Knowledge catalogue
arXiv:2610.17971v1 Announce Type: cross Abstract: The semantic entropy of a language model is the entropy of the meanings of its sampled answers. The meanings are never observed, and the entropy is es
arXiv:2506.19549v2 Announce Type: replace-cross Abstract: Identifying which tokens and activations truly influence model predictions is critical for both the efficiency and interpretability of large a
arXiv:2406.07169v3 Announce Type: replace Abstract: Human motion generation is a challenging task due to its high dimensionality and the difficulty of generating fine-grained motions. Diffusion method
arXiv:2610.18462v1 Announce Type: new Abstract: Readout scaling changes what a sparse autoencoder (SAE) learns, but the benefit of removing it depends on the data. We use readout-canonicalized decisio
arXiv:2610.18488v1 Announce Type: new Abstract: Many related prediction problems, which we call questions, come with few labels each. What information can be shared across them, and what is actually n
arXiv:2610.16409v1 Announce Type: new Abstract: Repetitive structures can give an incorrect pose candidate more inlier support than an accurate one, causing visual localization to select it. History-G
arXiv:2610.18388v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have shown strong potential for remote sensing understanding, yet reliable reasoning remains challenging when t
arXiv:2610.14205v1 Announce Type: new Abstract: Implicit neural representations (INRs) offer a powerful framework for modeling high-dimensional physical fields, but their training remains inefficient
arXiv:2610.16248v1 Announce Type: new Abstract: We study sampling from pi(x)proptoe^{-V(x)} on R^d, where V is alpha-strongly convex and eta-smooth with condition number kappa=eta/alpha. For this prob
arXiv:2610.16082v1 Announce Type: new Abstract: Heterogeneous medical image data motivate domain-specialized diffusion experts, but expert specialization alone does not determine how their predictions
arXiv:2610.15079v1 Announce Type: new Abstract: Squeeze-and-Excitation (SE) modules improve convolutional networks by modeling channel-wise dependencies, but global average pooling collapses spatial s
arXiv:2610.17623v1 Announce Type: new Abstract: Rubric-based reinforcement learning grades a response against many written criteria but collapses them into one reward, which discards the detail the ru
arXiv:2610.18292v1 Announce Type: new Abstract: Kernel Mean Matching (KMM) estimates risk under covariate shift by reweighting labelled source samples so that their kernel mean embedding matches that
arXiv:2610.16022v1 Announce Type: new Abstract: Neuromorphic sensing and computing promise low latency and high energy efficiency for robotics, yet most event-based visual place recognition (VPR) pipe
arXiv:2610.16427v1 Announce Type: new Abstract: Recursive reasoning models such as the Tiny Recursive Model (TRM) iteratively refine two latent states: an answer state y, decoded into the output, and
arXiv:2610.16347v1 Announce Type: new Abstract: Forward-Forward learning replaces end-to-end backpropagation with local, layer-wise training objectives. Its variants are evaluated primarily by classif
arXiv:2610.18139v1 Announce Type: new Abstract: We study causal error-feedback coefficients as design variables for model quantization. Modeling instantaneous quantization errors as independent, zero-
arXiv:2610.14269v1 Announce Type: new Abstract: Humanoid face robots can now move their lips in sync with speech and show detailed facial expressions. Give such a robot the face of a real person and d
arXiv:2610.15761v1 Announce Type: cross Abstract: For languages with limited resources, Sentiment Analysis remains a challenging problem due to limited annotated data and strong domain variability acr
arXiv:2610.14030v1 Announce Type: new Abstract: Looped transformers reuse one shared block across many recurrent steps, so depth becomes a quantity that can be spent at runtime rather than a stack of
arXiv:2610.15742v1 Announce Type: new Abstract: Scene classification of remote sensing imagery with multimodal large language models (MLLMs) is formulated as a single-forward-pass decision problem: ca
arXiv:2610.18479v1 Announce Type: new Abstract: Sonar was one of the first sensors with which mobile robots built maps, and in-air sonar keeps working where cameras and lidar fail, in darkness, smoke,
arXiv:2610.18458v1 Announce Type: new Abstract: Modern image restoration methods increasingly rely on large-scale supervised training, yet clean targets are often prohibitively difficult to obtain in
arXiv:2610.15186v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) reuses the same documents across many requests, making non-prefix KV-cache reuse attractive. Yet a cached documen
arXiv:2610.17998v1 Announce Type: cross Abstract: Spiking Neural Networks (SNNs) are promising for energy-efficient neuromorphic computing, but they still suffer from catastrophic forgetting when lear
arXiv:2610.16242v1 Announce Type: new Abstract: World-action models should preserve the intended manipulation across equivalent descriptions of a spatial goal. We evaluate this consistency in 864 roll
arXiv:2610.15916v1 Announce Type: new Abstract: In multi-group learning, a single predictor must perform nearly as well as the best hypothesis in a class on every group in a rich, possibly infinite an
arXiv:2610.16820v1 Announce Type: cross Abstract: In simulation-based inference (SBI), neural posterior estimators trained on a bounded range of sample sizes can become inaccurate on larger datasets b
arXiv:2601.21590v2 Announce Type: replace Abstract: Reinforcement learning (RL) post-training is a dominant approach for improving the reasoning performance of large language models (LLMs), yet growin
arXiv:2409.12333v2 Announce Type: replace-cross Abstract: Extracting hepatic vessels from abdominal images is of high interest for clinicians since it allows to divide the liver into functionally-inde
