Knowledge catalogue
arXiv:2503.16094v2 Announce Type: replace Abstract: Large Language Model (LLM) alignment is commonly achieved through supervised fine-tuning or reinforcement learning, both of which require labeled or
arXiv:2609.20839v1 Announce Type: new Abstract: Phoneme-centric visual speech recognition reconstructs sentences from intermediate phoneme predictions, making overall recognition performance highly de
arXiv:2609.21427v1 Announce Type: new Abstract: Mean-variance portfolio optimization (MVO) is a central framework in data-driven asset management. A widely adopted approach is a two-stage framework th
arXiv:2609.21113v1 Announce Type: new Abstract: Fine-tuning has emerged as a widely adopted approach for adapting LLMs to a variety of downstream tasks. However, how it reshapes their internal mechani
arXiv:2511.02845v3 Announce Type: replace-cross Abstract: The advancement of next-generation Wi-Fi technology heavily relies on sensing capabilities, which play a pivotal role in enabling sophisticate
arXiv:2609.21327v1 Announce Type: cross Abstract: Quantile-based reinforcement learning provides an interpretable approach to risk-sensitive decision-making by optimizing a prescribed quantile of the
arXiv:2609.21112v1 Announce Type: new Abstract: Training a visuomotor policy calls for abundant demonstrations that closely match the target environment, yet collecting them anew remains expensive. Ex
arXiv:2609.21423v1 Announce Type: new Abstract: Online agent deployments produce abundant execution traces, while task-specific verification and expert annotation are costly to scale. We study how to
arXiv:2609.21082v1 Announce Type: new Abstract: Quadcopters offer great utility in many applications, but their nonlinear nature and disturbance sensitivity present great control challenges. Basic PID
arXiv:2609.22086v1 Announce Type: new Abstract: Professional graphic design is a long-horizon agentic task in which structured, editable artifacts emerge from many interdependent actions, yet outcomes
arXiv:2609.21096v1 Announce Type: new Abstract: In this work, we examine the topology of information flow patterns within attention graphs to effectively distinguish hallucinated from non-hallucinated
arXiv:2609.21888v1 Announce Type: cross Abstract: Detecting pretraining data in large language models is challenging because high likelihood can reflect either training exposure or strong generalizati
arXiv:2609.21628v1 Announce Type: new Abstract: Automatic tooth segmentation and FDI numbering on panoramic radiographs underpins computer-assisted dental diagnosis, yet which factors govern performan
arXiv:2609.21045v1 Announce Type: new Abstract: Collecting real-world robot data for dexterous manipulation is costly and time-consuming. While high-fidelity physics simulators enable scalable data sy
arXiv:2609.21320v1 Announce Type: cross Abstract: Modern text and image representations are often matrix-valued, with rows corresponding to tokens, patches, or other local feature vectors. Predictive
arXiv:2609.22008v1 Announce Type: cross Abstract: Vision-language models (VLMs) rely on storing and transferring appropriate information across their sub-components. Verifying that the VLMs exhibit de
arXiv:2609.21698v1 Announce Type: new Abstract: Deep learning segmentation of renal tumors requires large annotated datasets, yet clinical deployments typically offer only a handful of tumor-positive
arXiv:2609.21138v1 Announce Type: cross Abstract: Octopus crawling motivates soft robots that exploit redundancy, yet discovering and organizing diverse coordination modes for adaptation remains chall
arXiv:2609.21857v1 Announce Type: cross Abstract: LLMs are increasingly used in social simulations for socially interactive agents and robots, offering more flexibility than rule-based systems. Howeve
arXiv:2609.20912v1 Announce Type: new Abstract: In this work, we study the neural scaling laws of RydbergGPT, an autoregressive transformer model trained on qubit projective measurement data gathered
arXiv:2609.20824v1 Announce Type: new Abstract: We explore whether entropy-based confidence signals can be leveraged to improve the accuracy of Small Language Models (SLMs) with fewer than 3 billion p
arXiv:2609.21000v1 Announce Type: cross Abstract: Spinning frequency-modulated continuous-wave (FMCW) radars have been gaining popularity in autonomous vehicle perception on account of their robustnes
arXiv:2609.21504v1 Announce Type: new Abstract: Vision-and-language navigation (VLN) has advanced rapidly in static indoor environments, but robots operating in human-populated spaces must ground lang
arXiv:2609.21486v1 Announce Type: new Abstract: Multimodal trajectory prediction improves behavioral coverage in end-to-end autonomous driving, but existing methods remain limited by sparse scene repr
arXiv:2609.21675v1 Announce Type: new Abstract: Despite the remarkable progress in Multimodal Large Language Models (MLLMs), prevailing Chain-of-Thought (CoT) paradigms remain confined to the natural-
arXiv:2412.07151v1 Announce Type: cross Abstract: Distributed model training needs to be adapted to challenges such as the straggler effect and Byzantine attacks. When coordinating the training proces
arXiv:2609.21548v1 Announce Type: new Abstract: Sequential recommendation aims to predict the next item a user will interact with based on their historical behavior. Advances in Transformers have sign
arXiv:2609.22073v1 Announce Type: new Abstract: Quadrupedal robots are increasingly deployed in environments where locomotion must remain robust to disturbances and constrained terrain. Gait type, suc
arXiv:2609.05799v2 Announce Type: replace Abstract: In streaming simultaneous speech translation, the speech translation system is trained to learn a read-write policy that alternates between consumin
arXiv:2609.21099v1 Announce Type: new Abstract: Coaxial rotor drones have generated considerable interest because of energy efficiency and small size, but they are afflicted with inherent underactuati
