Knowledge catalogue
arXiv:2608.18182v1 Announce Type: new Abstract: Small NLP models, especially BERT-family encoders, remain important in industrial workloads such as classification, ranking, and retrieval even in the e
arXiv:2608.18982v1 Announce Type: new Abstract: Bioassay activity prediction is often data-limited because drug-discovery datasets rely on time-consuming and expensive wet-lab experiments for data gen
arXiv:2608.18108v1 Announce Type: cross Abstract: Large language models are being incorporated into sensitive and important decision-making processes across nearly all fields. While prior work studies
arXiv:2608.17095v1 Announce Type: new Abstract: Vision-language-action (VLA) driving models couple a reasoning stage with a diffusion-based trajectory decoder, but do not give a direct way to redirect
arXiv:2608.14822v1 Announce Type: cross Abstract: Vision-language-action (VLA) models have improved the flexibility and generality of robotic manipulation, yet they remain fragile to online disruption
arXiv:2608.14629v1 Announce Type: cross Abstract: As Large Language Models (LLMs) become the mainstay for information retrieval and summarization tasks, ensuring that they are always non-partisan and
arXiv:2608.14756v1 Announce Type: cross Abstract: Real-world EV charging data exhibit three interlocking pathologies: hardware fragmentation (network timeouts and billing resets split sessions), physi
arXiv:2608.13773v1 Announce Type: cross Abstract: Neural networks are increasingly deployed in high-stakes applications with growing privacy leakage concerns. We show that this privacy leakage can occ
arXiv:2608.12932v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models promise to bring end-to-end reasoning to autonomous driving, but their computational cost remains far too high for r
arXiv:2608.12209v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) have achieved remarkable progress, visual understanding and generation are typically treated as divergent
arXiv:2601.16083v2 Announce Type: replace-cross Abstract: Computing the conditional mode of a distribution, better known as the maximum a posteriori (MAP) assignment, is a fundamental task in probabil
arXiv:2608.12306v1 Announce Type: cross Abstract: Safe offline RL typically assumes access to dense per-step cost annotations, but in practice supervisors provide only trajectory-level stop-feedback:
arXiv:2307.03587v4 Announce Type: replace Abstract: In non-stationary linear contextual bandits, existing efficient algorithms typically rely on the Weighted Regularized Least-Squares (WRLS) estimator
arXiv:2603.04568v2 Announce Type: replace Abstract: Many real-world computer vision tasks, such as depth completion, must handle inputs with arbitrarily shaped regions of missing or invalid data. For
arXiv:2608.08644v1 Announce Type: new Abstract: We consider the problem of sampling compositional and discrete objects from a given unnormalized posterior distribution. Notably, recent studies have sh
arXiv:2608.06554v1 Announce Type: new Abstract: Hidden Markov models (HMMs) are widely used probabilistic models for discrete sequential data but can be limited when hidden dynamics are complex. Hidde
arXiv:2603.00393v2 Announce Type: replace-cross Abstract: Inverse problems constrained by partial differential equations are often ill-conditioned due to noisy, incomplete data or inherent non-uniquen
arXiv:2608.05560v1 Announce Type: cross Abstract: Timely anticipation of physical hazards is essential for real-world safety, yet existing MLLM evaluations focus on harmful content or general risks, l
arXiv:2608.04121v1 Announce Type: cross Abstract: Vision-based guidance of unmanned aerial vehicles (UAVs) toward unmanned ground vehicles (UGVs) supports cooperative aerial--ground robotics, but reli
arXiv:2608.04904v1 Announce Type: new Abstract: Multilingual large language models exhibit substantial performance differences across languages, while existing adaptation methods often require paramet
arXiv:2608.04930v1 Announce Type: cross Abstract: Bayesian causal discovery seeks to determine the posterior distribution of causal theories, which are interpreted as directed acyclic graphs (DAGs) th
arXiv:2512.04954v3 Announce Type: replace Abstract: We present a novel technique for amortized posterior estimation using Normalizing Flows trained with likelihood-weighted importance sampling. This a
arXiv:2608.00077v1 Announce Type: new Abstract: Visual-token pruning is usually judged by answer quality at a fixed retention budget. For text-rich multimodal large language models (MLLMs), this proto
arXiv:2608.00852v1 Announce Type: new Abstract: Understanding and controlling complex dynamical systems often requires executing thousands of numerical simulations across vast parametric landscapes, w
arXiv:2606.15782v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) have demonstrated strong capabilities in vision-language understanding and natural-language response
arXiv:2608.00019v1 Announce Type: new Abstract: Deploying large language models (LLMs) for operations research (OR) tasks remains challenging because correctness depends on a coherent modeling process
Artificial intelligence hardware startup Olix Computing Ltd. today announced that it has raised 312 million in funding. The Series C round included contributions from Arm Holding plc, Netflix Inc. co-
arXiv:2607.29398v1 Announce Type: new Abstract: Diffusion models have revolutionized generative tasks but incur high latency due to iterative denoising. While cache-based strategies accelerate inferen
arXiv:2607.27842v1 Announce Type: new Abstract: Diffusion models are widely used to generate high-quality images and videos, but their iterative denoising process remains computationally intensive. A
arXiv:2607.27564v1 Announce Type: new Abstract: Multi-image medical VQA is not merely a prompt-length problem; it is a fundamental challenge of agentic decision-making. Medical vision-language agents
