Knowledge catalogue
arXiv:2610.11707v1 Announce Type: new Abstract: Memory-augmented mobile GUI agents store successful execution trajectories and reuse them in later tasks, but a stored trajectory rarely matches a new t
arXiv:2610.11220v1 Announce Type: new Abstract: Building upon the foundations laid by our previous work, this paper introduces Arena 5.0, the fifth iteration of our framework for robotics social navig
arXiv:2610.12437v1 Announce Type: cross Abstract: Density ratios quantify distribution shift from a probability-mass point of view, whereas displacement fields describe, from a dynamical point of view
arXiv:2610.11539v1 Announce Type: cross Abstract: As leading LLMs improve on capability evaluations, their limitations in producing creative outputs on design tasks remain insufficiently characterised
arXiv:2610.11845v1 Announce Type: new Abstract: Spin in clinical trials includes reporting practices that distort the presentation of results. This is particularly critical in medicine, where spin is
arXiv:2610.11748v1 Announce Type: cross Abstract: U-Net inference for brain-tumor segmentation requires billions of multiply-accumulate operations, motivating hardware that can reduce computation dyna
arXiv:2610.12470v1 Announce Type: cross Abstract: While learning dexterous manipulation from a single human video offers a promising alternative to costly robot demonstrations, many recent methods pre
arXiv:2610.10810v1 Announce Type: cross Abstract: Long-horizon robotic manipulation is often built by chaining independently trained skills. Although each skill can be reliable in isolation, performan
arXiv:2610.11659v1 Announce Type: cross Abstract: On-policy distillation (OPD) supervises student-generated trajectories with token-level teacher signals. Its sampled-token variant avoids the cost of
arXiv:2610.12094v1 Announce Type: cross Abstract: Particle filters are a standard tool for nonlinear state estimation, but their resampling step is discrete, preventing gradient-based learning in vari
arXiv:2610.10550v1 Announce Type: new Abstract: Personalizing text-to-image diffusion models from a few reference images requires preserving subject identity while following prompts that describe new
arXiv:2610.12214v1 Announce Type: cross Abstract: Recent full-duplex spoken dialog models enable simultaneous listening and speaking, but fine-grained models still advance their backbone autoregressiv
arXiv:2610.11067v1 Announce Type: new Abstract: Prompt learning is a popular method for adapting foundation models, but learned prompts are typically task-specific and fail to generalize to new classe
arXiv:2610.12052v1 Announce Type: cross Abstract: Despite their empirical success, why diffusion models overcome the bottlenecks of classical score-based samplers remains unclear. In this work, we lev
arXiv:2610.11934v1 Announce Type: cross Abstract: Industrial environments are increasingly characterized by the tight interaction among physical processes, communication infrastructures, and intellige
arXiv:2610.11751v1 Announce Type: new Abstract: Co-denoising pretrained representations such as DINO can substantially improve the training speed and quality of flow matching models, but it introduces
arXiv:2502.20612v2 Announce Type: cross Abstract: In self-supervised contrastive learning, negative pairs are typically constructed using an anchor image and a sample drawn from the entire dataset, ex
arXiv:2610.11113v1 Announce Type: new Abstract: Pre-trained vision-language models excel across varied perception tasks, but adapting them to novel downstream settings without sacrificing generalizati
arXiv:2610.10865v1 Announce Type: new Abstract: Self-supervised speech encoders contain linguistic and paralinguistic information in a shared, entangled representation space. We combine a TopK sparse
arXiv:2610.11656v1 Announce Type: new Abstract: Facial attractiveness prediction usually assigns one overall rating, leaving the roles of shape, appearance, and viewing conditions implicit. We propose
arXiv:2610.11205v1 Announce Type: new Abstract: Representation structure is crucial for understanding Vision Transformer (ViT) architectures and their generalization behavior. However, prior studies n
arXiv:2610.11012v1 Announce Type: new Abstract: Powerful misaligned AI models might recognize alignment evaluations and strategically behave well on them, rendering direct audits uninformative. Howeve
arXiv:2610.12355v1 Announce Type: cross Abstract: Spatial reasoning remains a persistent weakness of vision-language models (VLMs), because RGB inputs do not directly provide geometric evidence. Exist
arXiv:2610.11141v1 Announce Type: new Abstract: Relative localization is crucial for a multi-robot system to collaboratively perform tasks, such as exploration and formation. However, this is highly c
arXiv:2610.11308v1 Announce Type: new Abstract: Accurate and reliable relative localization is crucial for multi-robot applications like exploration, search, and rescue missions. LiDAR-based solutions
arXiv:2610.11317v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures have become essential for scaling large language models, with recent work demonstrating the benefits of fine-grai
arXiv:2610.11433v1 Announce Type: new Abstract: In this paper, we introduce a metric-guided dynamic loss controller (DLC) for multi-objective image restoration. Conventional image restoration pipeline
arXiv:2610.11206v1 Announce Type: new Abstract: Flat loss landscapes have long been linked to better generalization in neural networks. However, its role as a causal mechanism for generalization is le
arXiv:2610.11152v1 Announce Type: cross Abstract: LLM agents increasingly improve at inference time by accumulating experience in context rather than by updating parameters. This process is often desc
arXiv:2610.12048v1 Announce Type: new Abstract: Deep neural networks, including large language models, have achieved remarkable performance across various tasks. However, they are prone to overconfide
