Knowledge catalogue
arXiv:2605.05097v1 Announce Type: cross Abstract: LLMs are trained once, then deployed into a world that never stops changing. External memory compensates for this, but most systems manage it explicit
arXiv:2511.02230v4 Announce Type: replace-cross Abstract: KV cache management is essential for efficient LLM inference. To maximize utilization, existing inference engines evict finished requests' KV
arXiv:2605.03278v2 Announce Type: cross Abstract: Doubly Robust (DR) estimation of treatment effect relies on an untestable assumption that is the absence of unobserved confounding. This assumption is
arXiv:2605.04357v1 Announce Type: cross Abstract: The usage of large language models (LLMs) has grown increasingly fragmented, with no single model dominating. Meanwhile, cloud providers offer a wide
Jordan Novet / CNBC: CoreWeave reports Q1 revenue up 112% YoY to 2.08B, vs. 1.97B est., a $99.4B revenue backlog, forecasts Q2 revenue below estimates; CRWV drops 8%+ after hours — CoreWeave shares tu
arXiv:2605.03231v1 Announce Type: new Abstract: What if a browser agent could learn your work simply by watching you do it? We present cotomi Act, a browser-based computer-using agent that combines re
arXiv:2605.04555v1 Announce Type: new Abstract: Model-based reinforcement learning (MBRL) offers a promising approach for data-efficient energy management in buildings, combining the strengths of pred
arXiv:2605.04413v1 Announce Type: new Abstract: Structural causal models provide a unified semantics for interventions and counterfactuals, but most identifiability results rely on restrictive assumpt
arXiv:2605.04346v1 Announce Type: cross Abstract: The Forward-Forward algorithm eliminates global gradient flow and full network activations storage. However, in convolutional settings, existing BP-fr
arXiv:2605.05136v1 Announce Type: new Abstract: Domain Generalization (DG) aims to learn representations that remain robust under out-of-distribution (OOD) shifts and generalize effectively to unseen
arXiv:2605.04470v1 Announce Type: new Abstract: Open-loop imitation learning has advanced modern autonomous driving policy architectures, but closed-loop deployment remains vulnerable to policy-induce
arXiv:2605.04396v1 Announce Type: new Abstract: Recent work has shown that Transformers' compositional generalization is governed by complexity control, initialization scale and weight decay, which st
arXiv:2602.10043v2 Announce Type: replace Abstract: Head magnetic resonance imaging (MRI) data are routinely collected and shared for research under strict regulatory frameworks that require the remov
arXiv:2605.04905v1 Announce Type: new Abstract: Electrospinning is a highly sensitive fabrication process in which small variations in operating parameters can significantly influence fiber morphology
arXiv:2512.14954v2 Announce Type: replace Abstract: Computing next-token likelihood ratios between two language models (LMs) is a standard task in training paradigms such as knowledge distillation. Si
arXiv:2605.03309v1 Announce Type: cross Abstract: Dependency confusion attacks exploit a structural gap in software distribution: once a package is installed, there is no cryptographic proof of which
arXiv:2605.05023v1 Announce Type: new Abstract: Efficient CUDA implementations of attention mechanisms are critical to modern deep learning systems, yet supporting diverse and evolving attention varia
arXiv:2605.05204v1 Announce Type: new Abstract: The landscape of high-performance image generation models is currently shifting from the inefficient multi-step ones to the efficient few-step counterpa
arXiv:2605.04518v1 Announce Type: new Abstract: Automatic brain tumor segmentation from multi-modal MRI remains challenging because volumetric models often incur substantial computational cost. This p
arXiv:2605.04943v1 Announce Type: new Abstract: The condition monitoring (CM) of synthetic fibre ropes (SFRs) used in offshore, maritime, and industrial settings demands more than a classifier: inspec
arXiv:2408.09929v2 Announce Type: replace-cross Abstract: Inspired by the idea of Positive-incentive Noise (Pi-Noise or pi-Noise) that aims at learning the reliable noise beneficial to tasks, we scien
arXiv:2605.04477v1 Announce Type: new Abstract: Online reinforcement learning from human feedback (RLHF) has emerged as a promising paradigm for aligning large language models (LLMs) by continuously c
arXiv:2410.23222v3 Announce Type: replace Abstract: Recent advancements in foundation models have been successfully extended to the time series (TS) domain, facilitated by the emergence of large-scale
arXiv:2605.03882v1 Announce Type: cross Abstract: Individuals frequently form deep attachments to physical objects (e.g., plush toys) that usually cannot sense or respond to their emotions. While AI c
arXiv:2605.02970v1 Announce Type: cross Abstract: Network traffic anomaly detection represents a critical cybersecurity task, yet widespread encryption makes this task increasingly challenging. In res
arXiv:2605.04447v1 Announce Type: new Abstract: Medical foundation models pre-trained on large-scale datasets have shown powerful versatile performance. However, when adapting medical foundation model
arXiv:2605.04198v1 Announce Type: new Abstract: Performance of deep learning models is strongly governed by architectural capacity, with width and depth as primary controls. However, in physical-scien
arXiv:2605.03420v1 Announce Type: cross Abstract: This paper describes a submission to the Environment-Aware Speech and Sound Deepfake Detection Challenge (ESDD2) 2026, which addresses component-level
arXiv:2605.04324v1 Announce Type: new Abstract: Decentralized multi-source domain adaptation seeks to transfer knowledge from multiple heterogeneous and related source domains to an unlabeled target d
arXiv:2605.04903v1 Announce Type: cross Abstract: Large language models (LLMs) show strong potential for neural architecture generation, yet existing approaches produce complete model implementations
