Search: “research”

TinyDejaVu: Smaller RAM and Faster Inference with Neural Networks on MCUs for Sensor Data Streams

arXiv:2512.09786v2 Announce Type: replace Abstract: Examples of embedded intelligence include a wide variety of tiny neural networks used on-board wireless sensors and actuators, which are expected to

Research

Token Optimization Strategies for LLM-Based Oracle-to-PostgreSQL Migration

DGX agent

arXiv:2605.28557v1 Announce Type: cross Abstract: LLMs are increasingly used for software modernization, code translation, and database migration. However, LLM-based Oracle2PostgreSQL migration remain

researcharxiv-cs-ai

28 May 2026

Towards Reliable Multilingual LLMs-as-a-Judge: An Empirical Study

arXiv:2605.28710v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for the automatic evaluation of generated text, yet most prior work focuses on English. Despite the

Transfer learning RGB models to hyperspectral images with trainable tensor decompositions

arXiv:2605.28331v1 Announce Type: new Abstract: Transfer learning makes it possible to use large vision networks on a variety of domains, by specializing their models' general filters to new tasks. Ho

Transferable Graph Condensation from the Causal Perspective

arXiv:2601.21309v4 Announce Type: replace Abstract: The increasing scale of graph datasets has significantly improved the performance of graph representation learning methods, but it has also introduc

Triangular-Reference Schrodinger Bridges for Time Series Generation

arXiv:2605.27478v1 Announce Type: cross Abstract: We introduce Triangular-Reference Schrodinger Bridges for Time Series (TR-SBTS), a conservative extension of the SBTS framework in which the Brownian

Unification and Optimization of Robust Supervised Learning

arXiv:2605.28165v1 Announce Type: new Abstract: The literature has proposed various robust alternatives to empirical risk minimisation to address failure modes such as distribution shift, label noise

Unifying Low Dimensional Spectra in Deep Learning

arXiv:2404.06106v3 Announce Type: replace Abstract: Low dimensional structures appear ubiquitously in the eigenspectra of deep learning matrices in classification networks trained in the overparameter

UNIQUE: Universal Top-k Sparse Attention for Training-free Inference and Sparsity-aware Training

arXiv:2605.27740v1 Announce Type: new Abstract: Long-context inference in large language models (LLMs) is bottlenecked by the linear growth of the self-attention key-value (KV) cache. Top-k sparse att

Universal Time Series Generation with Neural Controlled Differential Equations

arXiv:2605.28507v1 Announce Type: new Abstract: Recent work on the sequence universality of State Space Models (SSMs) has introduced efficient, maximally expressive continuous-time approaches for time

Variance-Adaptive Optimal Algorithm for Reinforcement Learning with Multinomial Logit Function Approximation

arXiv:2605.28364v1 Announce Type: cross Abstract: Reinforcement learning with multinomial logistic (MNL) function approximation has become an important framework due to its flexibility and broad appli

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention

arXiv:2602.07574v2 Announce Type: replace-cross Abstract: Modern multimodal large language models (MLLMs) adopt a unified self-attention design that processes visual and textual tokens at every Transf

VidPrism: Heterogeneous Mixture of Experts for Image-to-Video Transfer

arXiv:2605.28229v1 Announce Type: cross Abstract: With the rapid development of pre-training technologies, adapting large-scale Vision-Language Models (VLMs) for video understanding ie image-to-video

When Confidence Misleads: Suffix Anchoring and Anchor-Proximity Confidence Modulation for Diffusion Language Models

arXiv:2605.28181v1 Announce Type: new Abstract: Diffusion language models decode text by iteratively denoising masked token sequences, making the choice of which positions to decode a central inferenc

When Helpful Context Leaks: Privacy Risks in Domain-Adapted ASR

arXiv:2605.28211v1 Announce Type: new Abstract: SpeechLLMs are increasingly deployed in professional settings where domain customisation is standard practice: users supply context in prompts with sens

When Seekers Are Hard to Help: Evaluating Emotional Support Dialogue Systems in Worst-Case Interactions

arXiv:2605.28228v1 Announce Type: new Abstract: Emotional Support Dialogue Systems (ESDSes) are increasingly evaluated and trained with LLM-simulated seekers. However, such simulated seekers often beh

