Knowledge catalogue
arXiv:2610.12231v1 Announce Type: new Abstract: Learning from demonstration has enabled impressive robot behaviors. A common choice for policy learning is to use diffusion or flow matching (Flow-Polic
arXiv:2610.11738v1 Announce Type: new Abstract: Reliable uncertainty quantification (UQ) is essential for deploying neural networks in scientific and high-stakes applications, but full Bayesian infere
arXiv:2610.11575v1 Announce Type: new Abstract: Sparse Mixture-of-Experts models scale parameter capacity efficiently while maintaining a fixed compute budget per token. However, traditional training
arXiv:2610.11952v1 Announce Type: new Abstract: Instruction following enables robots to perform diverse tasks specified in natural language, making it a fundamental capability for human-robot interact
arXiv:2610.09122v1 Announce Type: new Abstract: Parameter-efficient fine-tuning (PEFT) offers many parameterizations, yet their methodological and functional differences remain unclear. We compare six
arXiv:2610.09734v1 Announce Type: new Abstract: World Action Models (WAM) improve robot policies by augmenting sparse action supervision with dense future prediction. However, much of the predictable
arXiv:2610.09940v1 Announce Type: cross Abstract: Joint-embedding predictive architectures (JEPAs) predict masked or future observations in representation space, offering a natural source of predictiv
arXiv:2610.10114v1 Announce Type: new Abstract: The architectural design of Large Language Models (LLMs) is shifting from traditional full-attention-only models to hybrid models, which combine differe
arXiv:2610.10245v1 Announce Type: new Abstract: Despite the ubiquity of sensors in wearable and mobile devices and the abundance of human movement data they generate, translating unlabeled recordings
arXiv:2610.10437v1 Announce Type: new Abstract: Flow policies capture rich and diverse action distributions, and fine-tuning them with off-policy RL to improve beyond the demonstrations has drawn grow
arXiv:2610.09173v1 Announce Type: new Abstract: 3D foundation models enable efficient novel view synthesis by carrying a Gaussian head on the representation they already use for reconstruction. Howeve
arXiv:2610.09458v1 Announce Type: new Abstract: When an LLM answers a state-specific policy question wrongly, it may be hallucinating, or it may be returning a real value that holds in another state.
arXiv:2610.09317v1 Announce Type: new Abstract: Synthetic aperture radar (SAR) and electro-optical (EO) imagery provide complementary observations: SAR enables day-and-night, weather-resilient sensing
arXiv:2610.10270v1 Announce Type: new Abstract: World action models (WAMs) have emerged as an important class of generalist robot policies, aiming to transfer video prediction priors to action learnin
arXiv:2610.07339v1 Announce Type: cross Abstract: Tactical Combat Casualty Care (TC3) requires responders to connect visual observations of injuries and interventions with established clinical guidanc
arXiv:2610.08109v1 Announce Type: new Abstract: Cardiac magnetic resonance imaging reconstruction aims to recover high-quality images from undersampled acquisitions, enabling faster scans while preser
arXiv:2610.07576v1 Announce Type: new Abstract: Cassini synthetic aperture radar (SAR) images reveal the dunes, plains, and lake basins of Titan, providing an instance of representations learned from
arXiv:2610.07628v1 Announce Type: new Abstract: Out-of-distribution (OOD) generalization remains challenging for graph neural networks (GNNs), as graph distributions can vary substantially across time
arXiv:2610.08780v1 Announce Type: cross Abstract: World models offer a data-driven alternative to traditional simulators for robotics, with applications spanning policy evaluation, improvement, and pl
arXiv:2610.07906v1 Announce Type: new Abstract: We study sequential content sufficiency by investigating whether a representation retains the ordered target information available in its input. An info
arXiv:2610.08215v1 Announce Type: new Abstract: Learning from experience is essential for LLM agents to adapt to unfamiliar and dynmaic environments. Evaluating this ability is therefore important for
arXiv:2610.07613v1 Announce Type: cross Abstract: In mill yards, log loaders clear dense piles by a sequence of bundle grasps: hundreds of logs rest in contact, and each removal changes the pile avail
arXiv:2610.07809v1 Announce Type: new Abstract: Sparsely activated Mixture-of-Experts (MoE) models increase model capacity without a proportional increase in per-token computation. Dense-to-MoE upcycl
arXiv:2610.07764v1 Announce Type: cross Abstract: Natural language processing (NLP) models can detect depression-related language in text written near the time symptoms are measured, but whether pretr
arXiv:2610.08595v1 Announce Type: cross Abstract: Deep generative models often produce structured outputs composed of interacting components. Modelling these outputs with a single model requires learn
arXiv:2507.02115v3 Announce Type: cross Abstract: Synthesizing second-language (L2) speech is potentially highly valued for L2 language learning experience and feedback. However, due to the lack of L2
arXiv:2610.07385v1 Announce Type: new Abstract: Fine-tuning vision-language models (VLMs) is typically evaluated at a single downstream checkpoint, obscuring whether a semantic capability was never ac
arXiv:2610.07559v1 Announce Type: new Abstract: Recent progress in tabular foundation models suggests that training on synthetic tasks can substantially improve in-context learning capabilities, with
arXiv:2610.06963v1 Announce Type: new Abstract: Rotary Position Embedding (RoPE) encodes token positions by rotating each two-dimensional channel of the query and key vectors at a channel-specific fre
arXiv:2610.07025v1 Announce Type: new Abstract: Multi-person 3D pose estimation with WiFi channel state information (CSI) is challenging because reflections from different people overlap without direc
