Knowledge catalogue
arXiv:2609.33323v1 Announce Type: cross Abstract: Recent advances in Large Language Models (LLMs) have enabled agentic systems capable of solving complex tasks through multi-turn planning, tool use, v
An agentic security strategy must account for software that can act on legitimate instructions in unexpected ways. Agents can use credentials, call tools and choose their own routes toward a goal, exp
arXiv:2609.31713v1 Announce Type: new Abstract: As large language models (LLMs) become capable of processing increasingly diverse modalities and longer temporal contexts, an emerging line of work is m
arXiv:2609.34683v1 Announce Type: new Abstract: The optimization of LLM serving engines, such as vLLM and SGLang, is largely benchmark-driven: optimizations, scheduling policies, hardware and system d
arXiv:2609.34586v1 Announce Type: cross Abstract: Deploying LLM-enabled agentic applications across the Edge-to-Cloud continuum remains challenging due to hardware heterogeneity, deployment complexity
arXiv:2609.34176v1 Announce Type: new Abstract: Radiance fields need hundreds of views, and their placement matters as much as their number. Next-best-view (NBV) selection for 3D Gaussian Splatting (3
arXiv:2609.32478v1 Announce Type: cross Abstract: We study smoothed online prediction with bounded adversarial responses. This widely studied framework bridges i.i.d. sampling and adversarial covariat
arXiv:2609.34823v1 Announce Type: new Abstract: Augmented dexterity has the potential to reduce the fatigue experienced by surgeons during repetitive surgical tasks. In this paper, we propose the firs
arXiv:2609.35490v1 Announce Type: new Abstract: Generalist multitasking vision models aim to unify multiple vision tasks within a single framework, enabling more efficient and versatile learning. Howe
AI agent identity security is testing whether consolidated platforms can protect a growing class of machine identities. Palo Alto Networks Inc.’s acquisition of CyberArk Software Ltd. reflects broader
arXiv:2609.33522v1 Announce Type: cross Abstract: Manual visual inspection on assembly lines is a persistent manufacturing bottleneck: operator fatigue over extended shifts lowers defect-detection rat
arXiv:2509.01019v3 Announce Type: replace Abstract: Coral reefs are on the brink of collapse, with climate change, ocean acidification, and pollution leading to a projected 70-90% loss of coral specie
arXiv:2511.11257v2 Announce Type: replace-cross Abstract: The rational discovery of functional solvents remains challenging because macroscopic solvent behaviors emerge from complex many-body interact
NVIDIA TensorRT Model Connect is an open‑source library that delivers AI model reference implementations in C++ built on top of NVIDIA TensorRT, designed to make the inference stack accessible to deve
'The chance of human extinction is about a coin flip, in my view,' Geoffrey Irving, a former OpenAI and Google DeepMind employee, said in a new interview. It's one of a dozen interviews with AI resear
arXiv:2609.35257v1 Announce Type: new Abstract: Zeroth-order (ZO) optimization offers a memory-efficient alternative for LLM fine-tuning by estimating updates only from forward evaluations of perturbe
arXiv:2609.33728v1 Announce Type: new Abstract: Reliable world models should not only predict future states but express how actions change the world in an explicit, transparent and testable form, such
arXiv:2609.33073v1 Announce Type: new Abstract: In this work, we consider algorithmic harms that may arise as generative models are incorporated into machine learning platforms. We argue that existing
arXiv:2609.34962v1 Announce Type: new Abstract: Estimating mutual information (MI) from samples is a central objective in a variety of scientific fields. Modern neural estimators are accurate in the l
arXiv:2510.14391v3 Announce Type: replace-cross Abstract: Recent neural beat trackers predict beats and downbeats with two independent frame-wise binary classification heads, a convention adopted beca
arXiv:2609.34467v1 Announce Type: new Abstract: Recent advances in Vision-Language-Action (VLA) models point toward general-purpose robotic intelligence by unifying perception, instruction, and contro
arXiv:2602.03902v2 Announce Type: replace-cross Abstract: G-protein-coupled receptors (GPCRs), which are targeted by over one-third of approved drugs, undergo intricate conformational transitions to t
arXiv:2609.32317v1 Announce Type: cross Abstract: As AI models grow in size and usage, their energy demands increase dramatically, raising sustainability and economic concerns. Neuromorphic hardware,
arXiv:2609.32913v1 Announce Type: new Abstract: Recent progress in frontier models has renewed interest in large-scale reinforcement learning (RL), but the cost of generating large-model rollouts make
arXiv:2609.34188v1 Announce Type: cross Abstract: Formulaic alpha discovery is a core challenge in quantitative trading, as identifying alphas that work well together remains difficult. Recent reinfor
arXiv:2609.32527v1 Announce Type: cross Abstract: Predicting cellular responses to genetic perturbations helps prioritize experiments in single-cell genomics, where exhaustive measurement is infeasibl
arXiv:2609.33484v1 Announce Type: new Abstract: A humanoid with 5-DoF arms cannot track generic bimanual end-effector trajectories with its arms alone; pelvis and waist motion must be recruited, but w
arXiv:2609.32041v1 Announce Type: new Abstract: Modern Document AI reads contracts, extracts fields, reasons over tables, and grounds answers to page regions, then forgets everything. Processing an am
arXiv:2609.33835v1 Announce Type: cross Abstract: Weak-to-strong generalization (W2SG) occurs when a student trained on a teacher's predictions outperforms that teacher. We study when this happens und
arXiv:2609.35466v1 Announce Type: new Abstract: Soft Actor-Critic (SAC) is widely used for entropy-regularised reinforcement learning with continuous action spaces, and practical implementations perfo
