Knowledge catalogue
arXiv:2607.05150v1 Announce Type: new Abstract: In this paper, we introduce Claim-Level Rubric Rewards (CuRe), a structured reward framework designed to address the reward-design bottleneck in reinfor
arXiv:2607.02841v1 Announce Type: cross Abstract: End-to-end autonomous driving (E2E-AD) aims to directly map raw sensor information to driving actions. Recently, with the rapid advancement of multi-m
arXiv:2509.15330v2 Announce Type: replace Abstract: Recent advances in pre-training vision-language models (VLMs), e.g., contrastive language-image pre-training (CLIP) methods, have shown great potent
arXiv:2503.12755v3 Announce Type: replace Abstract: Artificial intelligence (AI) has significantly improved medical screening accuracy, particularly in cancer detection and risk assessment. However, t
arXiv:2607.02998v1 Announce Type: cross Abstract: Controllable generative models of 3D medical images can synthesize volumes with specified clinical attributes, but this demands samples that are simul
arXiv:2607.03693v1 Announce Type: new Abstract: Vision-language-action (VLA) models have advanced generalist robotic manipulation, yet real-world deployment reveals a fundamental challenge: robots are
arXiv:2607.05101v1 Announce Type: new Abstract: The application of machine learning-based predictive algorithms to Anti-Money Laundering (AML) has grown rapidly, driven by the vast volume of financial
Diana Novak Jones / Reuters: Court filing: Meta says four US states seek 1.4T over claims it designed Facebook and Instagram to addict youth and misled the public; its market cap is ~1.5T — Meta Platf
arXiv:2603.10494v2 Announce Type: replace Abstract: Evidence-grounded generation produces summaries whose claims should be supported by supplied evidence, but claim-level verifiers provide noisy feedb
arXiv:2607.04432v1 Announce Type: cross Abstract: A student model trained on pure uniform noise can still inherit its teacher's digit-classification ability, provided the two share initialization. Pre
arXiv:2607.02567v1 Announce Type: cross Abstract: Radio frequency fingerprint identification (RFFI) provides a physical-layer credential for Internet of Things devices, but open-set decisions become f
arXiv:2607.03570v1 Announce Type: new Abstract: Robot manipulation policies are typically tied to specific robotic hand embodiments, limiting the transfer of learned behaviors across platforms with di
arXiv:2607.04029v1 Announce Type: new Abstract: Recent hallucination detection techniques in large language models (LLMs) focus on directly extracting features from a model's internal representations
arXiv:2607.03529v1 Announce Type: new Abstract: Compliance is essential for dexterous manipulation, yet existing solutions often rely on external tactile or force sensors that are costly, fragile, and
arXiv:2607.02601v1 Announce Type: new Abstract: Zero-Shot Learning (ZSL) facilitates knowledge transfer via shared semantic spaces. However, a critical bottleneck in this paradigm is Semantic Entangle
arXiv:2607.04389v1 Announce Type: new Abstract: It is increasingly common to aggregate predictions from multiple LLMs, each with domain expertise or access to private tools and data, to improve collec
arXiv:2602.04853v2 Announce Type: replace Abstract: Large language models often struggle to recognize their knowledge limits in closed-book question answering, leading to confident hallucinations. Whi
arXiv:2607.04278v1 Announce Type: cross Abstract: We propose the first deep learning algorithm, the Certainty Equivalent Learning (CEL) algorithm, for solving high-dimensional discrete-time dynamic pr
arXiv:2607.04761v1 Announce Type: new Abstract: Real-time, text-promptable 4D reconstruction is indispensable for autonomous surgical interaction. Severe misalignment between semantic meaning and phys
arXiv:2607.03478v1 Announce Type: new Abstract: Post-training of frontier language models is conducted on curated task suites, and inevitably leaves a distribution shift between training and deploymen
arXiv:2607.03161v1 Announce Type: cross Abstract: In selective deployment, practitioners act only on a model-chosen subset of individuals based on predicted conditional average treatment effects, but
arXiv:2606.05242v2 Announce Type: replace-cross Abstract: Stochastic gradient Langevin algorithms often use tamed denominators to stabilize superlinear drifts. This paper shows that when the denominat
arXiv:2607.04665v1 Announce Type: new Abstract: Zero-shot composed image retrieval (ZS-CIR) aims to retrieve a target image from a multimodal query consisting of a reference image and an edit text des
arXiv:2607.03899v1 Announce Type: new Abstract: Diffusion models have become a dominant paradigm for conditional image generation, yet existing approaches generally follow two directions: task-specifi
arXiv:2607.05064v1 Announce Type: new Abstract: Reinforcement learning in real world environments often suffers from severe performance degradation due to delayed feedback. Existing approaches typical
arXiv:2607.04599v1 Announce Type: new Abstract: Accurate 3D medical segmentation is limited by anatomical variability and high computational costs. While knowledge distillation (KD) offers a route for
arXiv:2303.08777v3 Announce Type: replace-cross Abstract: Cross-validation is one of the most widely used tools for risk estimation and model selection in statistics and machine learning, yet its theo
arXiv:2508.19573v2 Announce Type: replace Abstract: Anomaly detection in medical images is challenging due to limited annotations and the domain gap. Existing reconstruction-based methods often rely o
arXiv:2607.03009v1 Announce Type: new Abstract: Background: Foundation models (FMs) trained on large-scale unlabeled physiological data have emerged as a promising paradigm for medical artificial inte
arXiv:2607.04681v1 Announce Type: cross Abstract: Embodied Chain-of-Thought has emerged as a promising mechanism to enhance robot decision-making and interpretability in black-box Vision-Language Acti
arXiv:2607.04428v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) generate text by iteratively denoising a masked sequence, offering a parallel alternative to autoregressive mo
arXiv:2607.02561v1 Announce Type: cross Abstract: Consumer depth sensors such as the LiDAR scanner on recent iPhones provide metric range, but their useful range is short and their returns are sparse.
