Knowledge catalogue
arXiv:2605.25942v1 Announce Type: cross Abstract: Unmanned Aerial Vehicles (UAVs) have quickly become common in various airspaces, representing a wide range of applications from recreation flying to c
arXiv:2605.24020v1 Announce Type: cross Abstract: Advancements at the intersection of computer vision and natural language processing are crucial for applications like assistive tech, multimedia query
arXiv:2605.25710v1 Announce Type: cross Abstract: Realistic physical systems are characterised by emergent interactions across multiple length and time scales, posing a significant challenge for predi
arXiv:2605.25966v1 Announce Type: cross Abstract: We test whether the optimal learning-rate schedule depends on bit-width during from-initialisation quantisation-aware training (QAT) for sub-100M deco
arXiv:2605.25771v1 Announce Type: cross Abstract: Multi-domain graph pre-training is a crucial step in constructing foundational graph models with cross-domain generalization capabilities. However, ex
arXiv:2605.23941v1 Announce Type: new Abstract: Alzheimer's disease is a neurodegenerative disorder marked by progressive declines in memory and language that reduce independence in daily life, motiva
arXiv:2605.25004v1 Announce Type: cross Abstract: Inferring network-wide traffic states from sparse observations with high accuracy and trustworthy uncertainty quantification is essential for intellig
arXiv:2605.24019v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) achieve outstanding performance, yet their huge model size severely hinders deployment on edge devices with limited reso
arXiv:2605.24973v1 Announce Type: cross Abstract: VLM-based OCR models have become the de facto choice for document parsing, as they can accurately extract page-level elements (e.g., paragraphs within
arXiv:2605.25001v1 Announce Type: new Abstract: While Physics-Informed Neural Networks (PINNs) are powerful for solving Partial Differential Equations (PDEs), their training is often paralyzed by grad
arXiv:2605.24957v1 Announce Type: new Abstract: The generation of factually incorrect objects, commonly known as object hallucination, remains a persistent challenge in Large Vision-Language Models (L
arXiv:2605.25869v1 Announce Type: new Abstract: Long-term memory is essential for persistent LLM agents, yet prevailing architectures store historical interactions as unstructured, flat text. This unc
arXiv:2605.24048v1 Announce Type: cross Abstract: Multi-AI collaboration, such as ensembling or debating large language models (LLMs), is a promising paradigm for aggregating information and boosting
arXiv:2602.20191v2 Announce Type: replace-cross Abstract: Dynamic runtime latency and memory constraints necessitate flexible large language model (LLM) deployment, where an LLM can be inferred with v
arXiv:2605.24425v1 Announce Type: cross Abstract: The residual update of a pre-norm Transformer layer admits an interpretation as one step of a first-order optimizer acting on a surrogate token energy
arXiv:2605.25596v1 Announce Type: new Abstract: Phonological features provide a language-general and linguistically grounded representation of speech. We present PhonoQ-2.0, a multilingual frame-level
arXiv:2605.24770v1 Announce Type: new Abstract: Muon is a recently developed matrix-aware optimizer that has shown strong results in transformer training, but its behavior in vision transformers (ViTs
Musician and human rights activist Peter Gabriel sent a special congratulatory message to Brewster Kahle, founder and digital librarian of the Internet Archive, on being honored as a 2026 Computer His
arXiv:2605.24914v1 Announce Type: cross Abstract: To reduce LLM costs and latency, semantic caching systems must accurately identify when a new prompt matches a cached one. Current methods often rely
arXiv:2306.14853v5 Announce Type: replace-cross Abstract: In this work, we consider bilevel optimization when the lower-level problem is strongly convex. Recent works show that with a Hessian-vector p
arXiv:2603.06798v2 Announce Type: replace Abstract: The growing scale of deep learning demands distributed training frameworks that jointly reason about parallelism, memory, and network topology. Prio
arXiv:2508.17090v4 Announce Type: replace-cross Abstract: Ecological Momentary Assessment (EMA) studies enable the collection of high-frequency self-reports of suicidal thoughts and behaviors (STBs) v
arXiv:2605.24993v1 Announce Type: new Abstract: Current fMRI decoders face a performance-fidelity trade-off where efficient ID encoders outperform geometrically faithful surface-based models. We argue
arXiv:2605.24956v1 Announce Type: new Abstract: Standard next-token prediction (NTP) supervises language models solely through discrete labels in the output logit space. We argue that this sparse one-
arXiv:2605.25786v1 Announce Type: cross Abstract: Efficiently solving Poisson equations on complex, irregular domains remains a fundamental challenge in scientific computing, as classical iterative so
arXiv:2605.25173v1 Announce Type: cross Abstract: Kernel Stein discrepancy (KSD) is among the most popular goodness-of-fit (GoF) measures on general domains with a large number of successful deploymen
arXiv:2506.00181v2 Announce Type: replace Abstract: Distributed stochastic optimization intertwines (i) stochastic gradient noise, (ii) communication compression, and (iii) adaptive/normalized updates
arXiv:2605.25846v1 Announce Type: new Abstract: Endowing models with consistent multilingual performance can be achieved by mixing pre-training data, or post-training approaches such as language-speci
arXiv:2509.25507v2 Announce Type: replace-cross Abstract: How can we generate samples from a conditional distribution that we never fully observe? This question arises across a broad range of applicat
arXiv:2605.25663v1 Announce Type: new Abstract: Black-box adversarial attacks that minimize only the ground-truth confidence suffer from class drift: perturbations wander through the feature space wit