arXiv:2609.32106v1 Announce Type: new Abstract: The global transition to a cashless economy has placed credit cards as the key element of digital transactions, acclaimed for their easy use, speed, and
arXiv:2509.05213v2 Announce Type: replace Abstract: This work addresses the key challenges of applying federated learning to large-scale deep neural networks, particularly the issue of client drift du
arXiv:2609.32762v1 Announce Type: cross Abstract: Visual imitation learning is a promising approach to training robot manipulation policies capable of completing a wide variety of tasks. However, poli
arXiv:2609.32376v1 Announce Type: new Abstract: Iterative generation poses a joint optimization problem across steps, as intermediate predictions shape subsequent computations and ultimately determine
arXiv:2604.07666v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) is widely used for post-training Large Language Models, but practical verifiers can make error
arXiv:2609.35437v1 Announce Type: cross Abstract: Quantitative characterization of lymph node morphology is important for assessing axillary lymph node metastasis in breast cancer. However, surfaces r
arXiv:2609.35505v1 Announce Type: new Abstract: We study on-policy distillation (OPD) through the lens of reinforcement learning, establishing a connection between the reverse-KL objective in OPD and
arXiv:2609.31933v1 Announce Type: cross Abstract: Native-latent guidance is a recent paradigm for solving inverse problems with latent diffusion models. It replaces repeated evaluations of the image-s
arXiv:2609.32350v1 Announce Type: new Abstract: Predictive coding (PC) is a local, energy-based alternative to backpropagation (BP) whose iterative inference dynamics make it attractive for implementa
arXiv:2609.32178v1 Announce Type: new Abstract: Rotary position encodings make attention sensitive to relative position, but extending them to graphs requires choosing how graph structure enters the r
arXiv:2609.34142v1 Announce Type: new Abstract: Continuous video analytics requires accurate localization at low latency within embedded power budgets. This paper presents a hardware-software design m
arXiv:2609.33520v1 Announce Type: new Abstract: Weakly-supervised thoracic disease detection in chest X-rays (CXR) is challenging due to subtle appearances and complex anatomical overlap, motivating a
arXiv:2609.32764v1 Announce Type: new Abstract: Detecting distributed denial-of-service (DDoS) attacks in cloud-integrated IoT networks is difficult when labeled traffic is scarce. Generative semi-sup
arXiv:2609.32602v1 Announce Type: new Abstract: Adversarial attacks optimized on a single open-weight LLM can transfer to and jailbreak architecturally different models, allowing an attacker with whit
arXiv:2609.32740v1 Announce Type: new Abstract: Intraoperative anesthesia requires systems to interpret evolving multimodal evidence, recommend timely management, and revise decisions as patient state
arXiv:2609.33611v1 Announce Type: new Abstract: Dynamic contrast-enhanced breast MRI (DCE-MRI) is rich in anatomical and perfusion information, but its reliance on gadolinium-based contrast agents rai
arXiv:2609.33814v1 Announce Type: cross Abstract: We characterize Bregman Douglas-Rachford splitting (BDRS) for unregularized discrete optimal transport and develop an anytime primal-dual certificate
arXiv:2609.35247v1 Announce Type: new Abstract: When a VLM answers a visual query, current interpretability tools rely on text rationales, which use a mismatched modality, or on internal read-outs, wh
Anthropic: Anthropic says GLM-5.3 can autonomously build end-to-end cyber exploits, like Claude Mythos Preview, but was released without robust safeguards against misuse — GLM-5.3 can develop working
Opus 5.5 dropped em dashes from 12.9 per 1,000 words to two in 57,000 words, and cut the rest of the Claudisms in half. Better, but not fixed. The post Anthropic says it fixed Claude’s writing. I ran
As Anthropic gears up for its greatly anticipated public debut, a preview of the company's IPO filing reportedly details its mounting losses, leadership proposals to retain power, and how its AI devel
In its pending IPO prospectus, Anthropic disclosed that advancing AI models could pose “existential risks to humanity,” highlighting potential for unintended behaviors such as manipulation and blackma
arXiv:2609.33748v1 Announce Type: new Abstract: World-action models (WAMs) couple predictive visual modeling with action generation, typically relying on iterative denoising with a fixed denoising ste
arXiv:2609.32248v1 Announce Type: new Abstract: Large language model (LLM) leaderboards compare model capabilities by ranking models according to their mean performance on fixed benchmarks. However, v
arXiv:2609.33371v1 Announce Type: cross Abstract: Tool-using large language model (LLM) agents turn credential hygiene from a storage problem into an execution-security problem. A key pasted into a pr
arXiv:2609.33193v1 Announce Type: new Abstract: How many directions in weight space does training need? The intrinsic dimension answers this with the smallest number of random directions in which trai
arXiv:2609.33586v1 Announce Type: new Abstract: On NVIDIA Blackwell B200, tensor-core throughput outpaces special-function exponential throughput by more than two orders of magnitude, exposing exponen
arXiv:2609.32156v1 Announce Type: cross Abstract: Safe underwater exploration requires a robot to understand where surrounding structures are located and which regions are available for motion. Existi
arXiv:2609.33299v1 Announce Type: new Abstract: World Action Models (WAMs) are becoming increasingly important and useful for embodied intelligence, as they enable robots to anticipate the consequence
arXiv:2609.35628v1 Announce Type: new Abstract: We study the minimum number of hidden neurons required for arbitrary-accuracy approximation of multivariate Holder-continuous functions on [0,1]^d and t