arXiv:2609.21100v1 Announce Type: new Abstract: Learning in robotic games is constrained not only by strategic information but also by what the body can still execute. We study this coupling in a hier
arXiv:2510.13046v3 Announce Type: replace Abstract: State space models offer linear-time sequence modeling and are a promising backbone for multi-label 12-lead ECG classification, but the design choic
arXiv:2609.21755v1 Announce Type: new Abstract: Emergency department (ED) decision-making relies on heterogeneous clinical information, including patient history, vital signs, laboratory results, and
arXiv:2609.21268v1 Announce Type: new Abstract: Text-guided video editing modifies target content while preserving the appearance and temporal coherence of unedited regions. Training-based approaches
arXiv:2609.21457v1 Announce Type: new Abstract: Deep neural architectures are widely used for signal processing in automated pain assessment systems. However, architecture design has remained largely
arXiv:2609.20954v1 Announce Type: new Abstract: We present a novel end-to-end model-based Reinforcement Learning (RL) algorithm for efficient policy synthesis under given Linear Temporal Logic (LTL) s
arXiv:2609.21267v1 Announce Type: new Abstract: Production LLM agents are evaluated repeatedly as they evolve, but full agent benchmarks are costly to rerun. We study efficient recurring evaluation fo
arXiv:2602.18071v2 Announce Type: replace Abstract: Humans rearrange objects in cluttered environments using egocentric perception, actively moving to keep task-relevant spatial cues in view. Mobile r
arXiv:2609.20888v1 Announce Type: new Abstract: Massive KV caches can cause severe memory-bandwidth bottlenecks during long-context decoding. Sparse attention methods mitigate this via selective loadi
arXiv:2609.21941v1 Announce Type: cross Abstract: The importance of deep neural networks (DNNs) is widely recognized, and the parameters obtained through training are regarded as valuable assets. Rece
arXiv:2609.20849v1 Announce Type: new Abstract: Large Audio Language Models (LALMs) perform well on complex question answering but often show a reasoning gap, where explicit Chain-of-Thought (CoT) red
arXiv:2609.21151v1 Announce Type: cross Abstract: Molecular solubility directly affects key aspects of molecular development such as reaction feasibility, formulation performance, separation efficienc
arXiv:2609.21841v1 Announce Type: new Abstract: Frontier language models now produce professional deliverables that expert graders judge to match human work on a substantial share of economically valu
arXiv:2609.21595v1 Announce Type: new Abstract: In-context learning using Large Language Models (LLMs) offers a compelling path to training-free post-OCR correction, yet its effectiveness for Devanaga
arXiv:2603.05807v2 Announce Type: replace Abstract: Event cameras are rapidly rising in popularity for robotic and computer vision tasks because their sparse activation delivers energy-efficient, high
arXiv:2609.21899v1 Announce Type: new Abstract: Best-of-n (BoN) sampling is a simple yet effective inference-time alignment method, but hard maximization provides only coarse control over the trade-of
arXiv:2601.06848v2 Announce Type: replace Abstract: Multimodal aspect-based sentiment analysis (MABSA) aims to identify aspect-level sentiments by jointly modeling textual and visual information, whic
arXiv:2609.21629v1 Announce Type: new Abstract: Multi-Channel imaging (MCI) data differs fundamentally from natural images, as each channel records a semantically distinct signal rather than a colour
arXiv:2609.20897v1 Announce Type: cross Abstract: We study a minimal classification problem: Given independent labeled observations Xsim P and Zsim Q from two unknown distributions P,Q, and given an i
arXiv:2509.25252v3 Announce Type: replace Abstract: 'The greatest enemy of knowledge is not ignorance, it is the illusion of knowledge.' Large Language Models have conquered natural language but remai
arXiv:2609.21296v1 Announce Type: cross Abstract: Fairness research on language models involves measuring bias, applying mitigation methods, and examining the evidence on which an evaluation rests. Ex
arXiv:2609.21358v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models pre-trained on large-scale, closed datasets have demonstrated remarkable success across diverse robotic manipulation
arXiv:2609.21306v1 Announce Type: new Abstract: A common requirement across organizations is to have a tool that can identify file types based on their contents, particularly in the cybersecurity doma
arXiv:2603.17201v2 Announce Type: replace Abstract: Visual SLAM systems combine visual tracking with global loop closure to maintain a consistent map and accurate localization. Loop closure is a compu
arXiv:2609.21057v1 Announce Type: new Abstract: Federated learning (FL) enables collaborative model training without sharing raw data, but its performance degrades under non-IID data and stochastic cl
arXiv:2609.21829v1 Announce Type: cross Abstract: Clustering high-dimensional data is a fundamental task in unsupervised machine learning with applications to a variety of domains. In the centralized
arXiv:2609.21216v1 Announce Type: cross Abstract: Vision-language-action (VLA) policies based on flow matching generate action chunks through repeated evaluations of an action expert. Increasing the n
arXiv:2609.21354v1 Announce Type: new Abstract: High-speed tracking of small, fast-moving organisms in their natural environments is important to better understand their behavior and ecology. Traditio
arXiv:2609.21228v1 Announce Type: cross Abstract: Vision-language-action (VLA) models built on pretrained vision-language models have demonstrated strong performance across diverse robotic manipulatio
arXiv:2609.21447v1 Announce Type: cross Abstract: Humanoid locomotion over complex terrain requires anticipating footholds that may no longer be visible at touchdown. Limited camera coverage and self-