research

LitSeg: Narrative-Aware Document Segmentation for Literary RAG

arXiv:2605.27156v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by incorporating external knowledge, particularly for long-tail domains suc

LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding

DGX agent

arXiv:2605.27365v1 Announce Type: cross Abstract: Vision-language models (VLMs) commonly formulate visual grounding and detection as a coordinate-token generation problem, serializing each 2D box into

researcharxiv-cs-ai

27 May 2026

Lost in Sampling: Assessing Lexical Reachability in LLMs via the Word Coverage Score (WCS)

arXiv:2605.27268v1 Announce Type: cross Abstract: Modern Large Language Models (LLMs) are often criticized for producing repetitive and homogeneous text, despite possessing vast latent vocabularies. W

LUCoS: Latent Unsupervised Context Selection for Tabular Foundation Models

arXiv:2605.27254v1 Announce Type: cross Abstract: Selecting which instances to label is a key challenge in low-label tabular learning. For recent Tabular Foundation Models such as TabPFN, context sele

Managing Uncertainty in LLM-Generated Procedural Knowledge for Virtual Laboratory Planning

arXiv:2605.26333v1 Announce Type: new Abstract: Educational virtual laboratories can make experimental training more scala-ble, adaptive, and accessible, especially when students have limited access t

Manipulating Tangible Virtual Object Dynamics to Promote Learning of Precision Force Generation

arXiv:2605.26782v1 Announce Type: new Abstract: Robotic haptic devices combined with virtual reality offer novel opportunities to train fine force generation, an essential yet overlooked component of

researcharxiv-cs-ro

Many Logics, One Methodology: A Plea for Logical Pluralism in Formalised Reasoning (preprint)

arXiv:2605.27246v1 Announce Type: cross Abstract: This position statement looks back on two decades of work on shallow embeddings of non-classical logics in classical higher-order logic (HOL), a line

Max-Window Scale Estimation for Near-Lossless HiF8 W8A8 Quantization-Aware Training

arXiv:2605.26189v1 Announce Type: cross Abstract: Quantization-aware training (QAT) with low-bit floating-point formats enables efficient LLM deployment, yet introduces subtle failure modes invisible

MedGuideX: Internalizing Decision Logic from Executable Guidelines into Large Language Models for Clinical Reasoning

arXiv:2605.26567v1 Announce Type: new Abstract: Clinical practice guidelines (CPGs) encode evidence-based decision logic that clinicians apply by evaluating patient variables, conditional criteria, an

Memory-Distilled Selection for Noise-Robust Anomaly Detection

arXiv:2605.26676v1 Announce Type: new Abstract: Anomaly detection (AD) under data contamination is critical for deploying unsupervised defect detection in industrial environments, where curating perfe

Message-Passing State-Space Models: Improving Graph Learning with Modern Sequence Modeling

arXiv:2505.18728v2 Announce Type: replace-cross Abstract: The recent success of State-Space Models (SSMs) in sequence modeling has motivated their adaptation to graph learning, giving rise to Graph St

MetaSICL: Adapting Audiroty LLM via Meta Speech In-Context Learning

arXiv:2601.18904v2 Announce Type: replace-cross Abstract: Auditory Large Language Models (LLMs) have demonstrated strong performance across a wide range of speech and audio understanding tasks. Nevert

Minimal surfaces, Knots, and Neural Networks

arXiv:2605.26234v1 Announce Type: cross Abstract: A recent conjecture by Joel Fine posits a relationship between the coefficients of the HOMFLY polynomial of a knot K in the 3-sphere S^3, and the sign

MiRD: Reliable Set-Valued Prediction for Open-Ended Question Answering via Miscoverage Risk Decomposition

arXiv:2605.27091v1 Announce Type: cross Abstract: Reliable set-valued prediction provides a principled way to mitigate hallucinations in open-ended question answering (QA), yet existing conformal appr

Model Merging on Loss Landscape: A Geometry Perspective

arXiv:2605.26693v1 Announce Type: cross Abstract: Model merging offers a promising avenue for knowledge integration and parallel development without retraining. Yet, existing methods either ignore the

