Knowledge catalogue
arXiv:2605.18224v1 Announce Type: cross Abstract: This note studies exact constant collapse in variational autoencoders, where the encoder mean becomes independent of the input. The goal is to make th
arXiv:2508.14422v4 Announce Type: replace-cross Abstract: This paper introduces a dimension-decomposed geometric learning framework called Sliced Learning for disturbance identification in quadrotor g
arXiv:2605.16315v1 Announce Type: cross Abstract: We show that a threshold in decision capacity determines whether self-play reinforcement learning agents collapse under asymmetric rule perturbations.
arXiv:2505.06907v2 Announce Type: replace Abstract: The rise of large language models (LLMs), such as ChatGPT, Gemini, and Grok, has reshaped the AI landscape. As prominent instances of foundational m
arXiv:2511.11934v3 Announce Type: replace-cross Abstract: We present a systematic benchmark of out-of-distribution (OOD) detection CSFs through a representation-centric lens. Our study spans CNN and V
arXiv:2605.17131v1 Announce Type: cross Abstract: Point cloud stands as the most widely adopted format for representing 3D shapes and scenes due to its simplicity and geometric fidelity. However, its
arXiv:2605.16430v1 Announce Type: cross Abstract: Scaling LLMs requires tremendous computational resources, and recent advances in AI have gone hand in hand with massive amounts of capital expenditure
arXiv:2605.17808v1 Announce Type: new Abstract: We develop a unified theoretical framework for data-free one-step sampling from unnormalized target distributions based on Wasserstein gradient flows. F
arXiv:2605.18250v1 Announce Type: cross Abstract: Many dynamical systems can be described in terms of structured flows combining source/sink behavior, cyclic dynamics, and topology-constrained transpo
arXiv:2504.14820v2 Announce Type: replace Abstract: For peg-in-hole tasks, humans rely on binocular visual perception to locate the peg above the hole surface and then proceed with insertion. This pap
arXiv:2605.17278v1 Announce Type: new Abstract: Abstract reasoning ability reflects the intelligence and generalization capacity of LLMs to extract and apply abstract rules. However, accurately measur
arXiv:2408.17352v2 Announce Type: replace-cross Abstract: Automatic Speaker Verification (ASV) systems, which identify speakers based on their voice characteristics, have numerous applications, such a
arXiv:2605.17413v1 Announce Type: cross Abstract: Safety-aligned language models often refuse cybersecurity requests whose wording resembles misuse, even when the task is authorized and defensive. Thi
arXiv:2605.17809v1 Announce Type: new Abstract: This research addresses the challenges inherent in developing Artificial Intelligence (AI) applications, particularly those leveraging Large Language Mo
arXiv:2510.07195v2 Announce Type: replace-cross Abstract: Fault-tolerant Quantum Processing Units (QPUs) promise to deliver exponential speed-ups in select computational tasks, yet their integration i
arXiv:2605.16789v1 Announce Type: new Abstract: Diffusion and rectified flow (RF) models generate high-fidelity images and videos, but their iterative velocity-field evaluations are computationally ex
arXiv:2605.17546v1 Announce Type: cross Abstract: Understanding galaxy morphology evolution across cosmic time requires models that can generate realistic galaxy populations conditioned on redshift. I
arXiv:2605.16299v1 Announce Type: cross Abstract: Large Language Models (LLMs) excel at code generation but remain heavily reliant on large-scale annotated solutions and verification-based supervision
arXiv:2310.07983v5 Announce Type: replace Abstract: The ProxSkip algorithm for distributed optimization is gaining increasing attention due to its effectiveness in reducing communication. However, exi
arXiv:2605.17088v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have shown that Chain-of-Thought (CoT) reasoning can substantially improve performance on complex reason
arXiv:2503.12181v4 Announce Type: replace Abstract: Online planning in continuous state, action, and observation spaces remains challenging for autonomous systems. While Monte Carlo Tree Search (MCTS)
arXiv:2605.18743v1 Announce Type: new Abstract: Inspired by the emergent behaviors in large language models that generalized human intelligence, the research community is pursuing similar emergent cap
arXiv:2510.04309v3 Announce Type: replace Abstract: Controlling the behaviors of large language models (LLM) is fundamental to their safety alignment and reliable deployment. However, existing steerin
arXiv:2605.17234v1 Announce Type: new Abstract: Predicting model performance at larger scales enables the design of training strategies and architectures tailored to specific performance targets. Empi
arXiv:2605.17950v1 Announce Type: new Abstract: Robotic systems are vulnerable to False Data Injection Attacks (FDIAs), where adversaries corrupt sensor signals to gain malicious control. Feedback lin
arXiv:2601.16287v3 Announce Type: replace-cross Abstract: Active learning for photonic crystals explores the integration of analytic approximate Bayesian last layer neural networks (LL-BNNs) with unce
arXiv:2605.16320v1 Announce Type: cross Abstract: We present AdaGraph, a graph-native clustering algorithm born from the Structure-Centric Machine Learning (SC-ML) paradigm -- a new field of unsupervi
arXiv:2503.02170v2 Announce Type: replace-cross Abstract: Domain shift remains a persistent challenge in deep-learning-based computer vision, often requiring extensive model modifications or large lab
arXiv:2602.02236v4 Announce Type: replace-cross Abstract: We study online fine-tuning of pretrained control policies for autonomous driving using Real-Time Recurrent Reinforcement Learning (RTRRL), a
arXiv:2510.04382v2 Announce Type: replace-cross Abstract: Even though more than 30 years have passed since the seminal Rudin--Osher--Fatemi (ROF) paper on total variation (TV) denoising, it remains re