arXiv:2607.04927v1 Announce Type: cross Abstract: World Action Models (WAMs) provide a promising alternative to Vision-Language-Action (VLA) policies by using video-based world modeling as dense super
arXiv:2607.03397v1 Announce Type: new Abstract: Text-to-Image diffusion models often propagate harmful bias inherited from the training data. Existing bias mitigation techniques typically intervene on
arXiv:2508.16170v2 Announce Type: replace-cross Abstract: MultiModal Recommendation (MMR) systems have emerged as a promising solution for improving recommendation quality by leveraging rich item-side
arXiv:2506.09740v2 Announce Type: replace-cross Abstract: Diffusion models excel at image generation. Recent studies have shown that these models not only generate high-quality images but also encode
arXiv:2607.04490v1 Announce Type: new Abstract: Facial expression recognition (FER) is crucial for social interaction in mixed reality environments that employ head-mounted displays (HMD). However, co
arXiv:2508.09629v2 Announce Type: replace Abstract: We revisit the role of texture in monocular 3D hand reconstruction, not as an afterthought for photorealism, but as a dense, spatially grounded cue
arXiv:2607.04862v1 Announce Type: new Abstract: Accurate extreme precipitation forecasting is critical for disaster mitigation but remains challenging for numerical weather prediction (NWP) models due
arXiv:2506.05716v2 Announce Type: replace-cross Abstract: Deep Q-Networks (DQN) can suffer from overestimation bias because bootstrapped targets use a maximisation operation over noisy value estimates
arXiv:2607.03168v1 Announce Type: cross Abstract: Entropy regularization is widely used in continuous-time reinforcement learning (RL) to reduce sensitivity to environmental perturbations, yet its rob
arXiv:2607.04416v1 Announce Type: new Abstract: Sri Lanka has experienced a decade of progressive forest degradation and rising atmospheric pollution, yet district-level respiratory admissions have pa
arXiv:2607.02646v1 Announce Type: cross Abstract: We present EVA-Client, an open-source framework for deployment, data collection, and evaluation of trained manipulation policies on real robots. Sitti
arXiv:2503.02368v4 Announce Type: replace-cross Abstract: While guided decoding, especially value-guided methods, has emerged as a cost-effective alternative for controlling language model outputs wit
arXiv:2607.03146v1 Announce Type: new Abstract: Vision-language-action (VLA) models open a new path toward intuitive robot control by directly linking perception, language, and action in a single end-
arXiv:2508.04928v5 Announce Type: replace-cross Abstract: We propose a method to extend foundational monocular depth estimators (FMDEs), trained on perspective images, to fisheye images. Despite being
arXiv:2509.15206v3 Announce Type: replace Abstract: The high memory demands of generative language models have drawn attention to quantization, which reduces memory usage by mapping model weights to l
arXiv:2510.15686v2 Announce Type: replace Abstract: Learning coordinated behaviors for multi-robot systems from only a few demonstrations is difficult because temporal task dependencies and spatial tr
arXiv:2607.04019v1 Announce Type: cross Abstract: Physical sensing and actuation noise floors should inform how much belief resolution a decision-making system can reliably use. We introduce Finite Re
arXiv:2607.04006v1 Announce Type: cross Abstract: We establish finite-sample closed-loop stability guarantees for Model Predictive Path Integral (MPPI) control applied to discrete-time Linear Time-Inv
arXiv:2607.05375v1 Announce Type: cross Abstract: Occupancy ratios correct distribution shift in offline reinforcement learning and are central to off-policy evaluation. Existing primal-dual and minim
arXiv:2607.03509v1 Announce Type: new Abstract: Recent progress in large-scale generative models has substantially advanced video generation, yet existing methods remain constrained by a rigid inferen
arXiv:2607.04750v1 Announce Type: new Abstract: We present FM-ChangeNet, a pathwise-supervised framework for change detection that reformulates bi-temporal reasoning as continuous transport in feature
arXiv:2607.04125v1 Announce Type: new Abstract: Small object detection in Unmanned Aerial Vehicle (UAV) imagery remains challenging under adverse conditions, including complex weather, low illuminatio
arXiv:2607.05396v1 Announce Type: cross Abstract: Real-world robot deployment rarely maintains the training-stage camera setup, where cameras often experience repositioning or remounting depending on
arXiv:2607.04691v1 Announce Type: new Abstract: While controllable image generation has made significant strides by incorporating visual reference conditions, existing methods predominantly operate as
arXiv:2607.03792v1 Announce Type: cross Abstract: Vision-and-Language Navigation (VLN) agents may satisfy conventional success criteria while still failing to establish reliable object-level grounding
Full clip of my presentation of the Independent International Scientific Panel’s preliminary report at the opening ceremony yesterday: https://webtv.un.org/en/asset/k1y/k1yd3dlebq?kalturaSeekFrom=3260
arXiv:2607.04422v1 Announce Type: cross Abstract: Recent NVFP4 pretraining methods mainly target transformer linear layers, leaving optimizer states, optimizer arithmetic and attention underexplored i
arXiv:2607.04607v1 Announce Type: cross Abstract: The rapid advancement of AI-generated videos poses increasing security risks and calls for robust detectors with strong cross-domain generalization. A