arXiv:2605.24072v1 Announce Type: cross Abstract: Finite-width fully connected neural networks with Gaussian-initialized weights deviate from their infinite-width Gaussian limit, exhibiting non-vanish
arXiv:2603.16481v2 Announce Type: replace Abstract: Non-conservative uncertainty bounds are essential for making reliable predictions about latent functions from noisy data, and thus, a key enabler fo
arXiv:2605.25312v1 Announce Type: new Abstract: We introduce P1SCO, a dataset of social media comments collected from three distinct platforms, annotated according to ten social dimensions to capture
arXiv:2605.25678v1 Announce Type: cross Abstract: We study the problem of multiclass PAC learning with bandit feedback in the realizable setting. In this framework, there is an unknown data distributi
arXiv:2605.24350v1 Announce Type: new Abstract: Robotic assistants in long-term human-robot collaboration need to assist users under partial observations while leveraging cross-day interaction history
arXiv:2512.20063v3 Announce Type: replace Abstract: We introduce exttt{PairFlow}, a lightweight preprocessing step for training Discrete Flow Models (DFMs) to achieve few-step sampling without requiri
arXiv:2605.10977v2 Announce Type: replace-cross Abstract: Watermarking for large language models (LLMs) is a promising approach for detecting LLM-generated text and enabling responsible deployment. Ho
arXiv:2603.09943v2 Announce Type: replace Abstract: Computational pathology demands both visual pattern recognition and dynamic integration of structured domain knowledge, including taxonomy, grading
arXiv:2605.24621v1 Announce Type: cross Abstract: Scattering transforms achieve Lipschitz stability and translation invariance, but dense prediction tasks require preserving spatial structure lost in
arXiv:2605.24509v1 Announce Type: cross Abstract: Latent video diffusion models generate videos by progressively transforming Gaussian noise into realistic samples conditioned on text or visual inputs
arXiv:2605.24451v1 Announce Type: new Abstract: Vietnamese exhibits substantial dialectal phonetic variation across Northern, Central, and Southern regions, where identical lexical items may be realiz
arXiv:2505.18190v5 Announce Type: replace-cross Abstract: Physics sensing plays a central role in many scientific and engineering domains, which inherently involves two coupled tasks: reconstructing d
arXiv:2605.23971v1 Announce Type: cross Abstract: This work presents a physics-guided machine-learning framework for carbon monoxide concentration inference from experimentally measured resistance tra
arXiv:2601.13236v2 Announce Type: replace-cross Abstract: Parallel imaging techniques reduce magnetic resonance imaging (MRI) scan time but image quality degrades as the acceleration factor increases.
arXiv:2605.24421v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as analyst assistants in security operations centers (SOCs), where they ingest log and alert data t
arXiv:2605.24465v1 Announce Type: new Abstract: Robots benefit from sensory information to coordinate body movement, gain robustness against perturbations, and transit between different modes to adapt
arXiv:2605.24622v1 Announce Type: new Abstract: A robot resolving ``put the cup on that one'' must fuse gesture, language, and scene geometry, yet 3D grounding benchmarks only partially capture this r
arXiv:2605.25664v1 Announce Type: cross Abstract: Poor posture is a significant concern due to its detrimental effects on health and productivity. This paper presents a collar-clipped device called Po
arXiv:2603.18363v2 Announce Type: replace-cross Abstract: Unsupervised Reinforcement Learning from Internal Feedback (RLIF) has emerged as a promising paradigm for eliciting the latent capabilities of
arXiv:2605.25704v1 Announce Type: new Abstract: In contemporary large language models (LLMs), the swish-gated linear unit (SwiGLU) activation function is widely adopted to regulate the information flo
arXiv:2605.25894v1 Announce Type: new Abstract: Predicting stock price movements during Earnings Announcements (EAs) is a significant challenge due to market noise and high-impact price discontinuitie
arXiv:2602.08426v2 Announce Type: replace-cross Abstract: Block-sparse attention is promising for accelerating long-context LLM pre-filling, yet identifying relevant blocks efficiently remains a bottl
arXiv:2605.25404v1 Announce Type: new Abstract: Cascaded Automatic Speech Recognition -- Large Language Model (ASR-LLM) pipelines remain popular for industrial Spoken Dialogue Systems (SDS), primarily
arXiv:2510.27118v4 Announce Type: replace Abstract: Most expressivity results for transformers treat them as language recognizers -- devices that accept or reject strings -- rather than as they are us
arXiv:2509.07961v2 Announce Type: replace Abstract: We develop new experimental paradigms for measuring welfare in language models. We compare verbal reports of models about their preferences with pre
arXiv:2605.24171v1 Announce Type: cross Abstract: Large language models are increasingly used for vulnerability detection, yet their reliability under different prompt formulations remains uncharacter
arXiv:2507.05890v4 Announce Type: replace-cross Abstract: As psychometric surveys are increasingly used to assess the traits of large language models (LLMs), the need for scalable survey item generati
arXiv:2605.25252v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a standard paradigm for post-training language models, but in practice, verifiers are
arXiv:2605.25041v1 Announce Type: new Abstract: 4D radar is increasingly attractive for robotic mapping because it provides range, azimuth, elevation, and Doppler measurements while remaining robust i
arXiv:2605.25057v1 Announce Type: cross Abstract: Neural networks with randomly generated hidden weights (RaNNs) have been extensively studied, both as a standalone learning method and as an initializ