Knowledge catalogue
arXiv:2609.27760v1 Announce Type: cross Abstract: Federated learning enables distributed training of a shared model without requiring clients to share their raw data. However, its reliance on the inte
Banger paper introducing Jev-as-a-Judge. The overall finding is that you want to use a cheap judge for most of your evals and send only the uncertain calls to a frontier model. This paper measures how
arXiv:2609.28339v1 Announce Type: new Abstract: Pretrained generative Diffusion Transformers (DiTs) capture rich pixel-level visual and language-conditioned structure through large-scale image and vid
arXiv:2609.27356v1 Announce Type: new Abstract: A region can overlap a target object yet contribute more to another class. We test regions selected by Cluster-based Concept Importance (CCI) in frozen
arXiv:2603.19713v2 Announce Type: replace Abstract: Even when it is difficult to assign absolute class labels to individual instances, relational information may still be available, such as whether tw
arXiv:2603.27597v2 Announce Type: replace Abstract: Research on artificial consciousness increasingly shifts evaluation from behaviour to internal architecture. Theory-based indicators are used to upd
arXiv:2609.27468v1 Announce Type: new Abstract: Action-chunked vision-language-action (VLA) policies improve inference efficiency, but limited feedback within committed action chunks can lead to accum
arXiv:2609.27242v1 Announce Type: cross Abstract: LLMs can generate programs for ARC-AGI-2 tasks, but the provided compute only allows a small number of attempts to generate, debug and validate soluti
arXiv:2609.28250v1 Announce Type: new Abstract: At test time, large language models (LLMs) can encode historical information in activation memory (i.e., KV caches) and parametric memory (i.e., updated
arXiv:2609.27439v1 Announce Type: new Abstract: Delayed acoustic positioning packets constrain historical navigation states, but a current-time update evaluates them against a mismatched state, wherea
arXiv:2609.28165v1 Announce Type: new Abstract: Multimodal learning (MML) falls into the optimization dilemma due to the modality imbalance phenomenon, leading to suboptimal overall performance in pra
arXiv:2609.28427v1 Announce Type: new Abstract: Personalizing exoskeleton assistance across operating conditions is constrained by the time and physical effort required to collect user feedback. We ex
arXiv:2609.28471v1 Announce Type: new Abstract: Our results show that contrastive learning outperforms a classification-based approach to authorship verification under the tested settings. We identify
arXiv:2609.27381v1 Announce Type: new Abstract: Contact detection during robotic manipulation allows robots to recognize unexpected contact and adapt their motion accordingly. However, in low-cost rob
arXiv:2609.28430v1 Announce Type: new Abstract: This work addresses continuous depression-severity score prediction from clinical interview transcripts under data scarcity. We propose a sequential low
arXiv:2609.27115v1 Announce Type: new Abstract: A face recognition model links two images of a person recorded on separate occasions when their embedding similarity exceeds an operating threshold. We
arXiv:2609.28159v1 Announce Type: new Abstract: Standard contrastive learning frameworks are mainly designed from a semantic perspective, yet learning 2D visual representations that preserve 3D spatia
arXiv:2609.27099v1 Announce Type: new Abstract: Surgical robots require highly dexterous and compact robotic systems capable of operating effectively within confined anatomical spaces. However, due to
arXiv:2609.28352v1 Announce Type: new Abstract: This study highlights the distribution of Standard Arabic (SA; H(igh) variety) and Colloquial Arabic (CA; L(ow) variety) across X and Facebook. 16754 pu
arXiv:2609.27233v1 Announce Type: new Abstract: Transformer language models process sequences token by token in an autoregressive manner, making growing contexts increasingly expensive. Yet many adjac
arXiv:2609.27194v1 Announce Type: new Abstract: Prototype-based neural networks provide inherent interpretability through case-based reasoning, yet suffer from critical limitations: prototypes converg
arXiv:2609.27043v1 Announce Type: new Abstract: Large language models have allowed the rapid deployment of pedagogical annotations corresponding to constructs of interest, allowing a natural language
arXiv:2609.27594v1 Announce Type: new Abstract: We study the problem of computational efficiency for linear bandits in high-dimensional settings with a finite arm set. In linear bandits, the increase
arXiv:2609.27784v1 Announce Type: cross Abstract: Semi-structured documents are ubiquitous in scientific reports, financial statements, and technical manuals. Question answering over such documents re
arXiv:2603.09222v2 Announce Type: replace Abstract: Efficient context compression is critical for retrieval-augmented question answering in resource-constrained settings, where long retrieved contexts
arXiv:2609.27950v1 Announce Type: cross Abstract: The emergence of multi-class malware attacks such as ransomware, spyware, trojans, etc., presents an increasing and serious threat to cybersecurity, p
arXiv:2609.27197v1 Announce Type: new Abstract: Minimum Risk Training (MRT) enables neural machine translation models to directly optimize sequence-level evaluation metrics instead of relying only on
arXiv:2609.27815v1 Announce Type: cross Abstract: Dynamic contrast-enhanced (DCE) imaging is the gold standard technique for the detection and characterization of breast cancer using magnetic resonanc
arXiv:2609.27749v1 Announce Type: new Abstract: The surge in AI-assisted generation of educational materials has outpaced our capacity to validate their pedagogical quality. Automated evaluation using
arXiv:2609.27389v1 Announce Type: cross Abstract: Audio language models understand what is said far better than how it sounds. Closing this gap takes more than data. Detailed acoustic annotation is co