arXiv:2610.11706v1 Announce Type: new Abstract: Self-blended images are widely used to train face-swap detectors, but primarily capture blending artifacts. We investigate whether adding illumination i
arXiv:2610.10564v1 Announce Type: cross Abstract: Dynamic-point filters are routinely added to feature-based visual SLAM, and several recent systems argue that removing dynamic features can leave too
arXiv:2610.11510v1 Announce Type: new Abstract: Large language models (LLMs) often default to Modern Standard Arabic (MSA) when generating Arabic, even when prompted with dialectal Arabic. A natural e
arXiv:2610.11938v1 Announce Type: new Abstract: Adversarial attacks on vision-language models optimize an image toward a text target, then cite the attacked model's similarity score as evidence of suc
arXiv:2610.10760v1 Announce Type: new Abstract: Prompt optimization for text-to-image (T2I) generation has been pursued almost entirely as text rewriting, in which a short user brief is expanded into
arXiv:2607.16656v2 Announce Type: replace Abstract: Object removal aims to eliminate target objects specified by a mask while preserving visual consistency with the surrounding regions. Existing metho
arXiv:2610.11776v1 Announce Type: new Abstract: Long-term personalization requires language models to use interaction history to track users' preferences across sessions. Parametric memory encodes thi
arXiv:2610.12468v1 Announce Type: cross Abstract: We present DreamTrue, a multi-view, cross-embodiment robot world model for action-faithful and physically plausible video prediction. Training such a
arXiv:2610.11299v1 Announce Type: new Abstract: Voice agents are converging on a collaboration pattern: a full-duplex interaction model stays on the live channel as the entry to the conversation, whil
arXiv:2610.12266v1 Announce Type: cross Abstract: Multimodal large language models have made remarkable progress in bridging vision and language, facilitating various perception tasks essential for hu
arXiv:2610.12095v1 Announce Type: new Abstract: Few-shot learning aims to recognize novel categories from limited labeled examples. Recent studies incorporate textual semantics to compensate for limit
arXiv:2604.04611v3 Announce Type: replace Abstract: Federated learning (FL) enables multiple clients to collaboratively train a global model by aggregating local updates without sharing private data.
arXiv:2610.11115v1 Announce Type: new Abstract: The escalating size of pretrained neural networks has rendered model compression a prerequisite for deployment under stringent memory and compute constr
arXiv:2610.11284v1 Announce Type: cross Abstract: Diffusion-based LLMs (dLLMs) have recently emerged as a promising alternative to autoregressive (AR) LLMs by enabling bidirectional parallel refinemen
arXiv:2610.11670v1 Announce Type: new Abstract: Diffusion models generalize early in training and later reproduce individual training samples. Standard tests detect memorization only once one-shot gen
arXiv:2610.11790v1 Announce Type: new Abstract: Byte-level language models such as the Byte Latent Transformer (BLT) group bytes into patches and run their large global model once per patch. BLT start
arXiv:2610.11431v1 Announce Type: new Abstract: Motion estimation in echocardiography is essential for quantitative assessment of cardiac function and myocardial mechanics, but remains challenging due
arXiv:2610.12436v1 Announce Type: new Abstract: AI agents can now conduct real-world cyberattacks, scale up capabilities with the number of agents, and collectively pursue misaligned goals to obtain r
arXiv:2610.12035v1 Announce Type: cross Abstract: Archetypal Analysis (AA) represents observations as convex combinations of extremal data-driven profiles, yielding interpretable low-dimensional descr
arXiv:2610.11303v1 Announce Type: new Abstract: Radiology report generation can automatically generate clinical descriptions from X-ray images, thereby significantly improving the efficiency of radiol
arXiv:2610.11976v1 Announce Type: cross Abstract: We detail scalable methods for approximating the quadratic entropy p^T d p for arbitrary distributions p and common distances d of negative type. We f
arXiv:2609.34181v2 Announce Type: replace Abstract: Large Reasoning Models (LRMs) have shown remarkable reasoning capabilities, yet they still suffer from overthinking, generating redundant reasoning
arXiv:2610.11347v1 Announce Type: new Abstract: Physically grounded manipulation of articulated objects requires understanding both the maximum forces encountered during contact and the work performed
arXiv:2610.12248v1 Announce Type: new Abstract: Wearable augmented reality (AR) assistants are moving toward continuous real-world interaction, where they perceive the user's activity through first-pe
arXiv:2610.11694v1 Announce Type: cross Abstract: Existing reaction models primarily learn molecular transformations, whereas enzy- matic reactions depend jointly on molecular structure and catalytic
arXiv:2610.11584v1 Announce Type: cross Abstract: To test conditional independence of X and Y given a text or an image Z, one conditions on an embedding psi(Z) in place of Z. The embedded test is vali
arXiv:2610.12369v1 Announce Type: cross Abstract: Most robot policies keep a model in the control loop: a VLA maps observations to actions, and an Agent Harness, such as Agent-as-Policy or Harness VLA
arXiv:2610.11063v1 Announce Type: cross Abstract: Scaling laws describe power-law improvements in model performance with dataset size and parameter count, yet their underlying mechanisms are not fully
arXiv:2610.10859v1 Announce Type: new Abstract: Text-to-image diffusion models are increasingly distilled into few-step variants and being deployed to enable fast inference. However, their ability to
arXiv:2312.01221v2 Announce Type: replace Abstract: Quantum Natural Language Processing (QNLP) is taking huge leaps in solving the shortcomings of classical Natural Language Processing (NLP) technique