Search: “research”

Why Attend to Everything? Focus is the Key

arXiv:2604.03260v2 Announce Type: replace-cross Abstract: Standard attention scales quadratically with sequence length. Efficient attention methods reduce this O(n^2) cost, but when retrofitted into p

researcharxiv-cs-ai

30 Apr 2026

World2VLM: Distilling World Model Imagination into VLMs for Dynamic Spatial Reasoning

DGX agent

arXiv:2604.26934v1 Announce Type: new Abstract: Vision-language models (VLMs) have shown strong performance on static visual understanding, yet they still struggle with dynamic spatial reasoning that

researcharxiv-cs-cv

30 Apr 2026

8DNA: 8D Neural Asset Light Transport by Distribution Learning

arXiv:2604.25129v1 Announce Type: cross Abstract: High-fidelity 3D assets exhibit intriguing global illumination effects like subsurface scattering, glossy interreflections, and fine-scale fiber scatt

'A decade ago, AI was supposed to replace radiologists. Today, radiologists make more than $500,000 per year, and their employment continues…

'A decade ago, AI was supposed to replace radiologists. Today, radiologists make more than $500,000 per year, and their employment continues to grow, see chart below. Reading scans is a task, not a jo

researchyann-lecun--x

A graph generation pipeline for critical infrastructures based on heuristics, images and depth data

arXiv:2512.07269v2 Announce Type: replace Abstract: Virtual representations of physical critical infrastructures, such as water or energy plants, are used for simulations and digital twins to ensure r

A paradox of AI fluency

arXiv:2604.25905v1 Announce Type: new Abstract: How much does a user's skill with AI shape what AI actually delivers for them? This question is critical for users, AI product builders, and society at

Applications

A systematic literature Review for Transformer-based Software Vulnerability detection

arXiv:2604.24822v1 Announce Type: cross Abstract: Context: Software vulnerabilities pose significant security threats to software systems, especially as software is increasingly used across many areas

applicationsarxiv-cs-lg

A Unifying Framework for Unsupervised Concept Extraction

arXiv:2604.24936v1 Announce Type: new Abstract: Techniques for concept extraction, such as sparse autoencoders and transcoders, aim to extract high-level symbolic concepts from low-level nonsymbolic r

Accuracy Improvement of Cell Image Segmentation Using Feedback Former

arXiv:2408.12974v4 Announce Type: replace Abstract: Semantic segmentation of microscopy cell images by deep learning is a significant technique. We considered that the Transformers, which have recentl

Adaptive Meta-Learning Stochastic Gradient Hamiltonian Monte Carlo Simulation for Bayesian Updating of Structural Dynamic Models

arXiv:2604.25710v1 Announce Type: cross Abstract: In the last few decades, Markov chain Monte Carlo (MCMC) methods have been widely applied to Bayesian updating of structural dynamic models in the fie

An analysis of sensor selection for fruit picking with suction-based grippers

arXiv:2604.24906v1 Announce Type: cross Abstract: Robotic fruit harvesting often fails to reliably detect whether a fruit has been successfully picked, limiting efficiency and increasing crop damage.

ARQ: A Mixed-Precision Quantization Framework for Accurate and Certifiably Robust DNNs

arXiv:2410.24214v3 Announce Type: replace-cross Abstract: Mixed precision quantization has become an important technique for optimizing the execution of deep neural networks (DNNs). Certified robustne

Automated detection of pediatric congenital heart disease from phonocardiograms using deep and handcrafted feature fusion

arXiv:2604.24767v1 Announce Type: cross Abstract: Congenital heart disease (CHD) is the most common type of birth defect, impacting about 1% of live births worldwide. Echocardiography, the gold-standa

Backtranslation Augmented Direct Preference Optimization for Neural Machine Translation

arXiv:2604.25702v1 Announce Type: new Abstract: Contemporary neural machine translation (NMT) systems are almost exclusively built by training on supervised parallel data. Despite the tremendous progr

Benchmarking Logistic Regression, SVM, and LightGBM Against BiLSTM with Attention for Sentiment Analysis on Indonesian Product Reviews

arXiv:2604.25452v1 Announce Type: new Abstract: Sentiment analysis of product reviews on e-commerce platforms plays a critical role in automatically understanding customer satisfaction and providing a

Benchmarking PyCaret AutoML Against IndoBERT Fine-Tuning for Sentiment Analysis on Indonesian IKN Twitter Data

arXiv:2604.25392v1 Announce Type: new Abstract: This paper benchmarks a classical machine learning approach based on PyCaret AutoML against a deep learning approach based on IndoBERT fine-tuning for b

