Knowledge catalogue
arXiv:2505.11884v3 Announce Type: replace Abstract: Face recognition performance based on deep learning heavily relies on large-scale training data, which is often difficult to acquire in practical ap
arXiv:2610.18082v1 Announce Type: new Abstract: Long-horizon agents often struggle to recover from failures whose causes lie several steps earlier, beyond what local reflection or backtracking can res
arXiv:2610.18593v1 Announce Type: new Abstract: Fairness constraints in predict-then-optimize pipelines are necessarily enforced on predicted outcomes hat{y}, since true outcomes y are unobserved at d
arXiv:2610.18260v1 Announce Type: new Abstract: Wearable fall detection is hampered by rare fall events, scarce labeled IMU data, and the cost of training deep models on large, imbalanced corpora. Exi
arXiv:2610.17841v1 Announce Type: cross Abstract: Evaluating fashion retrieval systems remains challenging due to the limited availability of benchmarks that capture the fine-grained, open-ended queri
arXiv:2610.15921v1 Announce Type: new Abstract: With ever increasing personalized large language model (LLM) services, the next question to answer is how to improve the quality of services/users' expe
arXiv:2610.16289v1 Announce Type: new Abstract: Quantization has emerged as one of the primary techniques for reducing the memory footprint of large language models during inference. A prominent examp
arXiv:2610.18839v1 Announce Type: new Abstract: This paper investigates offline Q-learning for finite-horizon Markov decision processes with Kullback-Leibler (KL) regularization. Recent studies have s
arXiv:2610.18451v1 Announce Type: cross Abstract: Large-scale expert parallelism (EP) has become the standard deployment configuration for Mixture-of-Experts (MoE) models in production. Meanwhile, the
arXiv:2610.14899v1 Announce Type: cross Abstract: The sudden growth in AI data centers is raising numerous environmental concerns. Low-frequency noise pollution is a concern for local residents, that
arXiv:2610.16694v1 Announce Type: new Abstract: Adversarial detection on evolving attributed graphs faces two challenges: fraud labels arrive late or not at all, and natural distributional drift erode
arXiv:2610.16845v1 Announce Type: cross Abstract: Standardizing a rare feature can help stochastic gradient descent learn its effect within a finite budget, but it also changes the noise cost of learn
arXiv:2601.22318v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly accessed as remotely hosted services by edge and enterprise clients that cannot run frontier models lo
arXiv:2610.16425v1 Announce Type: cross Abstract: In real-world scenarios, industrial processes can span multiple factories and goods are often produced at multiple sites, leading to a shared yet non-
arXiv:2605.06433v2 Announce Type: replace Abstract: Subgraph pattern detection is a fundamental graph mining task central to anti-money laundering (AML) in finance. However, state-of-the-art graph neu
arXiv:2610.17621v1 Announce Type: new Abstract: We propose FedLoRD, a personalized federated learning (PFL) method based on the low-rank structure of the differences between the global and personalize
arXiv:2610.16667v1 Announce Type: new Abstract: Accurate modelling of soft tactile sensors remains difficult because finite element methods (FEM) are computa- tionally expensive, while real-time simul
arXiv:2610.15307v1 Announce Type: new Abstract: Efficient neural architecture search (NAS) requires accurate performance estimation under limited evaluation budgets. Existing zero-cost proxies (ZCPs)
arXiv:2610.17951v1 Announce Type: new Abstract: Head circumference (HC) measured from 2D ultrasound is a routine marker of fetal growth, and automating it needs segmentations whose boundaries hold up
arXiv:2610.16840v1 Announce Type: new Abstract: Real-world systems often serve many objectives but can deploy only a few options, whose performance must be learned from noisy feedback. Modeling each o
A practical method for converting Figma theme evidence into an LLM handoff that fits an existing application and preserves accessibility.
Reuters: Filing: OpenAI says a staffer who joined Apple sent 100+ files to a personal account and made a presentation about an unreleased product to Apple leadership — An OpenAI employee who left the
arXiv:2610.17337v1 Announce Type: cross Abstract: Liveness requires a dynamical system to repeatedly accomplish a desired objective over time. In this work, we consider a particular form of liveness k
arXiv:2610.14579v1 Announce Type: cross Abstract: Embedding models underpin modern job-candidate matching: resumes, job descriptions, and queries are encoded as dense vectors, and recommendations come
arXiv:2601.22371v2 Announce Type: replace Abstract: Multi-fidelity (MF) regression often operates in regimes of extreme data imbalance, where the commonly-used Gaussian-process (GP) surrogates struggl
arXiv:2610.15595v1 Announce Type: new Abstract: In real-world indoor fire environments, visual degradation severely impairs instruction grounding, waypoint prediction, and long-horizon exploration in
arXiv:2610.16161v1 Announce Type: new Abstract: A fruitful approach towards understanding generalization in machine learning involves characterizing how models separate generalizable structure from id
arXiv:2605.05791v2 Announce Type: replace Abstract: Fitted Q-iteration (FQI) is well understood when the data come from a fixed distribution and the action set is finite, whereas value-based continuou
arXiv:2610.14982v1 Announce Type: new Abstract: Recurrent algorithmic reasoners are trained with per-step hints on small graphs and run for many more steps on large ones. On breadth-first search in SA
Every PC, one app. Fizgig finds your other computers on your network by itself. Train on the desktop's 5090 from your laptop, send a dataset across in one click, and see what every machine is training