arXiv:2605.04957v1 Announce Type: new Abstract: Point forecasting for graph-structured multivariate time series is a fundamental problem, but rigorous uncertainty quantification for such predictions i
arXiv:2605.04418v1 Announce Type: new Abstract: The empirical success of large language model (LLM) pre-training relies heavily on heuristic stabilization techniques, such as explicit normalization la
arXiv:2602.19651v2 Announce Type: replace-cross Abstract: Learning-based methods commonly treat state estimation in robotics as a sequence modeling problem. While this paradigm can be effective at max
arXiv:2605.04239v1 Announce Type: new Abstract: Optical satellite image time series are extensively used in many Earth observation applications, including agriculture, climate monitoring, and land sur
arXiv:2605.04454v1 Announce Type: cross Abstract: Alignment evaluation in machine learning has largely become evaluation of models. Influential benchmarks score model outputs under fixed inputs, such
arXiv:2605.04068v1 Announce Type: new Abstract: The use of artificial intelligence in supply chain forecasting has attracted many scientific studies for several decades. However, the process of select
arXiv:2605.04405v1 Announce Type: new Abstract: Driven by the rapid development of generative AI models, deepfake detectors are compelled to undergo periodic recalibration to capture newly developed s
arXiv:2605.05025v1 Announce Type: new Abstract: We propose a lightweight and single-pass uncertainty quantification method for detecting hallucinations in Large Language Models. The method uses attent
arXiv:2602.05890v2 Announce Type: replace-cross Abstract: Training reinforcement learning (RL) systems in real-world environments remains challenging due to noisy supervision and poor out-of-domain (O
arXiv:2512.20773v4 Announce Type: replace Abstract: Realistic user simulation is crucial for training and evaluating multi-turn dialogue systems, yet creating simulators that accurately replicate huma
arXiv:2605.04593v1 Announce Type: new Abstract: Weakly Supervised Semantic Segmentation (WSSS) with image-level labels typically leverages Class Activation Maps (CAMs) to achieve pixel-level predictio
arXiv:2605.04503v1 Announce Type: new Abstract: Image Difference Captioning (IDC) generates natural language descriptions that precisely identify differences between two images, serving as a key bench
arXiv:2605.04708v1 Announce Type: new Abstract: From neural ODEs to continuous-time machine learning, differentiable solvers allow physics, optimization, and simulation to become trainable components
arXiv:2603.29917v2 Announce Type: replace Abstract: This work presents a robust multi-class classification framework for handwritten digits that combines diffusion-driven feature denoising with a hybr
Recent advances in diffusion-based language models enable controllable sequence generation, but applying them to structured code remains challenging, prompting exploration of syntax-aware diffusion fr
arXiv:2510.09885v5 Announce Type: replace Abstract: Large language models (LLMs) are often used in environments where facts evolve, yet factual knowledge updates via fine-tuning on unstructured text o
arXiv:2605.05054v1 Announce Type: new Abstract: Recent flow matching (FM) methods improve the few-shot adaptation of vision-language models, by modeling cross-modal alignment as a continuous multi-ste
arXiv:2509.14274v2 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated significant promise in formal theorem proving. In this study, we investigate the ability of LLMs to d
arXiv:2605.04460v1 Announce Type: new Abstract: Transportation surveys are widely used to understand travel preferences and adoption barriers, yet most survey-based analyses remain descriptive or pred
arXiv:2605.04234v1 Announce Type: new Abstract: Implicit neural representations (INRs) have emerged as a powerful paradigm for medical imaging via physics-informed unsupervised learning. Classical INR
arXiv:2605.04507v1 Announce Type: new Abstract: Negotiation agents must infer what their counterpart values, update those beliefs over dialogue turns, and choose actions under uncertainty. End-to-end
arXiv:2602.16233v2 Announce Type: replace-cross Abstract: Circuit cutting decomposes a large quantum circuit into smaller subcircuits whose outputs are classically reconstructed to recover original ex
arXiv:2404.13649v2 Announce Type: replace-cross Abstract: Dimension reduction techniques usually lose information in the sense that reconstructed data are not identical to the original data. However,
arXiv:2601.17644v3 Announce Type: replace-cross Abstract: The growing adoption of multimodal Retrieval-Augmented Generation (mRAG) pipelines for vision-centric tasks (e.g., visual QA) introduces impor
arXiv:2605.04458v1 Announce Type: new Abstract: Evaluation of long-form, citation-backed reports has lately received significant attention due to the wide-scale adoption of retrieval-augmented generat
Don’t let the exponential gains in ability fool you: there are fewer real grand plans in AI (or frankly any field of human endeavor) than you think. Companies are pivoting as the market changes, somet
Perplexity has released a new Mac application for its Personal Computer feature, which users can download from perplexity.ai/personal-computer. The company is discontinuing support for the older versi
arXiv:2603.26114v2 Announce Type: replace Abstract: DPD-Cancer is a graph-attention deep learning framework for predicting small-molecule DPD-Cancer is a graph-attention deep learning framework for pr
arXiv:2605.04806v1 Announce Type: new Abstract: This paper introduces Dr-PoGO, a method for Simultaneous Localization And Mapping (SLAM) using a 2D spinning radar. Unlike cameras or lidars that requir
arXiv:2605.04568v1 Announce Type: new Abstract: State-of-the-art model-based Reinforcement Learning (RL) approaches either use gradient-free, population-based methods for planning, learned policy netw