Knowledge catalogue
Maximilian Schreiner / The Decoder: Nvidia launches Nemotron 3 Ultra, a 550B-parameter MoE open model; Artificial Analysis: it's the smartest open US model but trails the Chinese model Kimi K2.6 — It
arXiv:2510.07651v2 Announce Type: replace-cross Abstract: Large language models (LLMs) with extended context windows enable powerful applications but impose significant memory overhead, as caching all
arXiv:2605.30969v1 Announce Type: new Abstract: Text-based human motion editing aims to modify existing motion sequences according to natural language instructions while maintaining the consistency of
arXiv:2605.30544v1 Announce Type: new Abstract: Visual monitoring systems that rely on cloud-based AI inference expose raw image data to external services, creating fundamental tensions with the data-
arXiv:2605.31142v1 Announce Type: cross Abstract: Large-scale multilingual text embedding models play crucial role in both research and industry, yet their behavior in language-specific, multi-task se
One of the big reasons for the current lack of patriotism and pride in our nation’s history is that about 40 years ago our most prominent storytellers in Hollywood just basically stopped telling stori
One of the new, buzzy jobs in Silicon Valley is the AI Forward Deployed Engineer (FDE), an engineer who is embedded within a client organization to help customize solutions, such as building and tunin
OpenAI frontier models and Codex are now generally available on AWS, giving enterprises a new way to build on Amazon Bedrock with OpenAI through the security, compliance, and governance workflows they
OpenAI frontier models GPT-5.5 and GPT-5.4, and Codex, the OpenAI coding agent, are now generally available on Amazon Bedrock. AWS customers can access these latest OpenAI models through the same Amaz
arXiv:2605.30758v1 Announce Type: new Abstract: Pairwise preference data is widely used in language-model evaluation and alignment, often for model ranking, reward modeling, or preference optimization
Aaron Holmes / The Information: Palo Alto Networks says Mythos found 24+ critical bugs using $1M+ in tokens; Anthropic subsidizes Mythos but some companies plan to boost their Mythos budgets — When Pa
arXiv:2602.06902v2 Announce Type: replace Abstract: In this paper, we study dynamic regret in unconstrained online convex optimization (OCO) with movement costs. Specifically, we generalize the standa
arXiv:2605.30512v1 Announce Type: new Abstract: Generating physics diagrams from text requires strict adherence to physical laws. While current generative models produce visually plausible outputs, th
arXiv:2605.30542v1 Announce Type: new Abstract: World models for embodied AI must be physically viable: constructed to answer intervention queries by representing the physical structure governing acti
arXiv:2512.05976v3 Announce Type: replace-cross Abstract: Designing materials with controlled heat flow at the nano-scale is central to advances in microelectronics, thermoelectrics, and energy-conver
arXiv:2605.30639v1 Announce Type: cross Abstract: Embodied agents have made strong progress in navigating to target objects, but reaching the goal vicinity does not guarantee that the agent has found
arXiv:2602.01553v2 Announce Type: replace-cross Abstract: Link prediction is a core challenge in graph machine learning, demanding models that capture rich and complex topological dependencies. While
arXiv:2605.30942v1 Announce Type: new Abstract: Modern vision models process images in a single feed-forward pass, which limits their ability to recover missing evidence or refine uncertain representa
arXiv:2605.31204v1 Announce Type: new Abstract: Accurate weather forecasts are essential across various domains and are safety-critical in extreme weather conditions. Compared to simulation-based fore
arXiv:2605.31196v1 Announce Type: cross Abstract: Safe human--robot collaboration requires more than visual description: a monitor must determine whether the robot body is safely separated, already co
arXiv:2605.30574v1 Announce Type: new Abstract: Prior KV cache compression schemes empirically demonstrate that the prompt cache is partially redundant during decoding, dropping or summarising entries
arXiv:2605.30358v1 Announce Type: new Abstract: Quantum computing remains in the Noisy Intermediate-Scale Quantum (NISQ) era, where the performance is highly constrained to noise. Addressing the limit
arXiv:2601.22068v2 Announce Type: replace Abstract: Foundation models have become a dominant paradigm in machine learning, achieving remarkable performance across diverse tasks through large-scale pre
arXiv:2602.12192v3 Announce Type: replace Abstract: Built upon the existing analysis of retrieval heads in large language models, we propose an alternative reranking framework that trains models to es
arXiv:2605.31124v1 Announce Type: new Abstract: Estimating 3D attributes directly from images has advanced rapidly with the Visual Geometry Grounded Transformer (VGGT), which predicts camera parameter
Vercel has made Qwen 3.7 Plus, an AI model, available through its AI Gateway service, allowing developers to access this model via Vercel's platform. This addition expands the model options available
arXiv:2601.20076v2 Announce Type: replace-cross Abstract: We consider minimizing an objective function subject to constraints defined by the intersection of lower-level sets of convex functions. We st
arXiv:2510.01137v3 Announce Type: replace Abstract: Privacy is a central concern when fine-tuning large language models (LLMs) on sensitive data, and differentially private stochastic gradient descent
Google's I/O 2026 event showcased various AI applications and innovations developed by Google to enhance the conference experience. The post highlights creative implementations of AI technology integr
arXiv:2605.31589v1 Announce Type: new Abstract: While humans naturally gesture during speech, only a sparse subset of these movements are visually depictive and semantically linked to specific spoken
