Knowledge catalogue
arXiv:2606.08833v1 Announce Type: new Abstract: We introduce Contrast Sensitive Flow (CSFlow), a weighting scheme that connects the human eye's Contrast Sensitivity Function (CSF) to the iterative den
arXiv:2606.09572v1 Announce Type: cross Abstract: Vision-language-action models have shown strong promise for robot manipulation, yet raw language is primarily needed to specify task intent rather tha
arXiv:2606.09638v1 Announce Type: new Abstract: Differential equations play a critical role in scientific discovery because they provide a mathematical framework to describe the behaviour of physical
arXiv:2606.09615v1 Announce Type: cross Abstract: Dexterous manipulation presents substantial challenges for imitation learning due to its high-dimensional action space and complex contact-rich dynami
arXiv:2606.09758v1 Announce Type: cross Abstract: Parametric imitation learning via behavior cloning can suffer from poor generalization to out-of-distribution states due to compounding errors during
arXiv:2507.00260v3 Announce Type: replace-cross Abstract: When predictors are statistically dependent, the appropriate definition of feature importance depends on the operational goal. Conditional-inc
arXiv:2606.09725v1 Announce Type: new Abstract: Disentanglement, the separation of factors of variation in data using neural networks, remains a long-standing challenge in machine learning. Prior work
arXiv:2606.08596v1 Announce Type: new Abstract: Constructing efficient and reliable policies to assist humans is indispensable for human-AI collaboration. Existing methods mainly follow two lines of w
arXiv:2606.09388v1 Announce Type: new Abstract: Deploying safe large language models (LLMs) on resource-constrained edge devices presents a critical challenge: while dual-model systems combining LLMs
arXiv:2606.08974v1 Announce Type: new Abstract: Large reasoning models (LRMs) have attracted increasing attention for their ability to solve complex mathematical problems by generating extended reason
arXiv:2606.08532v1 Announce Type: new Abstract: A scientific hypothesis is the first step in research and undergoes experimental validation, yet it also reflects a deep understanding of and reasoning
arXiv:2606.05781v2 Announce Type: replace Abstract: Deploying frontier large language models (LLMs) for domain-specific structured evaluation tasks incurs prohibitive latency, cost, and data-privacy o
arXiv:2606.09378v1 Announce Type: new Abstract: Clinical ultrasound images often contain artificial markers, such as measurement calipers and text, to assist diagnostic interpretation and comparison.
arXiv:2606.09539v1 Announce Type: new Abstract: Spatio-temporal graph neural networks (STGNNs) have become the dominant approach for traffic prediction, yet their computational requirements pose chall
arXiv:2606.09243v1 Announce Type: cross Abstract: Estimating full-hand grasp pressure from egocentric video is critical for immersive VR and robotic manipulation, yet dense tactile sensing often relie
arXiv:2606.09525v1 Announce Type: cross Abstract: During instruction fine-tuning (IFT), large language models (LLMs) learn to follow instructions by using the provided context to answer a query. While
arXiv:2606.08205v1 Announce Type: new Abstract: Feed-forward 3D reconstruction models have recently shown strong generalization across diverse scenes, yet most of them recover geometry only up to an u
arXiv:2606.09234v1 Announce Type: cross Abstract: Recent state-of-the-art (SOTA) text-to-speech (TTS) systems typically adopt a cascaded pipeline consisting of a speech tokenizer, an autoregressive la
arXiv:2606.08908v1 Announce Type: cross Abstract: Semiconductor lithography inspection requires reliable detection of small pattern defects such as bridge, burr, pinch, and contamination. In this stud
arXiv:2606.08896v1 Announce Type: new Abstract: Large-scale retail and industrial forecasting systems contain many heterogeneous time series whose lifecycle, sparsity, volatility, seasonality, spectra
arXiv:2606.08653v1 Announce Type: cross Abstract: Action-supervised fine-tuning of vision-language-action (VLA) policies fits demonstrations effectively but constrains only the directions that change
arXiv:2606.09079v1 Announce Type: cross Abstract: Conventional LLMs keep the full KV cache loaded during decoding, causing a severe GPU memory bottleneck for ultra-long context serving. In this report
arXiv:2601.05212v2 Announce Type: replace Abstract: Brain Magnetic Resonance Imaging (MRI) plays a central role in studying neurological development, aging, and diseases. One key application is Brain
arXiv:2603.03292v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) exhibit high reasoning capacity in medical question-answering, but their tendency to produce hallucinations and o
arXiv:2512.20978v2 Announce Type: replace-cross Abstract: Language Model (LM)-based generative modeling has emerged as a promising direction for TSE, offering potential for improved generalization and
arXiv:2605.12213v2 Announce Type: replace Abstract: LLM-based conversational AI agents struggle to maintain coherent behavior over long horizons due to limited context. While RAG-based approaches are
arXiv:2606.09476v1 Announce Type: new Abstract: Hindsight relabeling usually turns achieved future states into exact goals, which can overconstrain offline robot learning when task success depends onl
arXiv:2606.08302v1 Announce Type: new Abstract: Visual Autoregressive (VAR) models adopt a next-scale prediction paradigm, offering high-quality generation with substantially fewer decoding steps. How
arXiv:2606.07690v1 Announce Type: cross Abstract: Finetuning data selection requires balancing two competing goals: selecting examples that improve the downstream objective, and doing so without repea
arXiv:2606.08051v1 Announce Type: new Abstract: Financial transaction processing requires extracting structured merchant information from noisy, abbreviated bank transaction strings at scale. Our curr
