Knowledge catalogue
arXiv:2602.18741v3 Announce Type: replace-cross Abstract: Spectral rendering reproduces the wavelength-dependent appearance that RGB rendering cannot: metamerism, colour shifts under spectrally rich i
arXiv:2608.24327v2 Announce Type: replace Abstract: With the advent of Large Language Models and its instruction following capabilities a promising application is the task of summarization. Within thi
arXiv:2609.24875v1 Announce Type: new Abstract: Recent foundation models are moving toward native multimodal Vision-Language Models (VLMs), making VLMs a central form of next-generation foundation mod
arXiv:2609.22663v1 Announce Type: cross Abstract: Molecular systems have many degrees of freedom, but their metastable behavior can often be described by a few collective variables. Identifying these
arXiv:2510.03095v4 Announce Type: replace Abstract: Diffusion- and flow-based generative models have recently demonstrated strong performance in protein backbone generation tasks, offering unprecedent
arXiv:2609.23643v1 Announce Type: new Abstract: Autonomous navigation of unmanned aerial vehicles in constrained three-dimensional environments has been a challenge in the robotics domain. The applica
arXiv:2609.23100v1 Announce Type: new Abstract: Where to look and how to move? A robot navigating an unmapped environment must do both at once, and the two goals pull against each other. The regions m
arXiv:2609.24226v1 Announce Type: new Abstract: Instance segmentation is a fundamental computer vision task with diverse real-world applications. Recently, prompt-driven foundation models have shown p
arXiv:2407.04308v4 Announce Type: replace Abstract: We propose a graph-based tracking formulation for multi-object tracking (MOT) where target detections contain kinematic information and re-identific
arXiv:2609.22128v1 Announce Type: cross Abstract: The wrist plays a critical role in upper-limb function by enabling precise hand positioning, force regulation, and object manipulation. Continuous bra
arXiv:2609.24482v1 Announce Type: new Abstract: Monocular 3D human pose estimation (HPE) remains challenging due to depth ambiguity, occlu- sions, and the need for temporal consistency. While multi-vi
arXiv:2603.07775v2 Announce Type: replace Abstract: Robotic systems deployed beyond controlled environments encounter abrupt and unobserved dynamics shifts that induce substantial transient performanc
arXiv:2603.21568v2 Announce Type: replace-cross Abstract: We present a numerical framework for the stability and bifurcation analysis of nonlinear partial differential equations (PDEs) in which the so
arXiv:2609.22888v1 Announce Type: new Abstract: Online post-training of vision-language-action (VLA) models requires efficient use of robot interaction and reliable policy improvement from continually
arXiv:2609.22172v1 Announce Type: cross Abstract: This paper presents two interpretable machine-learning frameworks for quality screening of e-transaxle assemblies in electric vehicles: a Stagewise Wa
arXiv:2609.24151v1 Announce Type: new Abstract: Four-dimensional (4D) Radar has emerged as a key sensor for environmental perception, providing range, azimuth, elevation, and Doppler measurements whil
arXiv:2609.22684v1 Announce Type: cross Abstract: Memory-dependent robotic manipulation often requires later actions to use information from earlier interactions. Existing vision-language-action (VLA)
arXiv:2609.22123v1 Announce Type: new Abstract: Multi-station multivariate weather forecasting aims to forecast future weather variables at multiple weather stations from historical surface observatio
arXiv:2609.23775v1 Announce Type: new Abstract: Obtaining the optimal action-value function in Markov decision processes is computationally intensive in large state--action spaces. In this study, we p
arXiv:2609.22240v1 Announce Type: new Abstract: The purpose of this paper is to rigorously quantify the statistical and learning-theoretic properties of adversarial training models for classification.
arXiv:2609.23223v1 Announce Type: cross Abstract: Day-ahead electricity price forecasts support trading and storage decisions, but for battery arbitrage predicting intraday price spreads is more relev
arXiv:2609.24896v1 Announce Type: new Abstract: Dexterous grasping requires deciding where to grasp, reaching the target, and maintaining stable contact. We connect these stages through a compact thre
arXiv:2609.23271v1 Announce Type: new Abstract: Trajectory planning and control in field robotics rely on predicting how propulsion and steering affect vehicle motion when contact points undergo slip.