arXiv:2610.04946v1 Announce Type: new Abstract: Cross-system transfer of longitudinal Electronic Health Record (EHR) representations is challenging because clinical coding, patient populations, and he
arXiv:2610.04204v1 Announce Type: new Abstract: Training large language models (LLMs) entails a fundamental trade-off: memory-efficient optimizers such as Adam discard cross-parameter curvature, where
arXiv:2610.06636v1 Announce Type: new Abstract: Many machine learning applications involve sensitive data and therefore require training under differential privacy (DP). However, DP training often deg
arXiv:2610.05333v1 Announce Type: new Abstract: Generative foundation models are attracting interest for their ability to produce desired outputs from demonstrations given at inference time, without u
arXiv:2610.04819v1 Announce Type: new Abstract: One-step real-world image super-resolution (Real-ISR) offers efficient inference, but recovering realistic and perceptually rich details often relies on
arXiv:2610.04554v1 Announce Type: new Abstract: Recovering detailed geometry from high-resolution images is critical for precise perception of the surroundings and objects. However, existing methods w
arXiv:2610.04139v1 Announce Type: new Abstract: Predicting future spatial states supports collision avoidance and timely decision-making in dynamic environments. However, existing vision-language mode
arXiv:2606.13894v3 Announce Type: replace-cross Abstract: AdamW is a default optimizer for deep learning, but its moment states add two parameter-sized buffers to training memory, increasing the cost
arXiv:2607.19234v2 Announce Type: replace Abstract: Time series classification is central to domains such as medical signal analysis, industrial monitoring, and sensor-based activity recognition, wher
arXiv:2610.05349v1 Announce Type: new Abstract: We introduce CNP-Flow, a flow matching framework for temporal generation that learns conditional source distributions through flow reversal. Whereas sta
Learning from data as we observe it is easy for humans, but most machine learning models have limited ability to learn from new data that they have not seen during training. Prior-fitted networks (the
arXiv:2610.05816v1 Announce Type: new Abstract: Image and video diffusion models allocate equal computation to every region, even when the intended scene calls for varying levels of detail. The spatia
arXiv:2610.05503v1 Announce Type: new Abstract: Large-scale EEG foundation models have demonstrated promising transferability across neurological disorders, but often require millions of parameters an
arXiv:2610.05872v1 Announce Type: new Abstract: A long-standing goal of AI is a model that can continually learn and improve itself. On post-trained models, supervised finetuning (SFT) on new data oft
arXiv:2610.03829v1 Announce Type: cross Abstract: Real-world outpatient oncology notes contain specialised terminology, tumour staging expressions, treatment names, toxicity descriptions, and institut
arXiv:2610.04937v1 Announce Type: cross Abstract: Level-K reasoning generates a hierarchy of policies specialized to opponents with different reasoning levels. When an opponent's level is unknown, a c
arXiv:2610.05240v1 Announce Type: new Abstract: Time-series foundation models offer a unified approach to forecasting across heterogeneous domains. Textual context and auxiliary observations provide c
arXiv:2610.06387v1 Announce Type: new Abstract: Large language models (LLMs) have achieved substantial performance gains through increases in model size, training data, and computational resources. Ho
arXiv:2610.05891v1 Announce Type: new Abstract: Post-hoc class activation maps (CAMs) are a standard tool for inspecting the evidence behind an image classifier's predictions, yet nothing in ordinary
arXiv:2512.13492v2 Announce Type: replace Abstract: Native 4K (2176imes3840) video generation remains a critical challenge due to the quadratic computational explosion of full-attention as spatiotempo
arXiv:2610.04869v1 Announce Type: new Abstract: An interaction has two parts: someone decides to act, and then chooses whom to act on. Temporal link prediction has concentrated on the second, and we s
arXiv:2610.03456v1 Announce Type: new Abstract: Drug-target affinity (DTA) prediction is widely used to prioritize candidate compounds before costly experimental screening. DTA models are often compar
arXiv:2610.02972v1 Announce Type: new Abstract: Large language models (LLMs) can support rubric-based screening of CVs, but applying a high-capability model to every candidate and criterion is costly.
arXiv:2610.02494v1 Announce Type: new Abstract: Automatic horizon tracking is a foundational task in 3D seismic interpretation. Most existing deep learning approaches formulate it as dense semantic se
arXiv:2610.03691v1 Announce Type: new Abstract: We present FlowHMR, a framework for recovering physically plausible global 3D human motion from monocular video. Previous learning-based methods typical
arXiv:2610.02418v1 Announce Type: cross Abstract: Modern large language models (LLMs) are trained on massive, largely unfiltered datasets, including content scraped from nearly every accessible websit
arXiv:2610.02840v1 Announce Type: cross Abstract: World action models jointly learn to forecast world dynamics and predict robot actions, such that the learned internal world dynamics guide accurate a
arXiv:2610.02683v1 Announce Type: new Abstract: Can programmable radio propagation serve as computational depth rather than only as a communication channel or one-shot analog transform? We introduce t
arXiv:2610.02718v1 Announce Type: cross Abstract: Vision-language models such as CLIP exhibit strong semantic generalization, but remain limited in fine-grained visual perception. A recent work named
First of all, thank you for reading. I trained a small MoE model completely from scratch (no external base weights) and wanted to share the results + a couple of lessons. Apex-2 - Architecture: Decode