Knowledge catalogue
Developer-centered artificial intelligence cloud provider Runpod Inc. today announced the launch of Flash, a software development kit and platform that removes the infrastructure overhead for deployin
arXiv:2604.25444v1 Announce Type: new Abstract: Large Language Models (LLMs) often fail to utilize their latent reasoning capabilities due to a distributional mismatch between ambiguous human inquirie
arXiv:2604.23278v1 Announce Type: new Abstract: The proliferation of agentic artificial intelligence has outpaced the conceptual tools needed to characterize agency in computational systems. Prevailin
arXiv:2604.23606v1 Announce Type: new Abstract: Lattice Hamiltonian systems underpin models across condensed matter, nonlinear optics, and biophysics, yet learning their dynamics from data is obstruct
arXiv:2604.24079v1 Announce Type: cross Abstract: Large Language Models (LLMs) reveal inherent and distinctive personas through dialogue. However, most existing persona discovery approaches rely on su
arXiv:2604.23724v1 Announce Type: cross Abstract: Expressway video anomaly detection is essential for safety management. However, identifying anomalies across diverse scenes remains challenging, parti
arXiv:2604.21260v1 Announce Type: cross Abstract: We study semisupervised mean estimation with a small labeled sample, a large unlabeled sample, and a black-box prediction model whose output may be mi
arXiv:2412.03594v3 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly play an important role in a wide range of information processing and management tasks in industry. M
arXiv:2604.19838v1 Announce Type: new Abstract: Understanding how road users resolve space-sharing conflicts is important both for traffic safety and the safe deployment of autonomous vehicles. While
arXiv:2603.04445v2 Announce Type: replace-cross Abstract: The rapid growth of large language models (LLMs) with diverse capabilities, costs, and domains has created a critical need for intelligent mod
arXiv:2509.16343v2 Announce Type: replace-cross Abstract: Building robust vision systems for high-stakes domains such as remote sensing requires stronger visual reasoning than what single-pass inferen
arXiv:2511.22003v2 Announce Type: replace-cross Abstract: Limited overlap between treated and control groups is a key challenge in observational analysis. Standard approaches like trimming importance
arXiv:2604.17967v1 Announce Type: cross Abstract: In this article, we establish a precise connection between binarized neural networks (BNNs) and Sugeno integrals. The advantage of the Sugeno integral
arXiv:2604.17115v1 Announce Type: new Abstract: Interactive video segmentation models such as SAM2 have demonstrated strong generalization across diverse visual domains. However, under weak user super
arXiv:2604.18567v1 Announce Type: cross Abstract: Large language models frequently commit unrecoverable reasoning errors mid-generation: once a wrong step is taken, subsequent tokens compound the mist
arXiv:2601.21159v2 Announce Type: replace Abstract: High-resolution remote sensing images contain densely distributed objects with pronounced scale variations and complex boundaries, which impose high
arXiv:2604.16955v1 Announce Type: new Abstract: Quantitative prediction of future retinal appearance from longitudinal imaging would support clinical decisions in progressive macular disease that curr
arXiv:2604.15373v1 Announce Type: cross Abstract: We propose InfoChess, a symmetric adversarial game that elevates competitive information acquisition to the primary objective. There is no piece captu
arXiv:2604.15475v1 Announce Type: new Abstract: Deploying learned multi-robot models on heterogeneous robots remains challenging due to hardware heterogeneity, communication constraints, and the lack
arXiv:2604.15464v1 Announce Type: cross Abstract: Large Language Model (LLM) deployment is increasingly shifting to cost-efficient accelerators like Google's Tensor Processing Units (TPUs), prioritizi
arXiv:2604.14575v1 Announce Type: new Abstract: Data-driven operations management often relies on parameters estimated from costly human-generated labels. Recent advances in large language models (LLM
arXiv:2604.14562v1 Announce Type: new Abstract: Accurate thermal modeling in metal additive manufacturing (AM) is essential for understanding the process-structure-performance relationship. While prio
arXiv:2604.12344v1 Announce Type: cross Abstract: The exponential growth of data from modern radio telescopes presents a significant challenge to traditional single-pulse search algorithms, which are
arXiv:2604.12110v1 Announce Type: new Abstract: Recent advances in recommendation scaling laws have led to foundation models of unprecedented complexity. While these models offer superior performance,
arXiv:2604.11001v1 Announce Type: new Abstract: Large language models (LLMs) have been widely adopted due to their great performance across a wide range of applications. ChatGPT and Gemini now serve h
arXiv:2604.09631v1 Announce Type: cross Abstract: As deep learning models are deployed on resource constrained edge platforms in autonomous driving systems, reli able knowledge of hardware behavior un
arXiv:2604.10424v1 Announce Type: new Abstract: Foundation-style ECG encoders pretrained with self-supervised learning are increasingly reused across tasks, institutions, and deployment contexts, ofte
arXiv:2601.12104v2 Announce Type: replace-cross Abstract: Fine-tuned language models pose significant privacy risks, as they may memorize and expose sensitive information from their training data. Mem
arXiv:2604.11496v1 Announce Type: cross Abstract: Dual-encoder Vision-Language Models (VLMs) such as CLIP are often characterized as bag-of-words systems due to their poor performance on compositional
arXiv:2604.08890v1 Announce Type: cross Abstract: Modeling causal relationships in graph representation learning remains a fundamental challenge. Existing approaches often draw on theories and methods
