Knowledge catalogue
arXiv:2606.06345v1 Announce Type: new Abstract: Brain decoding is limited by the availability of labeled neural data, and remains challenging in low-data regimes. To address this issue, we investigate
arXiv:2603.16475v2 Announce Type: replace Abstract: In schema-guided reasoning (SGR) pipelines, LLMs produce explicit intermediate structures -- rubrics, checklists, or verification queries -- before
David Sarnoff (1891-1971) rose from Russian Jewish immigrant office boy to president/chairman of RCA. He drove commercial radio, founded NBC, and heavily funded early electronic TV development. Simila
arXiv:2606.05863v1 Announce Type: cross Abstract: Grokking suggests that fitting the training data and learning a simple underlying rule may occur on different time scales. We formalize this phenomeno
arXiv:2606.05584v1 Announce Type: cross Abstract: High-dimensional feature representations are widely used in machine learning-based cyberattack detection systems. However, they increase computational
arXiv:2606.06357v1 Announce Type: cross Abstract: Continuous audio autoencoders reconstruct waveforms well but often produce latents with weak structure for understanding, while self-supervised audio
arXiv:2606.05199v1 Announce Type: cross Abstract: The identification of constitutive neural network models from heterogeneous full-field deformation data provides a robust alternative to traditional c
arXiv:2606.05602v1 Announce Type: new Abstract: AI assistants in human-AI collaboration often correct suboptimal human actions through behavioral feedback (e.g., alerts or steering-wheel nudges in ass
arXiv:2606.05326v1 Announce Type: cross Abstract: We study the dynamics of gradient descent in the Edge of Stability regime, where the learning rate is large enough to induce persistent oscillations i
arXiv:2606.05219v1 Announce Type: cross Abstract: Recent analyses of multi-pathway Deep Linear Networks use Gradient Flow to predict a 'winner-takes-all' specialization in which path symmetry breaks a
arXiv:2606.05770v1 Announce Type: cross Abstract: AI is changing how software engineers work, but it often comes with hidden burdens and costs. In this paper, we characterize two such often-overlooked
arXiv:2606.05391v1 Announce Type: cross Abstract: Autonomous software agents hold promise to increase developer productivity but make mistakes and exhibit novel failure modes, making human oversight c
arXiv:2606.06094v1 Announce Type: new Abstract: Advances in computational modeling, neuroimaging, and artificial intelligence are revolutionizing the modeling of neurological disorders for improved di
arXiv:2410.02628v5 Announce Type: replace-cross Abstract: Learning conditional distributions pi^*(dot|x) is a central problem in machine learning, which is typically approached via supervised methods
arXiv:2606.06159v1 Announce Type: cross Abstract: Spiking neural networks (SNNs) have the potential to emerge as the third generation of neural networks and have attracted increasing attention across
arXiv:2601.19568v2 Announce Type: replace Abstract: Code localization constitutes a key bottleneck in automated software development pipelines. While concurrent tool execution can enhance discovery sp
arXiv:2606.06315v1 Announce Type: new Abstract: Recent advances in interpretability suggest that large language models (LLMs) implicitly encode signals in their generated text that enable self-recogni
arXiv:2606.06056v1 Announce Type: cross Abstract: Multiple machine learning models can achieve near-equivalent predictive performance on the same task, yet provide divergent feature-based explanations
arXiv:2606.06300v1 Announce Type: new Abstract: We propose MResOpt, a staged residual neural network architecture for constrained optimization problems. Our architecture fits within predict-complete-c
arXiv:2606.05378v1 Announce Type: cross Abstract: We test whether a single screen-and-ablate recipe -- identify attention-head circuits by task-pattern selectivity, then verify by causal ablation agai
arXiv:2606.05697v1 Announce Type: new Abstract: User interface (UI) and user experience (UX) evaluation is central to product development, yet reliable feedback still relies on recruiting human partic
arXiv:2606.06303v1 Announce Type: cross Abstract: Controllable generation with discrete diffusion models is often hindered by high computational overhead or the need for retraining. In this paper, we
arXiv:2606.05875v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) improves large language model (LLM) answer quality by grounding generation in external evidence, but processing ret
arXiv:2606.06316v1 Announce Type: cross Abstract: Financial crashes, cascading failures in infrastructure, and critical errors in AI systems are frequently triggered by events that occur with extremel
arXiv:2505.11766v4 Announce Type: replace-cross Abstract: Neural Operators (NOs) are powerful architectures for learning mappings between function spaces. While most advances focus on refining kernel
arXiv:2606.05555v1 Announce Type: cross Abstract: Scaling reinforcement learning (RL) to diverse multitask settings remains a central challenge. While recent advances in model-based RL achieve strong
Knowledge scaling—increasing the volume of learned information—provides reliable performance on familiar tasks but limited flexibility when facing novel problems. Intelligence, by contrast, enables ad
arXiv:2509.24882v2 Announce Type: replace-cross Abstract: Neural scaling laws underlie many of the recent advances in deep learning, yet their theoretical understanding remains largely confined to lin
arXiv:2606.05625v1 Announce Type: new Abstract: Implicit reward hacking is hard to audit when a language model's chain of thought appears benign: a final answer may be anchored by a prompt shortcut wh
arXiv:2602.22067v2 Announce Type: replace Abstract: Grounding is a critical step in classical planning, yet it often becomes a computational bottleneck due to the exponential growth in grounded action