arXiv:2510.02060v2 Announce Type: replace Abstract: In tabular anomaly detection (AD), textual semantics often carry critical signals, as the definition of an anomaly is closely tied to domain-specifi
arXiv:2509.21379v3 Announce Type: replace-cross Abstract: Concept unlearning in diffusion models is hampered by feature splitting, where concepts are distributed across many latent features, making th
arXiv:2605.30854v1 Announce Type: cross Abstract: Language models fine-tuned with reinforcement learning typically optimize for task reward, ignoring multi-agent strategic structure. Because these age
arXiv:2605.30646v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used in clinical applications. However, their behavior remains highly sensitive to subtle linguistic var
arXiv:2602.16682v2 Announce Type: replace Abstract: A core aspect of human perception is situated awareness, the ability to relate ourselves to the surrounding physical environment and reason over pos
arXiv:2605.31469v1 Announce Type: cross Abstract: Conversational automatic speech recognition in Hungarian is constrained by the limited amount of publicly available dialogue-style training data. The
arXiv:2605.31238v1 Announce Type: new Abstract: Endowing large language models with compositional reasoning over specialized documents requires multi-hop training data at scale, where such data rarely
arXiv:2605.31426v1 Announce Type: cross Abstract: Image Scanning Microscopy (ISM) is a fluorescence imaging technique that combines detector-array acquisition and computational reconstruction to achie
arXiv:2605.30837v1 Announce Type: cross Abstract: Prompt-injection detectors are heterogeneous: each is strong on a different slice of attacks, and none is always reliable. Yet existing systems still
arXiv:2509.06856v2 Announce Type: replace-cross Abstract: We propose a novel randomized framework for the estimation problem of large-scale linear statistical models, namely Sequential Least-Squares E
arXiv:2601.05134v2 Announce Type: replace Abstract: Certified unlearning based on differential privacy offers strong guarantees but remains largely impractical: the noisy fine-tuning approaches propos
arXiv:2601.20789v3 Announce Type: replace Abstract: Open-weight coding agents should hold a fundamental advantage over closed-source systems because they can specialize to private codebases, encoding
arXiv:2603.20253v2 Announce Type: replace-cross Abstract: Evaluating LLM agents for scientific tasks has focused on token costs while ignoring tool-use costs like simulation time and experimental reso
arXiv:2605.31408v1 Announce Type: cross Abstract: Skill documents provide procedural knowledge to large-language-model agents at inference time. This article studies whether the presentation granulari
arXiv:2605.30396v1 Announce Type: cross Abstract: 3D Gaussian Splatting (3DGS) is a promising neural scene representation for real-time rendering, but trained models often suffer from large memory foo
So much great work lately from Nvidia, the 'King of American Open-source AI'! - Crossed 1,000 total public repositories on @huggingface (820 models, 249 datasets & 57 spaces) & almost 60,000 followers
arXiv:2605.31330v1 Announce Type: cross Abstract: Institutional incentives are widely used to promote cooperation among autonomous, self-regarding agents, from human societies to multi-agent and AI sy
arXiv:2605.31597v1 Announce Type: new Abstract: Measuring structured object understanding in vision foundation models remains challenging due to inconsistent evaluation protocols and limited part-leve
arXiv:2605.31371v1 Announce Type: new Abstract: Sign-based and LMO-inspired optimizers have recently attracted substantial attention in deep learning due to their strong performance and low memory foo
arXiv:2605.31148v1 Announce Type: cross Abstract: Humans can effortlessly perceive spatial layouts, form cognitive representations, reason about spatial relations, and translate such reasoning into ac
arXiv:2602.22971v2 Announce Type: replace Abstract: As LLMs achieved breakthroughs in general reasoning, their proficiency in specialized scientific domains reveals pronounced gaps in existing benchma
arXiv:2605.31183v1 Announce Type: cross Abstract: Sparse Autoencoders (SAEs) have been seen as a promising avenue for exploring the internals of Large Language Models (LLMs) and for steering model out
arXiv:2605.30383v1 Announce Type: cross Abstract: Scaling individual robot capabilities is common but costly. Here we investigate a system-level design question in real-world multi-robot coordination:
arXiv:2605.31529v1 Announce Type: new Abstract: True video intelligence demands more than recognizing what is visible: it requires reasoning about why events unfold, predicting what would change under
arXiv:2505.17607v3 Announce Type: replace Abstract: Large Language Models (LLMs) display reasoning capabilities over linguistic and symbolic objects but have limited capabilities to directly interpret
arXiv:2605.31156v1 Announce Type: new Abstract: Causal discovery aims to recover directed causal relations from observational and interventional data, providing a basis for mechanistic understanding a
arXiv:2503.21168v3 Announce Type: replace Abstract: Robots navigating human-populated environments must avoid collisions while respecting the social structure of crowds, particularly the implicit boun
arXiv:2508.19830v2 Announce Type: replace-cross Abstract: Real-world model deployments inevitably encounter distribution shifts, rendering the confidence estimates of deep neural networks highly unrel
arXiv:2603.07551v2 Announce Type: replace-cross Abstract: Zero-shot Text-to-Speech (TTS) voice cloning poses severe privacy risks, demanding the removal of specific speaker identities from trained TTS
arXiv:2601.09633v2 Announce Type: replace Abstract: Taxonomies form the backbone of structured knowledge representation across diverse domains, enabling applications such as e-commerce and semantic se