Knowledge catalogue
arXiv:2609.08123v1 Announce Type: cross Abstract: A robot that can be taught a new task from a handful of demonstrations has to work out for itself what it still cannot do, and then ask for exactly th
arXiv:2512.03936v2 Announce Type: replace Abstract: Autonomous driving planning systems perform nearly perfectly in routine scenarios using lightweight, rule-based methods but still struggle in dense
arXiv:2609.06898v1 Announce Type: cross Abstract: Byte Pair Encoding (BPE) constructs vocabularies through greedy pair merging, but the resulting merge order does not necessarily allocate a fixed mode
arXiv:2603.26483v2 Announce Type: replace Abstract: Medical edge-AI systems must operate under a difficult tension: delivering reliable diagnostic inference while running on devices with limited batte
arXiv:2609.05972v1 Announce Type: new Abstract: We present an efficient and robust method for 3D geometric reconstruction that is based solely on the camera-independent linear relationships among a gi
arXiv:2609.08330v1 Announce Type: new Abstract: Table detection is a core task in document analysis, supporting downstream applications such as information retrieval, document reconstruction, and visu
arXiv:2609.08381v1 Announce Type: new Abstract: Equivariant networks are commonly trained with Adam, yet recent work reports that matrix-structured optimizers such as Muon can perform better on these
arXiv:2609.06551v1 Announce Type: cross Abstract: Mobile vendors and application developers increasingly deploy LLMs on smartphones for diverse prefill-only services. Yet current systems rely mainly o
arXiv:2609.07893v1 Announce Type: cross Abstract: Deep learning is an efficient technique to monitor the real time welding process, reducing post-welding repairs and production delays. This paper leve
arXiv:2609.05905v1 Announce Type: cross Abstract: LLM agents are increasingly used for live forecasting, where they retrieve up-to-date information and produce estimates for unresolved future events.
arXiv:2609.06660v1 Announce Type: new Abstract: Accurate aerodynamic prediction is critical for designing fuel-efficient and safe transportation systems such as aircraft and automobiles, yet tradition
arXiv:2609.07497v1 Announce Type: new Abstract: Existing SLAM systems lack modeling of the functional relations required for fine-grained robotic interaction. Functional 3D scene graphs can represent
arXiv:2609.06823v1 Announce Type: new Abstract: The next generation of artificial intelligence systems will likely be natively temporal and multimodal in both inputs and outputs: able to converse, per
arXiv:2601.09233v3 Announce Type: replace Abstract: The prevailing post-training paradigm for Large Reasoning Models (LRMs)---Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL)-suffe
arXiv:2609.08607v1 Announce Type: new Abstract: We present GOLF, the first-place solution to the SHOW3D Interaction Field Estimation Challenge at HANDS@ECCV 2026. Given synchronized egocentric stereo
arXiv:2504.21323v3 Announce Type: replace-cross Abstract: Knowledge distillation is widely used to transfer behavior from a large teacher model to a smaller student. It is often assumed to be safe whe
arXiv:2609.07990v1 Announce Type: new Abstract: Sequential reinforcement learning (RL) solvers and global diffusion model (DM) solvers for neural combinatorial optimization exhibit complementary failu
arXiv:2603.25255v2 Announce Type: replace Abstract: Trajectory anomaly detection underpins applications from fraud detection to urban mobility analysis. Dense GPS methods preserve fine-grained evidenc
In my latest op-ed for @TIME, I discuss why the OpenAI Hugging Face cyber incident represents a turning point for AI safety. If we want to prevent more autonomous cyberattacks from threatening critica
arXiv:2609.08786v1 Announce Type: new Abstract: Hyperspectral unmixing decomposes mixed pixels into material endmembers and their abundances from contiguous spectral observations. In modular sensing p
arXiv:2505.17966v3 Announce Type: replace-cross Abstract: This paper evaluates single-view mesh reconstruction models for their potential in enabling instant digital twin creation for real-time planni
arXiv:2609.06955v1 Announce Type: new Abstract: Predicting hand--object interaction fields requires locating the nearest object-surface point for each hand joint, often from small and partially occlud
arXiv:2509.04772v2 Announce Type: replace Abstract: Timely floodwater depth estimates support road accessibility assessment and emergency response during urban flooding. Supervised vision methods ofte
arXiv:2609.06079v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) policies leverage pretrained vision-language models (VLMs) to guide action generation for robot control. VLMs provide hie
arXiv:2511.03032v3 Announce Type: replace Abstract: In the era of AI-driven science and engineering, we often want to design discrete objects in silico according to user-specified properties. For exam
arXiv:2609.08585v1 Announce Type: cross Abstract: Simulatability is an evaluation protocol for explanations that quantifies their usefulness by how well they help a user predict a task model's outputs
arXiv:2609.06341v1 Announce Type: new Abstract: Linear algebra provides the framework of concepts (matrix rank, singular value decomposition (SVD), and eigendecomposition) that modern artificial intel
arXiv:2609.05498v1 Announce Type: new Abstract: This technical report studies the local weak observability of a planar bicycle-model vehicle when vehicle pose, planar LiDAR extrinsic calibration, and
arXiv:2609.06476v1 Announce Type: new Abstract: Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires an embodied agent to navigate unseen environments by following natural langu
arXiv:2609.06469v1 Announce Type: new Abstract: Reinforcement learning (RL) across multiple domains can broaden the reasoning capabilities of large language models (LLMs), yet joint training often deg
