Knowledge catalogue
arXiv:2605.08778v1 Announce Type: new Abstract: Deploying LLMs in multi-turn dialogues facilitates jailbreak attacks that distribute harmful intent across seemingly benign turns. Recent training-based
arXiv:2605.10676v1 Announce Type: new Abstract: During MLLM decoding, attention often abnormally concentrates on irrelevant image tokens. While existing research dismisses this as invalid noise and fo
not every day @scaling01 and I agree. but he’s right. and most people won’t notice it happening, per the work of @informor. hot take: unrestricted LLMs are as dangerous as weapons of mass destruction
arXiv:2605.10061v1 Announce Type: cross Abstract: Futrell and Mahowald (2025) frame the success of neural language models (LMs) as supporting gradient, usage-based linguistic theories. I argue that LM
Gary Marcus references a conversation with someone named Haider, noting that despite Haider's typically optimistic outlook, he has shared documented evidence of expressing concerns about a particular
arXiv:2510.03895v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models represent a pivotal advance in embodied intelligence, yet they confront critical barriers to real-world de
Nous Portal is one easy subscription that gives you access to 300+ models, exclusive discounts, and bundles your tokens and paid tools together for hassle-free setup and simple billing. http://portal.
arXiv:2605.09950v1 Announce Type: cross Abstract: Most feature selection algorithms, especially wrapper methods, run inefficiently on CPU based platforms because of their high computational complexity
arXiv:2602.06382v2 Announce Type: replace Abstract: Achieving robust vision-based humanoid locomotion remains challenging due to two fundamental issues: the sim-to-real gap introduces significant perc
Announced today at SAP Sapphire — where NVIDIA founder and CEO Jensen Huang joined SAP CEO Christian Klein’s keynote by video — SAP and NVIDIA’s expanded collaboration helps enterprises run specialize
CNBC: Nvidia says that Jensen Huang is joining President Trump on his China trip; source: the president asked Huang to join after seeing media coverage of his absence — BEIJING — Nvidia CEO Jensen Hua
arXiv:2605.10155v1 Announce Type: new Abstract: Legal information in India remains largely inaccessible due to the complexity of legal language and the sheer volume of legal documentation involved in
arXiv:2605.09160v1 Announce Type: new Abstract: Learned representations are often invariant to rotational transformations, leaving individual dimensions non-identifiable and interchangeable. We study
arXiv:2605.10707v1 Announce Type: new Abstract: Object-centric view planning is a core component of active geometric 3D reconstruction in robotics, yet existing evaluations often conflate object compl
arXiv:2512.24552v2 Announce Type: replace Abstract: This paper proposes a novel second-order optimization algorithm based on the Optimal Control Principle (OCP), applicable to large-scale optimization
arXiv:2605.09055v1 Announce Type: cross Abstract: Recent agentic-robotics systems, from Code-asPolicies to modern vision-language-action (VLA) foundation models, presuppose that drivers, SDKs, or ROS-
arXiv:2605.09433v1 Announce Type: new Abstract: Existing preference datasets for text-to-image models typically store only the final winner/loser images. This representation is insufficient for rectif
arXiv:2605.08762v1 Announce Type: cross Abstract: Current omni-modal benchmarks mainly evaluate models under settings where multiple modalities are provided simultaneously, while the ability to start
arXiv:2605.09996v1 Announce Type: new Abstract: While multimodal large language models have advanced across text, image, and audio, personalization research has remained primarily vision-language, wit
arXiv:2605.08758v1 Announce Type: cross Abstract: Driven by the rapid expansion of e-commerce and small-batch production, the size of the intralogistics load unit of finished goods, semi-finished good
arXiv:2605.09200v1 Announce Type: new Abstract: We study adversarial noisy bandits given a known function class F. In each round, the adversary selects a function f in F, the learner chooses an arm, a
arXiv:2605.08368v1 Announce Type: new Abstract: Debates about large language model post-training often treat supervised fine-tuning (SFT) as imitation and reinforcement learning (RL) as discovery. But
arXiv:2605.10722v1 Announce Type: new Abstract: Molecular Graph Neural Networks (GNNs) are increasingly common in drug discovery, particularly for Quantitative Structure-Activity Relationship (QSAR) s
arXiv:2605.08400v1 Announce Type: cross Abstract: Dynamics of interacting systems in engineering, society, and nature often evolve over latent networks that govern which entities can interact. We stud
arXiv:2605.10818v1 Announce Type: new Abstract: Periodic signals are critical for representing physical and perceptual phenomena. Scalar, real angular measures, e.g., radians and degrees, result in di
arXiv:2605.09725v1 Announce Type: new Abstract: On-policy distillation (OPD), which supervises a student on its own sampled trajectories, has emerged as a data-efficient post-training method for impro
arXiv:2509.15816v5 Announce Type: replace Abstract: The Muon optimizer has demonstrated remarkable empirical success in handling matrix-structured parameters for training neural networks. However, a s
arXiv:2512.18248v3 Announce Type: replace Abstract: The low-rank adaptation (LoRA) algorithm for fine-tuning large models has grown popular in recent years due to its remarkable performance and low co
arXiv:2605.09606v1 Announce Type: cross Abstract: Recent advances in image-to-3D models have significantly improved the fidelity and accessibility of 3D content creation. Such a powerful reconstructio
arXiv:2605.10775v1 Announce Type: cross Abstract: A surprising phenomenon in the training of neural networks is the ability of gradient descent to find global minimizers of the training loss despite i