I'm really not interested in testing a new closed-weight model in the expensive tier. What's the point? I know what will happen: 1. They present the model. 2. The model beats the competition on benchm
arXiv:2606.08029v1 Announce Type: new Abstract: Object navigation requires a robot to search for an unobserved target in an unknown environment by deciding where to explore next under partial observab
arXiv:2606.09764v1 Announce Type: new Abstract: A useful phone agent needs to be personally intelligent. It should reason over a user's identity, history, and preferences as they exist on the device,
Ideogram 4.0 supports inpainting workflows , and Magic Fill is its inpainting tool that allows editing specific regions of images to replace objects, add text, fix imperfections, and change background
arXiv:2606.07616v1 Announce Type: cross Abstract: Scaling laws provide a fundamental framework for understanding the performance of Language Models (LMs), yet deriving them requires prohibitively expe
arXiv:2606.07819v1 Announce Type: new Abstract: Recently, the efficiency of Large Language Models (LLMs) deployment has become a critical concern in practical applications. While post-training quantiz
arXiv:2606.07686v1 Announce Type: cross Abstract: Physics-Informed Neural Network (PINN) is a way of including knowledge in the form of equations in Machine Learning methods. Beyond equations, knowled
arXiv:2606.09314v1 Announce Type: new Abstract: Generating high-quality dexterous grasps remains challenging for learning-based methods, which often depend on carefully tuned contact losses or costly
arXiv:2606.07923v1 Announce Type: cross Abstract: With the advent of Large Language Models (LLMs), many database systems introduced semantic operators that enabled analytical queries over unstructured
arXiv:2606.08657v1 Announce Type: cross Abstract: Diffusion-based visuomotor policies operating directly in raw action spaces conflate scene comprehension with trajectory generation within a single de
arXiv:2606.08641v1 Announce Type: new Abstract: The processing of gigapixel whole slide images within vision language models faces a major difficulty due to an excessive number of visual tokens. Exist
arXiv:2606.08751v1 Announce Type: new Abstract: Accurate quantification and uptake measurement in PET are critical for assessing disease progression and supporting clinical decision-making. While high
arXiv:2512.20591v3 Announce Type: replace Abstract: Contact often occurs without macroscopic surface deformation, such as during interaction with liquids, semi-liquids, or ultra-soft materials. Howeve
arXiv:2606.08153v1 Announce Type: cross Abstract: Detecting anomalies in large-scale system logs is critical for the reliability and security of modern computing infrastructure. We present LogNEO, a l
arXiv:2606.08676v1 Announce Type: cross Abstract: AI coding assistants have significantly improved developer productivity by automatically suggesting code that aligns with user intent, and many of the
arXiv:2606.08744v1 Announce Type: new Abstract: Global LiDAR localization is a fundamental task for autonomous navigation systems. Recent methods perform Scene Coordinate Regression (SCR) and achieve
arXiv:2606.08305v1 Announce Type: cross Abstract: Externally controlled survival trials are increasingly used when concurrent randomized controls are infeasible, particularly in oncology and rare-dise
arXiv:2606.09483v1 Announce Type: cross Abstract: Long-term memory for an LLM agent is more than retrieving the right passage at the right time. Current memory systems collapse belief revision, causal
arXiv:2606.07669v1 Announce Type: cross Abstract: Deploying Video Anomaly Detection (VAD) in real-world surveillance faces a fundamental tension between the demand for high-level semantics to ensure e
arXiv:2510.06052v2 Announce Type: replace Abstract: Reasoning models enhance performance by tackling problems in a step-by-step manner, decomposing them into sub-problems and exploring long chains of
arXiv:2606.07654v1 Announce Type: cross Abstract: Multi-vector visual document retrievers achieve strong fine-grained matching by representing each page with multiple vectors from deep Vision-Language
arXiv:2606.07585v1 Announce Type: cross Abstract: This thesis addresses group emotion recognition (GER) in-the-wild with a focus on privacy preservation. Unlike traditional emotion recognition methods
arXiv:2606.08535v1 Announce Type: new Abstract: Remote sensing applications for environmental monitoring and disaster management are frequently constrained by a spatial--temporal trade-off: imagery wi
arXiv:2606.09692v1 Announce Type: cross Abstract: Delegation-scoped execution is not identifiable from standard observables: audit logs and execution traces can be identical under multiple incompatibl
arXiv:2512.03606v2 Announce Type: replace Abstract: Accurate marine wind forecasts are essential for safe navigation, ship routing, and energy operations, yet they remain challenging because observati
arXiv:2606.09457v1 Announce Type: new Abstract: Embodied policies typically map current observations directly to actions, leaving candidate-action consequences implicit. World models provide predictiv
arXiv:2606.09156v1 Announce Type: new Abstract: Autoregressive (AR) models have demonstrated strong potential in visual generation, offering superior performance with simple architectures and optimiza
arXiv:2606.08514v1 Announce Type: new Abstract: Although video virtual try-on (VVT) has achieved significant progress, existing methods still exhibit two fundamental limitations: first, they are restr
arXiv:2606.09582v1 Announce Type: new Abstract: Recent work argues for using Gaussian differential privacy (GDP) to report the privacy guarantees in privacy-preserving machine learning. We provide pri
arXiv:2606.07589v1 Announce Type: new Abstract: Sequential filtering pipelines are a common design pattern in large-scale systems, where a large population of items is progressively reduced by a seque