Beyond Fidelity: Semantic Similarity Assessment in Low-Level Image Processing

arXiv:2604.25408v1 Announce Type: new Abstract: Low-level image processing has long been evaluated mainly from the perspective of visual fidelity. However, with the rise of deep learning and generativ

Biased Dreams: Limitations to Epistemic Uncertainty Quantification in Latent Space Models

arXiv:2604.25416v1 Announce Type: new Abstract: Model-Based Reinforcement Learning distinguishes between physical dynamics models operating on proprioceptive inputs and latent dynamics models operatin

Bridging the Indoor-Outdoor Gap: Cross-Technology Ranging for Seamless Robot Navigation

arXiv:2604.25541v1 Announce Type: cross Abstract: Mobile robots that move between outdoor and indoor environments still struggle with consistent positioning. Satellite-based and terrestrial ranging ea

researcharxiv-cs-ro

Calibrated Fusion for Heterogeneous Graph-Vector Retrieval in Multi-Hop QA

arXiv:2603.28886v2 Announce Type: replace-cross Abstract: Graph-augmented retrieval combines dense similarity with graph-based relevance signals such as Personalized PageRank (PPR), but these scores h

Can We Change the Stroke Size for Easier Diffusion?

arXiv:2603.26783v2 Announce Type: replace Abstract: Diffusion models can be challenged in the low signal-to-noise regime, where they have to make pixel-level predictions despite the presence of high n

Categorical Optimization with Bayesian Anchored Latent Trust Regions for Structural Design under High-Dimensional Uncertainty

arXiv:2604.25241v1 Announce Type: new Abstract: Categorical structural optimization under aleatoric uncertainty is challenging because each design variable must be selected from a finite catalog of ad

CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding

arXiv:2602.01785v2 Announce Type: replace Abstract: Large Language Models (LLMs) have achieved remarkable success in source code understanding, yet as software systems grow in scale, computational eff

Comparative Study of Bending Analysis using Physics-Informed Neural Networks and Numerical Dynamic Deflection in Perforated nanobeam

arXiv:2604.24768v1 Announce Type: new Abstract: In this chapter, we investigate the bending behavior of a perforated nanobeam subjected to sinusoidal loading using an efficient and computationally rob

Conditional Flow Matching for Probabilistic Downscaling of Maximum 3-day Snowfall in Alaska

arXiv:2604.25172v1 Announce Type: cross Abstract: Precipitation in complex terrain is governed by orographic processes operating at scales of a few kilometers, yet climate models typically run at reso

CoreFlow: Low-Rank Matrix Generative Models

arXiv:2604.24959v1 Announce Type: new Abstract: Learning matrix-valued distributions from high-dimensional and possibly incomplete training data is challenging: ambient-space generative modeling is co

Cornserve: A Distributed Serving System for Any-to-Any Multimodal Models

arXiv:2603.12118v2 Announce Type: replace Abstract: Any-to-Any models are an emerging class of multimodal models that accept combinations of multimodal data (e.g., text, image, video, audio) as input

CRC-SAM: SAM-Based Multi-Modal Segmentation and Quantification of Colorectal Cancer in CT, Colonoscopy, and Histology Images

arXiv:2604.24793v1 Announce Type: cross Abstract: We present CRC-SAM, a unified framework for colorectal cancer segmentation across colonoscopy, CT, and histopathology images. Unlike prior single-moda

Curl Descent: Non-Gradient Learning Dynamics with Sign-Diverse Plasticity

arXiv:2510.02765v4 Announce Type: replace Abstract: Gradient-based algorithms are a cornerstone of artificial neural network training, yet it remains unclear whether biological neural networks use sim

DenseScout: Algorithm-System Co-design for Budgeted Tiny Object Selection on Edge Platforms

arXiv:2604.25300v1 Announce Type: new Abstract: Deploying tiny object perception on edge platforms is challenging because practical systems must satisfy both strict compute budgets and end-to-end late

DiffAdapt: Difficulty-Adaptive Reasoning for Token-Efficient LLM Inference

arXiv:2510.19669v4 Announce Type: replace Abstract: Recent reasoning Large Language Models (LLMs) demonstrate remarkable problem-solving abilities but often generate long thinking traces whose utility

Diverse Image Priors for Black-box Data-free Knowledge Distillation

arXiv:2604.25794v1 Announce Type: cross Abstract: Knowledge distillation (KD) represents a vital mechanism to transfer expertise from complex teacher networks to efficient student models. However, in