MSCGC-KAN: Multi-scale Causal Graph Convolution and Kolmogorov-Arnold Feature Mapping for EEG Emotion Recognition

arXiv:2605.26624v1 Announce Type: new Abstract: Electroencephalogram (EEG)-based emotion recognition is an important affective computing task, and recent EEG foundation models provide useful generic r

MuCon: Clipped Muon Updates for LLM Training

arXiv:2605.26459v1 Announce Type: new Abstract: Muon-style optimizers take a matrix-valued momentum or preconditioned update B = U operatorname{diag}(sigma_1,ldots,sigma_r) V^op and replace it with it

Multi-Modal Building Inspection via Perceiver IO Fusion of Satellite and Street-Level Imagery

arXiv:2605.26381v1 Announce Type: new Abstract: We present a multi-modal classification framework that fuses satellite and street-level imagery through a Perceiver IO architecture operating on spatial

Natural Human Motion Recovery by Aligning High-Order Temporal Dynamics from Monocular Videos

arXiv:2605.26879v1 Announce Type: new Abstract: Human motion recovered from monocular videos often appears overly smooth or dynamically inconsistent, even when joint positions are numerically accurate

Natural Language Query to Configuration for Retrieval Agents

arXiv:2605.27361v1 Announce Type: new Abstract: Modern retrieval agents expose many configuration choices -- LLM, retriever, number of documents, number of hops, and synthesis strategy -- each shaping

Neural Scaling Laws of Deep ReLU and Deep Operator Network: A Theoretical Study

arXiv:2410.00357v2 Announce Type: replace Abstract: Neural scaling laws play a pivotal role in the performance of deep neural networks and have been observed in a wide range of tasks. However, a compl

Nonlinear Data Integration via Kernel Methods for Data Collaboration Analysis

arXiv:2605.27219v1 Announce Type: new Abstract: Collaborative analysis of decentralized confidential datasets is important, but direct sharing of original datasets is often restricted by privacy and i

Normalizing Flows on Quotient Manifolds via Boundary Quotients

arXiv:2511.22882v3 Announce Type: replace Abstract: We introduce boundary quotients and present a framework for learning densities on manifolds that arise as boundary quotients of simpler domains. We

Not All Modalities Are Equal: Instruction-Aware Gating for Multimodal Videos

arXiv:2605.26232v1 Announce Type: new Abstract: Pre-trained video large language models excel at visual reasoning. However, they struggle when videos arrive with auxiliary streams, such as audio, dept

Not All Tokens Matter Equally: Dynamic In-context Vector Distillation with Decisive-Token Supervision for Long-form Medical Report Generation

arXiv:2605.27194v1 Announce Type: new Abstract: Distilling demonstration effects into hidden-space interventions offers a lightweight alternative to full finetuning. However, existing multimodal varia

NSF-SciFy: Mining the NSF Awards Database for Scientific Claims

arXiv:2503.08600v3 Announce Type: replace Abstract: We introduce NSF-SciFy, a comprehensive dataset of scientific claims and investigation proposals extracted from National Science Foundation award ab

Object Pose and Shape Estimation for Grasping: Does it Work?

arXiv:2605.26944v1 Announce Type: cross Abstract: The problem of object pose and shape estimation has seen key advancements lately. Encoder-decoder (e.g., SAM3D, LRM, CRISP) and diffusion-based models

On the Detection of Commutative Factors in Factor Graphs: Necessary and Sufficient Conditions

arXiv:2605.26908v1 Announce Type: new Abstract: Exploiting the indistinguishability of objects in a probabilistic graphical model such as a factor graph is key to lifted probabilistic inference algori

On the Error-Correcting Effects of Stochasticity in Discrete Diffusion

arXiv:2605.26582v1 Announce Type: cross Abstract: Discrete diffusion models achieve strong performance in text and image generation, but their inference remains slow and must inherently balance sampli

On the Robustness of Machine Unlearning for Vision-Language Models

arXiv:2605.26992v1 Announce Type: new Abstract: Vision-language models (VLMs) may memorize undesirable information from training data, motivating growing interest in machine unlearning. In this work,

