) with 'Artésiens' (residents of Artois, the reg
arXiv:2605.22563v1 Announce Type: new Abstract: Training Deep Neural Networks for tracking individual cells in biomedical videos requires a large amount of annotated data. The annotation of videos for
arXiv:2601.23086v2 Announce Type: replace Abstract: Chain-of-thought (CoT) reasoning provides a significant performance uplift to LLMs by enabling planning, exploration, and deliberation of their acti
arXiv:2605.22005v1 Announce Type: cross Abstract: We show that singular value decomposition of the lm_head} weight matrix of a transformer-based large language model -- requiring only five lines of Py
Reuters: China's Wingtech files a lawsuit against Nexperia, saying its control over the Dutch chipmaker remained restricted, and seeks ~$1.2B for economic losses — China's Wingtech Technology (600745.
arXiv:2605.22616v1 Announce Type: new Abstract: Understanding how conceptual knowledge is grounded in bodily experience, and to what extent machine systems can acquire such knowledge without direct se
arXiv:2605.22734v1 Announce Type: new Abstract: Biomedical knowledge graphs (KGs) treat disease associations as static facts, but temporal information is crucial for clinical reasoning, e.g., a sympto
arXiv:2505.16416v3 Announce Type: replace Abstract: Rotary Position Embedding (RoPE) is widely adopted in large language models, but when applied to vision-language models (VLMs) it couples text and i
arXiv:2605.21949v1 Announce Type: new Abstract: Medical RAG systems in high-risk QA settings are often evaluated through a single answer-or-abstain decision, but mixed evidence may support one claim,
Closed and gated surveillance economy SaaS systems and models will get replaced by open source in two tiers: - The models themselves - The everything-ultra-app harness If an American open source champ
arXiv:2605.21688v1 Announce Type: new Abstract: Autonomous contact-based micromanipulation is challenging because surface and interfacial interactions at the microscale are difficult to model accurate
CNBC: 'When you look at the SpaceX prospectus, what do you see in it that sounds fantastical… but you might think is real based on what you've seen accomplished at this point?'https://x.com/ElonClipsX
arXiv:2605.20618v1 Announce Type: new Abstract: Although Vehicle Routing Problems (VRP) are essential to many real-world systems, they remain computationally intractable at scale due to their combinat
arXiv:2605.22068v1 Announce Type: new Abstract: We formalize and enable the task of open tree decomposition, which segments an image into hierarchical trees of visual components with unconstrained gra
arXiv:2506.11060v2 Announce Type: replace-cross Abstract: Large Language Model (LLM)-based coding agents have shown promising results on coding benchmarks, but their effectiveness on systems code rema
arXiv:2605.20519v1 Announce Type: cross Abstract: Prior attacks on Audio Large Language Models (Audio LLMs) demonstrated that carefully crafted waveform-domain perturbations can force targeted adversa
Cohere Command A+ is now available in Microsoft Foundry as a Managed Compute offer. Cohere’s latest open-source model is built for enterprise-grade agentic AI workloads, bringing together reasoning, m
arXiv:2605.22447v1 Announce Type: new Abstract: The study of online discourse has become central to understanding societal polarization. While much research has focused on detecting overt toxicity, th
arXiv:2605.21845v1 Announce Type: new Abstract: Suicide is a leading cause of death in the United States, and understanding the circumstances that precede it requires extracting structured information
arXiv:2605.22679v1 Announce Type: new Abstract: Vision-language models learn powerful multimodal embeddings, yet their internal semantics remain opaque. While sparse autoencoders (SAEs) can extract in