arXiv:2406.08966v3 Announce Type: replace-cross Abstract: The separation power of a machine learning model refers to its ability to distinguish between different inputs and is often used as a proxy fo
arXiv:2606.05510v1 Announce Type: new Abstract: Telehealth systems have become increasingly important for delivering accessible and timely medical information. Existing large language models often str
arXiv:2602.19373v3 Announce Type: replace-cross Abstract: Deep reinforcement learning systems often suffer from unstable training dynamics due to non-stationarity, where learning objectives and data d
arXiv:2606.06102v1 Announce Type: new Abstract: Ultra-short-term solar irradiance prediction is critical for photovoltaic system dispatch and power grid stability. Existing approaches suffer from thre
arXiv:2606.05217v1 Announce Type: cross Abstract: We exhibit an exact correspondence between sampling with score-based diffusion models and adiabatic transport of ground states for a family of Schrodi
This is an actual page on the White House web site. It reads like something written about a third world dictator. So embarrassing. I have not seen any branch of the federal government sink this low in
This is really stupid, and it’s not getting enough attention. The Trump administration is pulling a working $368 million ocean monitoring system out of the water, equipment taxpayers already bought, b
arXiv:2606.05481v1 Announce Type: cross Abstract: Data-driven Prognostics and Health Management (PHM) uses time-varying condition-monitoring data to diagnose system states and estimate remaining usefu
arXiv:2606.06034v1 Announce Type: cross Abstract: Matrix inversion in chunk-wise parallel linear attention is a major bottleneck for long-context modeling, particularly on NPUs, where forward-substitu
arXiv:2606.05528v1 Announce Type: new Abstract: Existing frameworks assess whether AI systems might be conscious but provide no guidance on what to do with that assessment. We address this gap with a
arXiv:2606.05654v1 Announce Type: cross Abstract: Hate moderation is often evaluated as classification on clean English inputs, but deployed systems must route content to actions such as ALLOW, FLAG,
arXiv:2606.05262v1 Announce Type: cross Abstract: Uncrewed aerial vehicles (UAVs) are increasingly considered as aerial platforms capable of providing both sensing and communication services, represen
You have to read this. Trump demolished the East Wing of the White House and replaced it with a private ballroom funded by corporate donors. Now we know what they got for it. More than half of the pub
arXiv:2606.05330v1 Announce Type: new Abstract: Large language models can shift human beliefs across high-stakes domains, but most persuasion studies rely on pre/post belief change. These endpoint mea
arXiv:2606.05236v1 Announce Type: new Abstract: Robotic arms capable of traversing arbitrary spatial paths, especially in highly obstructed workspaces, are highly desired across several industries. Qu
arXiv:2606.06407v1 Announce Type: new Abstract: Medical imaging artificial intelligence has achieved strong performance in isolated image interpretation, but remains poorly aligned with radiological p
arXiv:2510.05544v2 Announce Type: replace Abstract: Large language models (LLM) and vision-language models (VLM) have achieved state-of-the-art performance, but they impose significant memory and comp
arXiv:2606.05742v1 Announce Type: new Abstract: Speculative decoding accelerates generation by verifying multiple drafted tokens in a single target-model forward pass, reducing sequential decoding ite
arXiv:2606.05840v1 Announce Type: cross Abstract: Nonlinear Model Predictive Control requires solving a constrained nonlinear program (NLP) in real-time at every sampling instant, a computational bott
arXiv:2606.05620v1 Announce Type: new Abstract: Recursion enables the generation of hierarchical linguistic structures but imposes substantial processing demands during real-time comprehension. While
This week I’ve been at SXSW London. There’s been music, film, and a lot—and I mean a lot—of talk about AI. I also had the opportunity to sit down with Gloria Mark, a psychologist at the University of
arXiv:2606.05999v1 Announce Type: new Abstract: Cloud removal aims to accurately reconstruct the ground objects obscured by clouds in remote sensing images. Existing Transformer-based methods utilizin
arXiv:2606.06047v1 Announce Type: new Abstract: Errors in speech translations reduce trustworthiness of Speech Translation (ST) systems and can have serious consequences. Yet currently there is no est
arXiv:2606.05778v1 Announce Type: new Abstract: Traditional Image Aesthetic Assessment (IAA) methods mainly rely on regressing absolute Mean Opinion Scores (MOS). However, such a paradigm overlooks th
arXiv:2512.08560v3 Announce Type: replace Abstract: Understanding how the human brain represents visual concepts, and in which brain regions these representations are encoded, remains a long-standing
arXiv:2606.05515v1 Announce Type: new Abstract: Learning representations of CAD models is a largely open problem. While 3D representation learning has flourished around point clouds and meshes, the na
arXiv:2606.05799v1 Announce Type: cross Abstract: Existing calibration methods for Large Language Models (LLMs) often overlook a critical dimension of trustworthiness: a model's {em behavioral robustn
arXiv:2606.05478v1 Announce Type: new Abstract: Diffusion Models (DM) have revolutionized text-driven generation by enabling the synthesis of high-quality, photorealistic visual content from user prom
arXiv:2601.12983v3 Announce Type: replace Abstract: Multimodal large language models (MLLMs) are increasingly used to automate chart generation from data tables, improving analysis and reporting effic
arXiv:2606.05568v1 Announce Type: cross Abstract: While ColBERT is an effective neural retrieval architecture, it requires a heavy index structure to support candidate set retrieval based on approxima