arXiv:2610.14423v1 Announce Type: cross Abstract: Frontier AI systems are increasingly natively multimodal, jointly pretrained on multiple modalities, such as text, vision, and audio. However, the sci
arXiv:2610.18838v1 Announce Type: cross Abstract: A central challenge in scaling flow models is maintaining stability in training and integration. In flow matching, this stability depends critically o
arXiv:2610.18039v1 Announce Type: new Abstract: Vision Transformers achieve strong performance but incur high computational costs from quadratic token interactions. Training-free token reduction metho
arXiv:2610.14866v1 Announce Type: new Abstract: Cross-modal Thermal Geo-localization (TG) provides an illumination-robust positioning solution for Unmanned Aerial Vehicles (UAVs) in Global Navigation
arXiv:2610.15617v1 Announce Type: cross Abstract: Recursive synthetic-data training can degrade a fitted model, but its effects on the variable-screening stage that precedes model fitting are less und
arXiv:2610.17939v1 Announce Type: cross Abstract: Traditional time-series classification methods often operate as black boxes, providing a class prediction without indicating which time point or time
arXiv:2610.16104v1 Announce Type: new Abstract: Test-Time Reinforcement Learning (TTRL) enables large language models to adapt directly on unlabeled test problems by constructing pseudo-labels from mu
arXiv:2610.14730v1 Announce Type: cross Abstract: Adapting embedding models to new tasks requires training data that reflect task-specific information needs and relevance criteria. However, manual dat
arXiv:1307.2965v3 Announce Type: replace Abstract: The automatic segmentation of human knee cartilage from 3D MR images is a useful yet challenging task due to the thin sheet structure of the cartilag
arXiv:2610.15467v1 Announce Type: new Abstract: Image-computable low-level image saliency has shaped perceptual psychology and computer science, but is limited by its inability to capture human high-l
arXiv:2610.15515v1 Announce Type: new Abstract: Adaptive image tokenizers compress an image into a variable number of tokens matched to its complexity, and recent work makes this allocation controllab
arXiv:2610.13999v1 Announce Type: new Abstract: Rule decisions such as content moderation, advertising compliance, and eligibility checks combine several conditions, exemptions, and missing-informatio
arXiv:2610.15156v1 Announce Type: new Abstract: Distribution-system state estimation is a growing necessity for the modern power grid as the addition of local storage and generation add system complex
arXiv:2610.16878v1 Announce Type: new Abstract: Autoregressive electronic health record (EHR) foundation models predict the next event token in patient trajectories: sequences of structured medical ev
arXiv:2603.08185v2 Announce Type: replace Abstract: Post-training quantization (PTQ) has emerged as a prevailing technique for deploying large language models (LLMs) efficiently in terms of both memor
arXiv:2610.14478v1 Announce Type: new Abstract: Omnidirectional aerial robots offer full 6-DoF independent control over position and orientation, making them popular for aerial manipulation. Although
arXiv:2610.13997v1 Announce Type: new Abstract: Concept representations in diffusion models drift across network depth and denoising time, yet existing sparse autoencoders offer only per-block or per-
arXiv:2610.15854v1 Announce Type: new Abstract: Grounded spatial reasoning about indoor scenes rests on a geometric reconstruction that the multimodal system does not itself produce. Feed-forward mult
arXiv:2507.23449v3 Announce Type: replace Abstract: One-class learning is an effective methodology for time series anomaly detection, yet kernel one-class approaches often compare sequences in a point
arXiv:2610.17534v1 Announce Type: new Abstract: Actuator sizing is an early and consequential decision: joint torque and velocity specifications fix the motors, gearboxes and brakes before any CAD mod
arXiv:2610.14011v1 Announce Type: new Abstract: Modern experiments increasingly produce rich post-treatment objects---such as text, images, and video---that may provide early surrogate signals for out
arXiv:2604.01477v2 Announce Type: replace Abstract: Reinforcement learning (RL) and model predictive control (MPC) offer complementary strengths, yet existing MPC-RL frameworks commonly rely on gradie
arXiv:2610.15968v1 Announce Type: new Abstract: Spiking Transformers achieve energy efficiency by discarding softmax normalization in favor of thresholded, binary attention. However, this removal brea
arXiv:2610.18486v1 Announce Type: new Abstract: Membership Inference Attacks (MIAs) are currently the dominant approach to evaluating privacy in machine learning applications. Despite their significan
arXiv:2610.17226v1 Announce Type: cross Abstract: Most machine-learning interatomic potentials (MLIPs) are trained on gas-phase data, which limits their use for chemistry in solution. Here, we introdu
arXiv:2610.14671v1 Announce Type: new Abstract: Streaming video understanding requires answering questions from the observed video, with evidence drawn from recent observations or earlier events. Hist
arXiv:2610.15660v1 Announce Type: new Abstract: Domain generalised semantic segmentation (DGSS) has recently benefited from combining multiple foundation models, such as vision-language and vision fou
arXiv:2610.15039v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models combine specialized experts through an input-dependent routing mechanism, and their sparse variants underpin many modern
arXiv:2610.14512v1 Announce Type: new Abstract: Objective. To evaluate whether spatial context and temporal modeling improve tissue recognition during optical trocar entry, where multiple abdominal-wa
arXiv:2610.16264v1 Announce Type: new Abstract: Electroencephalography (EEG) is a non-invasive, scalable source of quantitative biomarkers for the early diagnosis of brain disorders, and deep represen