arXiv:2605.18459v1 Announce Type: new Abstract: Adaptive experimentation enables efficient estimation of causal effects, but existing methods are not designed for survival data with censoring, where e
arXiv:2605.16817v1 Announce Type: cross Abstract: Learned image compression has achieved competitive rate-distortion performance, but very-low-bitrate reconstruction remains difficult because the tran
arXiv:2605.17609v1 Announce Type: new Abstract: Many inference-time language-model pipelines combine a cheap reward signal with an expensive verifier, such as exact answer checking in mathematical rea
arXiv:2605.17923v1 Announce Type: cross Abstract: In video generation models, particularly world models, training large-scale video diffusion Transformers (such as DiT and MMDiT) poses significant com
arXiv:2601.09722v2 Announce Type: replace-cross Abstract: In this work, we present an annotation framework that demonstrates how a multilingual LLM pretrained on a large corpus can be used as a teache
arXiv:2605.17380v1 Announce Type: new Abstract: We present the Agentic AI Detection and Response (ADR) system, the first large-scale, production-proven enterprise framework for securing AI agents oper
arXiv:2605.18733v1 Announce Type: new Abstract: Autoregressive video generation has improved rapidly in visual fidelity and interactivity, but it still suffers from long-term inconsistency and memory
arXiv:2510.03879v3 Announce Type: replace-cross Abstract: Translating C to memory-safe languages, like Rust, prevents critical memory safety vulnerabilities that are prevalent in legacy C software. Ev
arXiv:2510.10140v2 Announce Type: replace Abstract: Deep learning-based weather forecasting (DLWF) models leverage past weather observations to generate future forecasts, supporting a wide range of do
arXiv:2605.16993v1 Announce Type: cross Abstract: Current clinical artificial intelligence (AI) systems are evaluated almost exclusively on clean, standardised, English-language inputs, conditions tha
arXiv:2605.17517v1 Announce Type: new Abstract: Recent advances in Vision-Language-Action (VLA) models have shown strong potential for general-purpose robotic manipulation. However, the visual represe
arXiv:2605.17698v1 Announce Type: new Abstract: The deployment of Large Language Models (LLMs) as autonomous economic agents introduces systemic risks that extend beyond individual capability failures
arXiv:2602.03955v2 Announce Type: replace Abstract: While large language model (LLM) multi-agent systems achieve superior reasoning performance through iterative debate, practical deployment is limite
arXiv:2601.15630v2 Announce Type: replace Abstract: Healthcare organizations are beginning to embed agentic AI into routine workflows, including clinical documentation support and early-warning monito
arXiv:2605.17041v1 Announce Type: cross Abstract: We present Agentic AI Translate, an agentic translator prototype that operationalises the thesis of Yamada (forthcoming) -- that the metalanguage of T
arXiv:2605.17903v1 Announce Type: new Abstract: We automatically generate feedback causal fuzzy cognitive maps (FCMs) from text by teaching large-language-model agents to break the text into overlappi
arXiv:2605.17831v1 Announce Type: new Abstract: Query optimization in big data analytics remains computationally expensive, particularly for resource-constrained environments where traditional optimiz
arXiv:2605.16419v1 Announce Type: cross Abstract: Kinematic monitoring plays a critical role in long-term rehabilitation for patients with spinal cord injury (SCI), where multi-view markerless motion
arXiv:2605.16819v1 Announce Type: cross Abstract: GPU kernel optimization is increasingly critical for efficient deep learning systems, but writing high-performance kernels still requires substantial
arXiv:2605.17746v1 Announce Type: new Abstract: AI systems are becoming active participants in organizational and knowledge work. They increasingly interact with humans, coordinate workflows, and oper
arXiv:2605.17583v1 Announce Type: new Abstract: While existing text-to-speech (TTS) models exhibit high expressiveness, fine-grained control over composite instructions remains challenging due to the
arXiv:2605.16265v1 Announce Type: new Abstract: The safety of autonomous AI agents is increasingly recognized as a critical open problem. As agents transition from passive text generators to active ac
arXiv:2511.23253v3 Announce Type: replace Abstract: Recent advancements in Vision-Language Models (VLMs) have significantly impacted various industries. In agriculture, these multimodal capabilities h
arXiv:2605.17634v1 Announce Type: cross Abstract: Prompt injection is the most critical vulnerability in deployed AI agents. Despite recent progress, we show that the prevailing defense paradigm (data
arXiv:2602.20042v2 Announce Type: replace Abstract: General Alignment has improved average-case helpfulness and safety, but current alignment practice still rewards confident, single-turn responses. T
arXiv:2605.18661v1 Announce Type: new Abstract: AI-assisted research is crossing a threshold: fully automated systems can now generate research papers for as little as $15, while long-horizon agents c
arXiv:2605.16291v1 Announce Type: cross Abstract: With the growing adoption of AI systems, reasoning about how society can exert control over AI becomes an increasingly urgent problem. Existing work o
arXiv:2605.16275v1 Announce Type: cross Abstract: Artificial intelligence (AI) retrieval-augmented generation (RAG) tools now enable educators to transform course materials into diverse multimedia at
arXiv:2605.18476v1 Announce Type: cross Abstract: Coding and computation remain major bottlenecks in Markov chain Monte Carlo (MCMC) workflows, especially as modern sampling algorithms have become inc
arXiv:2605.16905v1 Announce Type: cross Abstract: Post-hoc saliency methods are widely used to interpret deep neural networks, but their faithfulness is difficult to evaluate reliably. Existing evalua