arXiv:2609.05820v1 Announce Type: new Abstract: We study adaptive routing of prompts to large language model (LLM) experts to maximize response quality in an online setting with limited feedback. We f
arXiv:2609.06947v1 Announce Type: new Abstract: Flow matching, together with classifier-free guidance (CFG), is widely used in generative modeling, yet much of the theoretical understanding remains di
arXiv:2609.09145v1 Announce Type: new Abstract: We introduce Point4D, a feed-forward model for 4D reconstruction of long-range video sequences. Point4D is able to reliably infer dense per-point 3D tra
arXiv:2410.23667v2 Announce Type: replace Abstract: Neural differential equations offer a powerful approach for learning dynamical systems from data. However, they do not inherently respect known cons
arXiv:2609.07229v1 Announce Type: new Abstract: Vision-language models offer a promising approach for zero-shot anomaly detection (ZSAD). However, due to object-centric bias, normal and anomalous text
arXiv:2505.01862v4 Announce Type: replace Abstract: Adapting autonomous agents for real-world industrial, domestic, and other daily tasks is currently gaining momentum. However, in global or cross-lin
arXiv:2609.07414v1 Announce Type: new Abstract: Image relighting is traditionally tackled via complex inverse rendering pipelines, which suffer from ill-posed optimization, or single-image generative
arXiv:2501.10621v2 Announce Type: replace-cross Abstract: Driven by the need to address labor shortages and meet the demands of a rapidly growing population, robotic automation has become a critical c
arXiv:2602.01533v2 Announce Type: replace Abstract: Online handwritten character recognition leverages stroke order and dynamic features, which generally provide higher accuracy and robustness compare
arXiv:2509.23442v2 Announce Type: replace-cross Abstract: Convolutional Neural Networks have become a cornerstone of medical image analysis due to their proficiency in learning hierarchical spatial fe
arXiv:2504.08192v2 Announce Type: replace Abstract: Machine unlearning is a promising approach to improve LLM safety by removing unwanted knowledge from the model. However, prevailing gradient-based u
arXiv:2609.05850v1 Announce Type: new Abstract: Despite the significant efforts devoted to aligning large language models (LLMs) with human values and ensuring safe deployment, recent work has reveale
arXiv:2609.06385v1 Announce Type: new Abstract: Pretrained 3D generative models produce detailed geometry and appearance but are primarily designed for object-centric generation within a limited spati
arXiv:2609.06484v1 Announce Type: new Abstract: Planning with a generative model aims to estimate the value of a state using as few simulator calls as possible. SmoothCruiser achieves problem-independ
arXiv:2609.06296v1 Announce Type: new Abstract: Self-supervised sign language representation learning must model two properties not central to natural-image SSL: signs are produced by a small set of a
arXiv:2401.09895v3 Announce Type: replace Abstract: One of the fundamental challenges in cell microscopy (MS) image analysis is instance segmentation (IS), particularly when segmenting cluster regions
arXiv:2609.07445v1 Announce Type: new Abstract: Autonomous tugboating is central for automating maritime operations such as port logistics and vessel maneuvering, where multiple tugboats must cooperat
The fix: run the server detached/headless instead of keeping it attached to a console window. RTX 5090, ~27B NVFP4 model via ninfer: Terminal focused: 130–200 tok/s Terminal unfocused: 50–60 tok/s Cli
arXiv:2609.06186v1 Announce Type: new Abstract: Prioritized Sweeping (PS) accelerates model-based reinforcement learning by selecting backups according to Bellman residual magnitude. In nonstationary
arXiv:2601.10324v3 Announce Type: replace Abstract: Synthetic aperture radar (SAR) imagery exhibits intrinsic information sparsity due to its unique electromagnetic scattering mechanism. Despite the w
arXiv:2609.07148v1 Announce Type: cross Abstract: While Reinforcement Learning (RL) effectively incentivizes reasoning in Large Language Models, current pipelines are hindered by training instability
arXiv:2609.05550v1 Announce Type: new Abstract: Near-infrared (NIR) video is a promising modality for contactless sleep monitoring, but recent video-based sleep staging methods often use it as a route
arXiv:2601.13713v2 Announce Type: replace-cross Abstract: Software testing is crucial for ensuring the correctness and reliability of software systems. Automated generation of issue reproduction tests
arXiv:2512.12427v3 Announce Type: replace Abstract: Many aerial tasks involving quadrotors demand both instant reactivity and long-horizon planning for obstacle avoidance, energy efficiency, or trajec
arXiv:2601.02310v2 Announce Type: replace Abstract: High-Frequency trading (HFT) environments are characterised by large volumes of limit order book (LOB) data, which is notoriously noisy and non-line
arXiv:2602.13418v2 Announce Type: replace Abstract: Does natural language text have an intrinsic curvature? Language is increasingly modeled in curved geometries - hyperbolic spaces for hierarchy, mix
arXiv:2504.16450v4 Announce Type: replace Abstract: We derive a differential equation that governs the evolution of the generalization gap when a model is trained by gradient descent-based methods. Th
arXiv:2609.08341v1 Announce Type: new Abstract: On-Policy Distillation (OPD) facilitates the transfer of knowledge from domain expert to student in the post-training phase of Large Language Models (LL
arXiv:2511.13032v2 Announce Type: replace Abstract: We present Uni-Inter, a unified framework for human motion generation that supports a wide range of interaction scenarios: including human-human, hu
arXiv:2609.06729v1 Announce Type: new Abstract: Accurate 3D brain tumour segmentation from multi-modal Magnetic Resonance Imaging (MRI) is essential for clinical diagnosis and treatment planning. Exis