Where LLM Annotators Fail: Label-Free Learning on Graphs with LLMs

arXiv:2605.27913v1 Announce Type: new Abstract: Node classification on graphs often requires labeled nodes, yet obtaining labels at graph scale is expensive. When node attributes contain semantic cont

Which Heads Matter for Reasoning? RL-Guided KV Cache Compression

arXiv:2510.08525v3 Announce Type: replace Abstract: Reasoning large language models exhibit complex reasoning behaviors via extended chain-of-thought generation that are highly fragile to information

Whose Is This?: Context-Aware Object Ownership Inference with Uncertainty-Guided Questioning

arXiv:2605.28087v1 Announce Type: new Abstract: Service robots must infer object ownership to correctly interpret instructions such as 'bring me my cup.' However, ownership is a latent attribute that

researcharxiv-cs-ro

Why We Need Speech to Evaluate Speech Translation

arXiv:2605.28227v1 Announce Type: new Abstract: Speech translation models are increasingly capable of preserving speech-specific information (e.g., speaker gender, prosody, and emphasis), yet evaluati

Worker Disagreement Reveals Sharp Directions in Local SGD

arXiv:2605.27739v1 Announce Type: cross Abstract: Deep neural network training often exhibits highly anisotropic loss geometry, where a few sharp dominant Hessian directions coexist with a large flatt

Zero-shot Quantum Neural Architecture Search

arXiv:2605.27410v1 Announce Type: cross Abstract: Variational Quantum Algorithms (VQAs) are a leading approach to exploiting near-term quantum hardware, leveraging parameterized quantum circuits and c

Zipping the Thought: When and How Compressed Reasoning Data Works in LLM Post-Training

arXiv:2605.28008v1 Announce Type: new Abstract: Large language models (LLMs) can now solve complex problems through long chain-of-thought (CoT) reasoning, but the trade-off between performance and tok

2-ASP(Q) programs with weak constraints: Complexity and efficient implementation

arXiv:2605.27338v1 Announce Type: new Abstract: ASP(Q) extends Answer Set Programming (ASP) with Quantifiers over answer sets. In this paper we focus on the class of ASP(Q) programs with two quantifie

A Bioinspired Underwater Robot with a Latch-Mediated Soft Bistable Mechanism

arXiv:2605.26936v1 Announce Type: new Abstract: Underwater robotics has advanced significantly over recent decades. however, the development of miniaturized underwater robots remains limited by low en

researcharxiv-cs-ro

A Dynamic Programming Framework for Discovering Count and Values of Multilevel Image Thresholding

arXiv:2605.27287v1 Announce Type: new Abstract: Multilevel Image thresholding is an important preprocessing algorithm in computer vision applications nowadays. Since most common thresholding methods t

A first-order method for constrained nonconvex-nonconcave minimax optimization

arXiv:2510.01168v3 Announce Type: replace-cross Abstract: We study a class of constrained nonconvex-nonconcave minimax optimization problems in which the inner maximization involves potentially comple

A Logical View of GNN-Style Computation and the Role of Activation Functions

arXiv:2512.19332v2 Announce Type: replace Abstract: We study the numerical and Boolean expressiveness of MPLang, a declarative language that captures the computation of graph neural networks (GNNs) th

A Method for Learning Large-Scale Computational Construction Grammars from Semantically Annotated Corpora

arXiv:2603.12754v2 Announce Type: replace Abstract: We present a method for learning large-scale, broad-coverage construction grammars from corpora of language use. Starting from utterances annotated

A multifractal-based masked auto-encoder: an application to medical images

arXiv:2605.26287v1 Announce Type: new Abstract: Masked autoencoders (MAE) have shown great promise in medical image classification. However, the random masking strategy employed by traditional MAEs ma

A PAC-Bayesian View of Generalisation for Physics-Informed Machine Learning

arXiv:2605.26341v1 Announce Type: new Abstract: Physics-informed machine learning (PIML) integrates mechanistic knowledge, typically in the form of partial differential equations (PDE), into data-driv

A Physics-Informed Hierarchical Neural Network for Microwave Scattering Analysis of 3D PEC Targets

arXiv:2508.03774v5 Announce Type: replace-cross Abstract: Accurate modeling of scattering from three-dimensional (3D) perfectly electrically conducting (PEC) targets at microwave frequencies constitut