arXiv:2607.26859v1 Announce Type: cross Abstract: The monitoring of business conduct risk is hindered by sparse, uneven, and visibility-biased data. Prior studies show that business conduct risk infor
arXiv:2607.25468v1 Announce Type: new Abstract: In picture-based agricultural insurance for smallholder farmers, missed damage detections carry substantially higher cost than false alarms: a farmer wh
arXiv:2603.05147v2 Announce Type: replace Abstract: Current research on Vision-Language-Action (VLA) models predominantly focuses on enhancing generalization through reasoning techniques. While effect
arXiv:2607.22804v1 Announce Type: cross Abstract: Accurate geological characterization of subsurface reservoirs from well log data is essential to support projects such as carbon capture and storage (
arXiv:2607.23052v1 Announce Type: cross Abstract: Dual-encoder vision-language models (VLMs) expose a similarity interface that enables zero-shot retrieval but fails compositional constraints: queries
arXiv:2607.22961v1 Announce Type: cross Abstract: Verbalized Machine Learning (VML) parameterizes a model as a natural-language prompt that an LLM evaluates as f(x; theta). The framework is interpreta
I wanted to know how cheap you can go and still run local models, so I ran Ollama CPU-only on a Youyeetoo X1S. It's a single-board x86 machine with a Celeron N5095 (Jasper Lake, 4C/4T, 15W), 16GB of R
arXiv:2607.20293v1 Announce Type: new Abstract: Diffusion policies achieve strong visuomotor control by iteratively denoising action chunks, but repeated denoising makes real-time deployment computati
arXiv:2607.19712v1 Announce Type: new Abstract: In RLHF pipelines, reward scoring blocks policy updates. Slow scoring bottlenecks the entire loop, since no update runs until every rollout gets a score
arXiv:2506.06488v3 Announce Type: replace Abstract: A key tool in developing safe AI models is data auditing, i.e., using statistical tools to determine whether harmful content may have been used in t
arXiv:2607.20205v1 Announce Type: cross Abstract: Low-rank adaptation (LoRA) has become a widely used parameter-efficient fine-tuning method for large language models. Since different modules and laye
arXiv:2505.14303v3 Announce Type: replace-cross Abstract: Using Resistive Random Access Memory (RRAM) crossbars in Computing-in-Memory (CIM) architectures offers a promising solution to overcome the v
arXiv:2607.13612v1 Announce Type: cross Abstract: Joint-Embedding Predictive Architectures (JEPAs) are the dominant design for latent world models, yet they are usually justified by empirical performa
arXiv:2607.12732v1 Announce Type: new Abstract: Robot motion planning is inherently multimodal, yet classical planners typically return only a single solution. Probabilistic formulations address this
This paper was accepted at the AI4TCI (Workshop on AI for Secure and Trustworthy Critical Infrastructure Systems) Workshop at the International Conference on Availability, Reliability and Security (AR
arXiv:2505.16456v3 Announce Type: replace Abstract: Recent advances in 3D content generation have amplified demand for dynamic models that are both visually realistic and physically consistent. Howeve
arXiv:2607.08444v1 Announce Type: cross Abstract: In this paper, we study quantile-based distributional reinforcement learning from the perspective of statistical efficiency. We focus on distributiona
arXiv:2607.08122v1 Announce Type: new Abstract: Workload-based differentially private (DP) synthetic data methods privately measure aggregate queries and post-process the noisy answers into synthetic
arXiv:2603.24705v3 Announce Type: replace-cross Abstract: Discrete choice models are fundamental tools in management science, economics, and marketing for understanding and predicting decision-making.
arXiv:2304.03388v2 Announce Type: replace Abstract: Deep Neural Networks (DNNs) have become ubiquitous for their ability to solve problems across various domains, including computer vision, natural la
arXiv:2511.13726v2 Announce Type: replace-cross Abstract: We propose RT (Refine Thought), a method that can enhance the semantic reasoning ability of text embedding models. The method obtains the fina
arXiv:2607.06583v1 Announce Type: cross Abstract: DNA methylation (DNAm) serves as one of the most robust molecular biomarkers of biological aging. While conventional epigenetic clocks accurately pred
arXiv:2511.21245v3 Announce Type: replace Abstract: Monocular 3D face reconstruction estimates a 3D morphable model (3DMM) representation from a single image, providing geometry-aware expression codes
Chip startup SambaNova Inc. today announced that it has raised 1 billion in funding at a 11 billion valuation. General Atlantic led the Series F round with contributions from more than a dozen others.
arXiv:2607.04244v1 Announce Type: new Abstract: This report describes our approach to the Efficient Qwen Competition, where the goal is to enable low-latency serving of Qwen3.5-4B on a resource-constr
arXiv:2511.15409v2 Announce Type: replace Abstract: We present a class of algorithms for state estimation in nonlinear, non-Gaussian state-space models. Our approach is based on a variational Lagrangi
arXiv:2607.01313v1 Announce Type: cross Abstract: In practice, most commercial LLM providers do not publicly release details of underlying LLM architectures. However, prior work has shown that given l
arXiv:2607.01276v1 Announce Type: cross Abstract: Embedding models are essential components of modern Information Retrieval (IR) systems, yet they are typically hidden behind APIs. Recent works have s
arXiv:2607.01759v1 Announce Type: cross Abstract: Open-vocabulary object detection aims to localize and classify objects beyond the fixed set of categories seen dur ing training. Recent open-vocabular
arXiv:2607.01674v1 Announce Type: new Abstract: In multi-source ECG deployment, models may need to incorporate new data sources when earlier raw ECGs cannot be retained or replayed. Freezing a pretrai