arXiv:2602.01654v2 Announce Type: replace Abstract: Steering vectors (SVs) offer a lightweight way to control large language models (LLMs) at inference time by shifting hidden activations, providing a
arXiv:2609.24187v1 Announce Type: cross Abstract: Autonomous endoscopic navigation requires the policy model to predict actions from texture-poor monocular observations, make safe control decisions, a
arXiv:2609.22158v1 Announce Type: new Abstract: Key-value (KV) caching is essential for efficient autoregressive large language model (LLM) inference, but the cache grows linearly with context length,
arXiv:2609.23716v1 Announce Type: new Abstract: Textual-gradient methods automate prompt optimization through natural-language feedback, but their iterative updates can be unstable. We identify two so
arXiv:2609.23290v1 Announce Type: cross Abstract: High-dimensional count data are common in scientific applications, but most diffusion and flow models are designed for continuous or categorical data,
arXiv:2609.23334v1 Announce Type: cross Abstract: Stochastic reconfiguration (SR) is the standard optimizer for neural quantum states (NQS), but modern NQS often have far more parameters than Monte Ca
arXiv:2605.13165v2 Announce Type: replace Abstract: Long chain-of-thought (Long CoT) reasoning improves performance on multi-step problems, but it also induces overthinking. This inefficiency is espec
arXiv:2609.22534v1 Announce Type: cross Abstract: Strategic classification studies how a decision maker should choose a classifier when the agents being classified can adjust their features in respons
arXiv:2609.22257v1 Announce Type: cross Abstract: Producing task-specific large language models requires discovering effective training strategies through experimentation. Automated fine-tuning system
arXiv:2410.14606v3 Announce Type: replace Abstract: Learning from a stream of experience as it arrives, also known as streaming learning, is a core part of natural learning. However, reliable streamin
arXiv:2609.24788v1 Announce Type: new Abstract: In this paper, we propose SVEET, a framework that requires merely training on a pretrained bidirectional video diffusion model but supports high-quality
arXiv:2609.23483v1 Announce Type: new Abstract: Humanoid loco-manipulation faces two prominent limitations: controllers using continuous velocity commands cannot precisely regulate individual foothold
arXiv:2609.24275v1 Announce Type: new Abstract: Text-to-speech (TTS) corpora are costly to record, yet many utterances add little new phonetic information. Core-set selection reduces this cost by choo
arXiv:2609.23841v1 Announce Type: new Abstract: Long-horizon robotic search must resolve natural language against heterogeneous, incomplete, and often ambiguous evidence: textual information, prior ma
arXiv:2609.22392v1 Announce Type: new Abstract: Image steganography hides secret message within normal images, with most existing works relying on cover-preserving transmission. However, such a paradi
arXiv:2609.23596v1 Announce Type: new Abstract: With face-recognition models now embedded in everyday authentication and surveillance, recent works have pinpointed a critical weakness: these models re
arXiv:2108.11204v4 Announce Type: replace-cross Abstract: Humans excel in solving complex reasoning tasks through a mental process of moving from one idea to a related one. Inspired by this, we propos
arXiv:2609.22120v1 Announce Type: cross Abstract: Test-time self-evolving agents improve by reusing past experience, yet sparse-reward trajectories contain failures, loops, and detours, while summarie
arXiv:2609.22094v1 Announce Type: new Abstract: Content moderation systems traditionally entangle multimodal understanding with policy-specific classification, requiring full pipeline retraining for e
arXiv:2609.24303v1 Announce Type: cross Abstract: Post-training often improves task performance but can degrade confidence calibration, leaving post-trained language models (PoLMs) more overconfident
arXiv:2609.22226v1 Announce Type: new Abstract: Decode-time alignment methods steer a frozen language model by scoring candidate continuations with an external reward and selecting the maximiser. We a
arXiv:2609.24559v1 Announce Type: new Abstract: We present t_0, a family of open-weights foundation models for forecasting with multivariate context. We release its first two members: exttt{t0-alpha}
arXiv:2609.24156v1 Announce Type: new Abstract: Most existing time series forecasting methods rely solely on numerical observations, overlooking rich contextual information from auxiliary texts. Recen
arXiv:2609.24507v1 Announce Type: new Abstract: Visuomotor policies trained from a few demonstrations may reproduce demonstrated trajectories without reliably following changes in object position. Exi
arXiv:2407.16139v2 Announce Type: replace Abstract: Federated Learning (FL) faces challenges due to data heterogeneity, which limits the global model's performance across diverse client distributions.
arXiv:2609.24385v1 Announce Type: new Abstract: Tactile sensing is an essential modality for robots performing contact-rich, dexterous manipulation, particularly under visual occlusion. While pre-trai
arXiv:2609.23688v1 Announce Type: new Abstract: We study norm-constrained linear classification under Eu clidean adversarial perturbations in a Gaussian model with a low-dimen sional informative subsp
arXiv:2609.24591v1 Announce Type: new Abstract: Sea ice forecasts are issued several days ahead, allowing errors to accumulate while new, often sparse sea ice concentration (SIC) observations become a
arXiv:2609.24246v1 Announce Type: new Abstract: Large language models (LLMs) have shown remarkable progress in natural language understanding, yet their effectiveness in specialized fields like astron
arXiv:2609.22165v1 Announce Type: new Abstract: Automatic synthesis of analog and Radio Frequency (RF) circuits is an emerging area that requires an efficient circuit modeling method. In recent years,
arXiv:2609.23151v1 Announce Type: cross Abstract: Assembly remains a challenging robotic manipulation task in presence of tight tolerances and complex contact interactions. While Learning from Demonst
arXiv:2609.22238v1 Announce Type: cross Abstract: Neural network pruning can be formulated as a combinatorial optimization problem, yet many existing approaches rely on independent filter-importance s
arXiv:2609.22795v1 Announce Type: new Abstract: Different tasks performed by legged robots impose distinct torque and speed requirements on actuators. Existing robotic actuators are generally optimize
arXiv:2609.23580v1 Announce Type: new Abstract: Reactive vision--language--action (VLA) models struggle with long-horizon manipulation when visually similar observations can correspond to different ac
arXiv:2609.22254v1 Announce Type: new Abstract: On-policy distillation (OPD) is a promising approach for transferring knowledge between language models, where a student receives dense token-level supe
arXiv:2609.22221v1 Announce Type: new Abstract: Large language models (LLMs) can generate fluent and coherent text that is increasingly difficult to distinguish from human writing, motivating the deve
arXiv:2509.01167v3 Announce Type: replace-cross Abstract: Vision-language models (VLMs) can ingest only a limited number of video frames, making frame selection a practical necessity. But do current V