A Unified Framework for Diffusion Model Unlearning with f-Divergence

arXiv:2509.21167v2 Announce Type: replace-cross Abstract: Most existing methods for concept unlearning in text-to-image diffusion models minimize a mean squared error (MSE) loss between the denoiser o

Accountable Human-AI Deliberation with LLMs: Scaling Collective Intelligence through Symbiotic Scaffolding

arXiv:2605.26940v1 Announce Type: new Abstract: Large language models (LLMs) can support democratic deliberation at scales previously constrained by turn-taking and facilitation bandwidth. Recent work

AdaMorph: Unified Motion Retargeting via Embodiment-Aware Adaptive Transformers

arXiv:2601.07284v2 Announce Type: replace Abstract: Retargeting human motion to heterogeneous robots is a fundamental challenge in robotics, primarily due to the severe kinematic and dynamic discrepan

researcharxiv-cs-ro

Adaptive Reinforcement Learning for Robust Open Quantum System Control: A Multi-Task Framework with Temporal Optimization

arXiv:2605.26925v1 Announce Type: cross Abstract: We present a Multi-task Soft Actor-Critic (SAC) Reinforcement Learning framework designed for open-system quantum control across diverse Hamiltonians,

Advancing Metallic Surface Defect Detection via Anomaly-Guided Pretraining on a Large Industrial Dataset

arXiv:2509.18919v2 Announce Type: replace Abstract: The pretraining-finetuning paradigm is a crucial strategy in metallic surface defect detection for mitigating the challenges posed by data scarcity.

Algorithmic Monocultures in Hiring

arXiv:2605.27371v1 Announce Type: cross Abstract: Many employers screen job applicants with algorithms built by the same few algorithm vendors. We hypothesize that algorithmic monoculture leads to the

Amortized Factor Inference Networks for Posterior Inference

arXiv:2605.26419v1 Announce Type: new Abstract: Amortized inference promises fast test-time Bayesian inference, but existing methods are inherently tied to fixed models. Extending amortization to unse

An In-Vitro Study on Cross-Lingual Generalization in Language Models

arXiv:2605.26683v1 Announce Type: cross Abstract: Cross-lingual transfer in language models is difficult to study in natural corpora because lexical overlap, morphology, data imbalance, and tokenizati

AnchorDiff: Training-Free Concept Grounding for MM-DiTs via Anchor-Based Graph Propagation

arXiv:2605.26460v1 Announce Type: cross Abstract: Multi-Modal Diffusion Transformers (MM-DiTs) encode rich representations for training-free concept grounding, but existing attention-based methods oft

Anchored Decoding: Provably Reducing Copyright Risk for Any Language Model

arXiv:2602.07120v2 Announce Type: replace Abstract: Language models (LMs) tend to memorize portions of their training data and emit verbatim spans. When the underlying sources are sensitive or copyrig

AnySurf: Any Surface Generation with Directed Edge

arXiv:2605.26149v1 Announce Type: cross Abstract: Open surface components prevail in real industrial 3D content and support rendering, physical simulation and geometric editing. Garments serve as a ty

APEX: Amplitude Anchors and Phase Priors for Target-Scarce Higher-Frequency Wave Prediction

arXiv:2605.26732v1 Announce Type: new Abstract: Learning-based surrogates have become increasingly effective for wave-field prediction, and neural operators in particular have shown strong performance

Assessing Per-Sample Membership Inference Vulnerability without Retraining

arXiv:2602.15919v2 Announce Type: replace-cross Abstract: Recent work in the privacy literature shows that sample-targeted membership inference attacks (MIAs) significantly outperform untargeted appro

Attenuation-Resilient Alternating Optimization for Laparoscopic Liver Landmark Detection

arXiv:2605.26630v1 Announce Type: new Abstract: Liver surface landmark detection is a fundamental prerequisite for anatomical guidance in laparoscopic liver surgery. However, it remains unreliable in

Beyond Binary: Speech Representations Across the Cognitive Score Hierarchy

arXiv:2605.27189v1 Announce Type: new Abstract: This study examines the relationship between speech representations and the hierarchical structure of cognitive assessment in mild cognitive impairment.

Beyond Differences: Doubly Robust Meta-Learners for Ratio-Based Treatment Effects

arXiv:2605.26288v1 Announce Type: cross Abstract: When treatment effects are naturally expressed as ratios -- as in medicine, pricing, and marketing -- the ratio-based CATE au(x) = E[Y|W=1,X=x] / E[Y|