arXiv:2601.21619v2 Announce Type: replace-cross Abstract: Parallel thinking improves LLM reasoning through multi-path sampling and aggregation. In standard evaluations, due to a lack of sample-specifi
arXiv:2605.09757v1 Announce Type: new Abstract: Providing non-conservative uncertainty quantification for function estimates derived from noisy observations remains a fundamental challenge in statisti
arXiv:2605.09235v1 Announce Type: cross Abstract: One-step generative modeling has emerged as a leading approach to amortize the inference cost of diffusion and flow-matching models. Among distillatio
SpaceX fueled its new Starship V3 megarocket for the first time, setting a new record as the world's tallest rocket at approximately 408 feet (124.4 meters), surpassing the V2 by 4 feet. The successfu
arXiv:2605.09727v1 Announce Type: cross Abstract: A central challenge in reinforcement learning (RL) is to learn models that generalize beyond the tasks on which they are trained, a goal traditionally
Red Hat Enterprise Linux, the platform underpinning much of enterprise IT, has spent 20 years as the quiet foundation of enterprise computing. Now, as AI moves into production at scale, it’s becoming
arXiv:2605.10179v1 Announce Type: cross Abstract: Neural Flows efficiently model irregular multivariate time series by directly learning ODE solution trajectories with neural networks, bypassing step-
arXiv:2601.22158v3 Announce Type: replace Abstract: Modern diffusion/flow-based models for image generation typically exhibit two core characteristics: (i) using multi-step sampling, and (ii) operatin
arXiv:2505.23617v3 Announce Type: replace-cross Abstract: Effective video tokenization is critical for scaling transformer models for long videos. Current approaches tokenize videos using space-time p
arXiv:2605.09565v1 Announce Type: new Abstract: We consider the problem of learning an unknown subset N_ext{target} of a domain in an online setting. In each round t, the learner predicts a set of ite
arXiv:2605.10572v1 Announce Type: new Abstract: Bayesian optimization (BO) is a widely used framework for optimizing expensive black-box functions, commonly based on Gaussian process (GP) surrogate mo
arXiv:2605.10040v1 Announce Type: new Abstract: The rapid evolution of generative paradigms has enabled the creation of highly realistic imagery, which escalating the risks of identity fraud and the d
arXiv:2605.09184v1 Announce Type: new Abstract: We present Open Ontologies, an open-source ontology engineering system implemented in Rust that integrates LLM-driven construction with formal OWL reaso
OpenAI contacted me to say “Study Mode is still live and accessible via /study and /learn shortcuts” so that’s good, although the official study mode page doesn’t mention that. (I don’t think slash co
Sam Altman's personal investments faced increased scrutiny from Republican lawmakers following reporting by The Wall Street Journal in April regarding potential conflicts of interest. The controversy
arXiv:2603.10165v2 Announce Type: replace-cross Abstract: Every agent interaction generates a next-state signal, namely the user reply, tool output, terminal or GUI state change that follows each acti
arXiv:2605.10484v1 Announce Type: new Abstract: Scene graph alignment establishes object correspondences between two 3D scene graphs constructed from partially overlapping observations. This enables e
Opinion: It is rare for the US public to agree on anything these days. Fear of AI is as close to a national consensus as it gets. A clear majority says that AI will do more harm than good. https://ft.
arXiv:2605.08904v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in reasoning and tool use. However, the fundamental cognitive faculties essential
arXiv:2605.10917v1 Announce Type: new Abstract: We consider anonymous multi-agent path finding (MAPF) where a set of robots is tasked to travel to a set of targets on a finite, connected graph. We sho
arXiv:2511.01292v2 Announce Type: replace-cross Abstract: Pretrained Transformers can perform in-context learning (ICL) from a few demonstrations, but this ability can fail sharply when the test distr
arXiv:2605.08332v1 Announce Type: cross Abstract: Feedback-based adaptive quantum optimization (FALQON) is a promising approach for solving combinatorial problems on noisy intermediate-scale quantum (
arXiv:2605.09454v1 Announce Type: cross Abstract: We study the extit{single-index bandit} problem, where rewards depend on an unknown one-dimensional projection of high-dimensional contexts through an
arXiv:2602.00318v2 Announce Type: replace-cross Abstract: The rise of bot accounts on social media poses significant risks to public discourse. To address this threat, modern bot detectors increasingl
arXiv:2605.09075v1 Announce Type: cross Abstract: Although the Laplace approximation offers a simple route to uncertainty quantification in deep neural networks, its reliance on inverting large Hessia
arXiv:2605.08660v1 Announce Type: new Abstract: In the recent literature, Support Vector Regression (SVR) has been cited as one of the weakest performers on the California Housing benchmark dataset, w
arXiv:2605.08169v1 Announce Type: cross Abstract: Automated culprit identification in surveillance systems is a critical task that requires high accuracy along with computational efficiency for real-t
arXiv:2605.09991v1 Announce Type: new Abstract: Mode connectivity has been widely studied, yet the role of the optimizer remains underexplored. We revisit it through optimizer-induced implicit regular
arXiv:2605.09813v1 Announce Type: cross Abstract: We investigate the control and optimization of vertical federated learning (VFL), a class of distributed machine learning (ML) methods in which edge/f
arXiv:2605.09822v1 Announce Type: cross Abstract: We define Oracle Poisoning, an attack class in which an adversary corrupts a structured knowledge graph that AI agents query at runtime via tool-use p