arXiv:2604.09220v1 Announce Type: new Abstract: Implicit neural video representations encode entire video sequences within the parameters of a neural network and enable constant time frame reconstruct
arXiv:2604.09048v1 Announce Type: cross Abstract: While the large energy consumption of Large Language Models (LLMs) is recognized by the community, system operators lack guidance for energy-efficient
arXiv:2604.08133v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) has become a dominant architecture for scaling large language models due to their sparse activation mechanism. However, the s
arXiv:2507.08390v4 Announce Type: replace Abstract: Discrete diffusion models have recently emerged as strong alternatives to autoregressive language models, matching their performance through large-s
arXiv:2604.06798v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) based large language models (LLMs) offer strong performance but suffer from high memory and computation costs. Weight binariz
arXiv:2508.16703v4 Announce Type: replace-cross Abstract: On-device running Large Language Models (LLMs) is nowadays a critical enabler towards preserving user privacy. We observe that the attention o
arXiv:2604.06831v1 Announce Type: cross Abstract: Current LLM-based services typically require users to submit raw text regardless of its sensitivity. While intuitive, such practice introduces substan
arXiv:2610.21020v1 Announce Type: cross Abstract: We study whether the classical momentum-based acceleration that improves the condition-number dependence of gradient descent from kappa to sqrt{kappa}
arXiv:2610.21378v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models reduce computation by routing each token to a small set of experts, but each selected expert is still used at a fixed pr
arXiv:2610.21869v1 Announce Type: new Abstract: Graph Unlearning (GU) aims to remove the influence of specific training data from a Graph Neural Network without retraining anew. While most methods add
arXiv:2610.21049v1 Announce Type: new Abstract: Learned dynamical models can accurately predict trajectories while producing unreliable sensitivities when differentiated or transposed, limiting their
arXiv:2610.14826v1 Announce Type: cross Abstract: Recent alignment-free Text-to-Speech (TTS) models achieve high synthesis quality by removing explicit alignment modules and simplifying training. Howe
arXiv:2610.14389v1 Announce Type: new Abstract: Benchmark scores tell us what an LLM can do, but not how much energy is required to deliver that capability. We directly measure this trade-off for 86 o
arXiv:2601.03822v2 Announce Type: replace Abstract: Large language models (LLMs) can achieve strong reasoning performance with sufficient computation, but they do not inherently know how much computat
arXiv:2610.15417v1 Announce Type: new Abstract: Mixture-of-experts (MoE) models activate only a few experts per token, but when their expert weights are offloaded to host memory, host-to-device (H2D)
arXiv:2610.19046v1 Announce Type: new Abstract: Information-theoretic exploration is of primary interest in methodological studies of reinforcement learning (RL) and computational cognitive neuroscien
arXiv:2610.14926v1 Announce Type: new Abstract: Multi-finger hands contact objects at different times, so a global close command can overload early-contact fingers while others are still moving. Dense
arXiv:2610.16187v1 Announce Type: cross Abstract: Existing cumulative regret guarantees for Bayesian optimization (BO) do not necessarily characterize the quality of the algorithm's final output. This
arXiv:2605.06046v2 Announce Type: replace Abstract: Auto-regressive token generation in large language models is memory-bound because it requires 'attending to' key and value tensors (KV cache) of all
arXiv:2610.17146v1 Announce Type: cross Abstract: Bayesian predictive regions account for parameter uncertainty but can be poorly calibrated under model misspecification, even with expensive full MCMC
arXiv:2610.17458v1 Announce Type: cross Abstract: Unsupervised clustering is widely used to discover underlying group structure, after which researchers often seek to validate these groups via post-ho
A few weeks ago we posted the open-source Graphsignal profiler here: wrap vllm serve / sglang serve / whatever in graphsignal-run and it serves everything it measures as JSON, mainly so an agent can r
arXiv:2610.13764v1 Announce Type: cross Abstract: Prior-data fitted networks (PFNs) are trained to approximate the Bayesian posterior predictive distribution (PPD) of a synthetic prior, yet results ab
arXiv:2610.13278v1 Announce Type: new Abstract: Vision-language models (VLMs) exhibit complementary capabilities, yet selecting the most suitable expert for a given image-question query remains challe
Learn how to deploy one large language model across two GPU nodes on Amazon EKS using the multi-node Ray LLM Deep Learning Containers, with separate prefill and decode nodes behind one OpenAI-compatib
arXiv:2610.13656v1 Announce Type: cross Abstract: Latent field models are essential for spatial statistics, but the posterior distribution of the latent field, even with a Gaussian process (GP) prior,
arXiv:2610.12986v1 Announce Type: cross Abstract: Continuous-time latent state-space models are widely used for irregularly observed time series, typically representing uncertainty through a random in
arXiv:2610.12316v1 Announce Type: new Abstract: Recent motion generative models have demonstrated strong capabilities in synthesizing physically plausible character motion, but often overlook establis
ALHR - Adaptive Learnable Hierarchical Routing, uses static binary trees and learnable functions to minimize the amount of keys to be read. It does use a dense teacher while phase 1 of training howeve
There are way too many forks to keep track of, so I've gotten lost. As far as I can tell, Radiance VLLM is best for models that fit in GPUs while some form of llama.cpp is probably best for MOE RAM-sp