arXiv:2609.27337v1 Announce Type: cross Abstract: Open RAN (O-RAN) slicing xApps must adapt resource allocations to changing channel conditions and traffic demands while meeting service-level agreemen
arXiv:2609.28150v1 Announce Type: new Abstract: Closed-loop revision is increasingly used in large language model (LLM) applications, but failures may reflect incomplete feedback or ineffective respon
arXiv:2609.26926v1 Announce Type: cross Abstract: Large-scale text annotation brings expert insight to millions of documents, often through a codebook that AI annotators follow. Developing a robust co
arXiv:2410.00848v2 Announce Type: replace-cross Abstract: A faster implementation of mixtures of Manly transformations is proposed. This method, called FastManly, uses Newton's method for optimization
arXiv:2609.27110v1 Announce Type: cross Abstract: Vision-language models (VLMs) are deployed as zero-shot judges of image aesthetics, and panels of several models are recommended, on thin evidence, as
arXiv:2609.28110v1 Announce Type: cross Abstract: Dental cone-beam computed tomography (CBCT) systems often employ detector configurations that provide a truncated field of view (FOV) that only captur
arXiv:2511.19486v3 Announce Type: replace-cross Abstract: Driven by recent advances in artificial intelligence, a growing literature has demonstrated the potential of using large language models (LLMs
arXiv:2609.27160v1 Announce Type: new Abstract: Unlike most intensely physical pursuits, surgical robotic teleoperation training focuses primarily on task outcomes rather than surgeon body posture or
arXiv:2609.27385v1 Announce Type: cross Abstract: Time-series foundation models (TSFMs) provide forecasts for operational decisions, but accuracy alone does not determine their value. Evaluating agent
arXiv:2609.27399v1 Announce Type: cross Abstract: Recent zero-shot text-to-speech (ZS-TTS) systems can reproduce a speaker's voice with high fidelity from only a few seconds of reference speech, raisi
arXiv:2609.28183v1 Announce Type: new Abstract: Electrocardiography (ECG) contains subject-specific morphology that supports biometric recognition, yet image-based performance depends on how the wavef
arXiv:2609.28414v1 Announce Type: cross Abstract: Latent world models that integrate a flow in a frozen self supervised latent space train stably and cheaply, yet silently lose the property manipulati
arXiv:2609.27264v1 Announce Type: new Abstract: We present GaussPDE, a framework that injects physically structured partial differential equation (PDE) dynamics into pretrained 3D Gaussian scenes with
arXiv:2609.28258v1 Announce Type: cross Abstract: Robotic assembly in high-mixture settings requires adaptable systems that can handle diverse parts, yet current approaches typically rely on policies
arXiv:2609.27848v1 Announce Type: new Abstract: The BIC-MAC challenge targets whole-body pseudo-CT synthesis from NAC-PET, Dixon MRI, and a 2D topogram for CT-less PET attenuation correction. We propo
arXiv:2609.28194v1 Announce Type: cross Abstract: Old-growth forests develop over centuries under minimal anthropogenic disturbance, producing structurally complex and biodiverse stands. In Europe, pr
arXiv:2511.22857v2 Announce Type: replace Abstract: Inverse rendering of indoor scenes remains challenging due to the ambiguity between reflectance and lighting, exacerbated by inter-reflections among
arXiv:2609.26806v1 Announce Type: cross Abstract: This paper presents a complete, structure-preserving port to Lean 4 of the Isabelle/HOL dataset accompanying Benzmuller and Scott's study of Godel's m
arXiv:2609.27278v1 Announce Type: new Abstract: Learning a sparse graph from scarce data is practically important but challenging. Motivated by the desirable combination of local sparsity and strong g
arXiv:2609.26822v1 Announce Type: new Abstract: Financial time series evolve across multiple temporal resolutions, challenging forecasting systems to incorporate newly available information without re
arXiv:2609.27593v1 Announce Type: cross Abstract: Concept erasure methods that operate via linear projection assume that features occupy separable subspaces. We show this assumption fails under dense
arXiv:2609.27154v1 Announce Type: new Abstract: In human-robot interaction, traditional interfaces such as joysticks and handheld tablets introduce latency into navigation tasks and require the operat
arXiv:2508.04899v3 Announce Type: replace Abstract: Reliable evaluation of machine learning models for neonatal seizure detection is critical for clinical adoption. Current practices often rely on inc
arXiv:2609.25244v2 Announce Type: replace-cross Abstract: Children increasingly interact with AI chatbots, making trust calibration essential to AI literacy. Prior research has examined children's tru
arXiv:2609.28177v1 Announce Type: cross Abstract: LLM leaderboard gains can reflect selection among privately evaluated model variants, yet neither the number of variants nor their dependence is publi
arXiv:2609.27462v1 Announce Type: new Abstract: Open-vocabulary 3D segmentation localizes objects from free-form text queries, but remains challenging in real image sequences: incomplete or noisy 2D s
arXiv:2609.27011v1 Announce Type: new Abstract: Target-oriented face de-identification models aim to anonymize the identity of a target individual across different images or video frames, such that th
arXiv:2609.28248v1 Announce Type: new Abstract: We present hyperbolix, an open-source library for hyperbolic deep learning in JAX, built on Flax NNX. To our knowledge, it is the first comprehensive, g
arXiv:2609.27893v1 Announce Type: cross Abstract: A blind image denoising framework based on an infinite directional lower semi-frame (DLSF) is proposed for additive white Gaussian noise. The model em
Impressive paper from Salesforce. It discusses the importance of good verifiers for RL environments. Only 35.8% of the environments in the cleanest public RL collection for terminal agents passed Sale