Do LLMs Capture Embodied Cognition and Cultural Variation? Cross-Linguistic Evidence from Demonstratives

arXiv:2604.25423v1 Announce Type: new Abstract: Do large language models (LLMs) truly acquire embodied cognition and cultural conventions from text? We introduce demonstratives, fundamental spatial ex

DualGeo: A Dual-View Framework for Worldwide Image Geo-localization

arXiv:2604.25533v1 Announce Type: new Abstract: Worldwide image geo-localization aims to infer the geographic location of an image captured anywhere on Earth, spanning street, city, regional, national

Dynamic Regret for Online Regression in RKHS via Discounted VAW and Subspace Approximation

arXiv:2604.25021v1 Announce Type: new Abstract: We study online regression with the square loss in a reproducing kernel Hilbert space under a dynamic regret criterion. The learner is compared with a t

Dynamic UGV-UAV Cooperative Path Planning in Uncertain Environments

arXiv:2604.25267v1 Announce Type: new Abstract: This paper addresses the Dynamic UGV-UAV Cooperative Path Planning (DUCPP) problem involving one unmanned ground vehicle (UGV) assisted by one or more u

researcharxiv-cs-ro

Edge-Cloud Collaborative Reconstruction via Structure-Aware Latent Diffusion for Downstream Remote Sensing Perception

arXiv:2604.25319v1 Announce Type: new Abstract: The exponential surge in high-resolution remote sensing data faces a severe bottleneck in satellite-to-ground transmission. Limited downlink bandwidth f

Elderly-Contextual Data Augmentation via Speech Synthesis for Elderly ASR

arXiv:2604.24770v1 Announce Type: new Abstract: Despite recent progress in automatic speech recognition (ASR), elderly ASR (EASR) remains challenging due to limited training data and the distinct acou

Emergent Self-Attention from Astrocyte-Gated Associative Memory Dynamics

arXiv:2604.25481v1 Announce Type: cross Abstract: We introduce a Hopfield-type associative memory in which effective connectivity is multiplicatively modulated by astrocytic gains evolving under an en

Enhancing SignSGD: Small-Batch Convergence Analysis and a Hybrid Switching Strategy

arXiv:2604.25550v1 Announce Type: new Abstract: SignSGD compresses each stochastic gradient coordinate to a single bit, offering substantial memory and communication savings, but its 1-bit quantizatio

Evaluation without Generation: Non-Generative Assessment of Harmful Model Specialization with Applications to CSAM

arXiv:2604.25119v1 Announce Type: new Abstract: Auditing the fine-tunes of open-weight generative models for harmful specialization has become a new governance challenge for model hosting platforms. T

Evolving Multi-Channel Confidence-Aware Activation Functions for Missing Data with Channel Propagation

arXiv:2602.13864v2 Announce Type: replace-cross Abstract: Learning in the presence of missing data can result in biased predictions and poor generalizability, among other difficulties, which data impu

Explainable AI for Jet Tagging: A Comparative Study of GNNExplainer, GNNShap, and GradCAM for Jet Tagging in the Lund Jet Plane

arXiv:2604.25885v1 Announce Type: cross Abstract: Graph neural networks such as ParticleNet and transformer based networks on point clouds such as ParticleTransformer achieve state-of-the-art performa

Fast Geometric Embedding for Node Influence Maximization

arXiv:2506.07435v3 Announce Type: replace-cross Abstract: Computing classical centrality measures such as betweenness and closeness is computationally expensive on large-scale graphs. In this work, we

三井住友FG、数時間で顧客企業に戦略提案サカナAIと組み作成 https://www.nikkei.com/article/DGXZQOUB2713R0X20C26A4000000/?n_cid=SNSTW001&n_tw=1777493482

Sumitomo Mitsui Financial Group (SMFG) has partnered with Sakana AI to develop a system that can deliver strategic business proposals to corporate clients within hours, leveraging AI technology to acc

researchdavid-ha--x

For years, voice AI has been stuck in a rigid loop: think, then speak. But real human conversation is messy, overlapping, and asynchronous. …

For years, voice AI has been stuck in a rigid loop: think, then speak. But real human conversation is messy, overlapping, and asynchronous. In our new #ICASSP2026 work, we built a tandem architecture

researchdavid-ha--x

Fractionally Supervised Classification with Maxima Nominated Samples

arXiv:2604.25145v1 Announce Type: cross Abstract: Fractionally supervised classification (FSC) offers a flexible framework for combining labeled and unlabeled data in model-based classification, but e

From Ambiguity to Accuracy: The Transformative Effect of Coreference Resolution on Retrieval-Augmented Generation systems

arXiv:2507.07847v3 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) has emerged as a crucial framework in natural language processing (NLP), improving factual consistency and redu