arXiv:2610.17901v1 Announce Type: new Abstract: Long-context training of large language and multimodal models couples structured attention masks (document, prefix-LM, share-question, sliding-window, b
arXiv:2610.17552v1 Announce Type: new Abstract: Recent video super-resolution (VSR) models achieve efficient one-step generation through diffusion distillation. However, high-resolution inference rema
arXiv:2602.02481v2 Announce Type: replace Abstract: Likelihood-based policy gradient methods are the dominant approach for training robot control policies from rewards. These methods rely on different
arXiv:2610.14588v1 Announce Type: cross Abstract: Test-time sampling promises to turn one action prediction into a set of distinct executable candidates that a verifier can choose among. Downstream fi
arXiv:2610.16277v1 Announce Type: new Abstract: Prior avatar embodiment research has studied tracking completeness (how faithfully the body, hands, and face are sensed and reproduced) and personalized
arXiv:2610.18142v1 Announce Type: new Abstract: Prompt optimization and generator post-training are two complementary ways to improve text-to-video (T2V) generation, and recent systems increasingly tr
arXiv:2610.18030v1 Announce Type: new Abstract: Closed-loop evaluation of end-to-end (E2E) driving systems typically relies on generating sensor observations and re-processing them through the percept
arXiv:2610.16160v1 Announce Type: new Abstract: Recent advances in 3D reconstruction enable the extraction of temporally consistent 3D motion from RGB observations; however, current Vision-Language-Ac
arXiv:2610.16914v1 Announce Type: new Abstract: Intraoperative frozen-section diagnosis of central nervous system (CNS) lesions guides surgical decisions but is challenged by artefacts, diagnostic com
arXiv:2610.17707v1 Announce Type: new Abstract: Multimodal sarcasm detection has attracted increasing attention due to the widespread use of images and text on social media platforms. Existing studies
arXiv:2610.17818v1 Announce Type: new Abstract: We give the first adversarial linear bandit algorithm based on Follow-the-Perturbed-Leader (FTPL) that achieves sqrt{T} regret over general convex actio
arXiv:2610.17161v1 Announce Type: new Abstract: Teleoperation is widely used to collect high-quality demonstrations for robot learning. Dexterous manipulation, however, requires coordinated control of
arXiv:2610.18160v1 Announce Type: new Abstract: Robotic harvesting of cherry tomatoes in greenhouses remains challenging due to dense fruit clusters, delicate skin, and the need for gentle yet effecti
arXiv:2610.18852v1 Announce Type: new Abstract: Expert demonstrations show how to complete contact-rich tasks, but provide limited coverage of how interaction forces respond to different actions. Task
arXiv:2610.18118v1 Announce Type: new Abstract: Visually similar actions can produce contact loss, jamming, slippage, or irreversible damage, while tactile feedback may arrive after a critical transit
arXiv:2610.16890v1 Announce Type: cross Abstract: We introduce FORGE (Fast On-chip Rotor Generation for Experts), a procedural weight generation system for Sparse Mixture-of-Experts (MoE) inference. R
arXiv:2610.18650v1 Announce Type: new Abstract: Vision-language-action (VLA) policies perform manipulation tasks using camera images and language instructions, but object slip or visual occlusion can
arXiv:2610.17449v1 Announce Type: cross Abstract: Last-mile functional coverage closure for modern chip designs remains costly because a mature UVM environment exposes many controls while direct hits
arXiv:2610.14787v1 Announce Type: new Abstract: Online continual learning (OCL) requires a learner to acquire a sequence of tasks in a single pass over the data, and catastrophic forgetting of earlier
arXiv:2610.17503v1 Announce Type: new Abstract: Event logs are ubiquitous across real-world domains, including business processes, manufacturing workflows, healthcare, and many other operational syste
arXiv:2610.14951v1 Announce Type: new Abstract: Feed-forward geometric foundation models (GFMs) directly predict dense geometry and camera poses from batches of images. Emerging visual SLAM methods ch
arXiv:2610.16744v1 Announce Type: new Abstract: Video large language models (Video LLMs) encode each frame into hundreds of visual tokens, making video inference expensive. Existing methods reduce thi
arXiv:2610.18023v1 Announce Type: new Abstract: Graph fraud explanation generation emerges as an important task, which requires jointly leveraging graph structure and content information to produce hu
arXiv:2610.15284v1 Announce Type: new Abstract: Drug discovery requires efficient exploration of an astronomically large chemical space. Molecular graph diffusion models offer a promising approach to
arXiv:2610.14568v1 Announce Type: new Abstract: In autoregressive video generation, retaining all historical key-value (KV) states increases memory usage and per-step attention costs as videos grow lo
arXiv:2610.17639v1 Announce Type: new Abstract: Aesthetic image cropping improves composition by balancing subjects, context, and image boundaries. Large vision-language models bring semantic knowledg
arXiv:2610.14445v1 Announce Type: new Abstract: In film production, chroma keying composites an approved foreground performance into a new environment, but conventional workflows require coordinated b
arXiv:2610.17191v1 Announce Type: new Abstract: Linear-time sequence models typically store long-context information in a recurrent state. A fixed-size state limits how much information can be stored,
arXiv:2610.17859v1 Announce Type: new Abstract: Thermal-to-visible (T2V) face translation has important applications in nighttime biometric recognition, low-light surveillance, and human interpretatio
arXiv:2610.15922v1 Announce Type: new Abstract: Autoregressive (AR) video generation enables long-horizon synthesis but requires repeated forward passes through large diffusion transformers. Training-