Once-For-All: A Train-Once and Select-Anytime Framework for Multimodal Instruction Tuning

arXiv:2605.26761v1 Announce Type: new Abstract: Multimodal instruction tuning is the de facto recipe for adapting vision language models (VLMs), yet instruction data are highly redundant, making data

Online Learning on Hidden-Convex Losses via Algorithmic Equivalence: Optimal Regret, Geometric Barrier, and Bandit Feedback

arXiv:2605.26373v1 Announce Type: new Abstract: We study adversarial online learning with hidden-convex losses, i.e., nonconvex losses that become convex after a nonlinear reparameterization. Ghai, Lu

Open Source Must Win - The Pope

Open Source Must Win - The Pope Today, among the goods that are universally intended for everyone, we must also include new forms of property, such as patents, algorithms, digital platforms, technolog

researchnous-research--x

PARE: Pruning and Adaptive Routing for Efficient Video Generation

arXiv:2605.27336v1 Announce Type: new Abstract: Video Diffusion Transformers (DiTs) generate high-quality videos but demand substantial compute due to wide blocks, deep architectures, and iterative sa

Parsimonious Learning-Augmented Online Metric Matching

arXiv:2605.26886v1 Announce Type: cross Abstract: Learning-augmented algorithms have received significant attention in recent years, particularly in the context of online optimization. Motivated by th

ParsVoice: A Large-Scale Multi-Speaker Persian Speech Corpus for Text-to-Speech Synthesis

arXiv:2510.10774v3 Announce Type: replace-cross Abstract: Persian remains substantially underrepresented in open speech-text resources, limiting progress in multi-speaker text-to-speech (TTS), speech-

Particle-Lund Multimodality in Jet Taggers

arXiv:2605.26821v1 Announce Type: cross Abstract: The Lund plane offers a physics-motivated, hierarchical representation of QCD radiation within jets, while transformer-based taggers have reached stat

PATE-TabTransGAN: Differentially Private Synthetic Tabular Data Generation via Transformer-Based Student Discrimination

arXiv:2605.26802v1 Announce Type: new Abstract: Generating high-fidelity synthetic tabular data under formal differential privacy guarantees remains an open challenge. Methods that provide strong theo

Petraeus: Putin is the personification of evil. He wants to reassemble as much of the former Soviet Union or Russian Empire as he can, and h…

Petraeus: Putin is the personification of evil. He wants to reassemble as much of the former Soviet Union or Russian Empire as he can, and he does not believe Ukraine has a right to exist as an indepe

researchyann-lecun--x

Physics Informed Neural Networks for damped harmonic oscillator and Burger's Equation (with extrapolation analysis) [P]

researchr-machinelearning

Physics-informed neural networks (PINNs) are machine learning models that incorporate physical laws and equations as constraints during training to solve differential equations. This post likely discu

PinPoint: Prompting with Informative Interior Points

arXiv:2605.26689v1 Announce Type: cross Abstract: Modern referring image segmentation pipelines couple a vision-language model (VLM) for grounding with a promptable segmenter such as the Segment Anyth

PLAID: A Unified Data Model for Machine Learning on Heterogeneous Physics Simulations

arXiv:2505.02974v3 Announce Type: replace Abstract: Machine learning-based surrogate models have emerged as a powerful tool to accelerate simulation-driven scientific workflows, but their adoption is

Plans for Evaluating Structured Generative Search Summaries

arXiv:2605.26400v1 Announce Type: cross Abstract: We propose a framework for evaluating structured generative search summaries that are placed atop organic web search results. A structured summary, ge

PlayClass: Automated Play Behaviour Classification in Poultry

arXiv:2605.27304v1 Announce Type: new Abstract: Automated monitoring of animal welfare has largely targeted negative indicators, leaving positive welfare behaviours such as play underexplored. To addr

Pop-Up Distractions Reveal Bag-of-Events Behavior in Video Large Language Models

arXiv:2605.27101v1 Announce Type: cross Abstract: A key capability for video understanding is reliably linking subjects to events across time, yet whether Video Large Language Models (VideoLLMs) actua

Pretraining Data Exposure in Large Language Models: A Survey of Membership Inference, Data Contamination, and Security Implications

arXiv:2605.26133v1 Announce Type: cross Abstract: Large Language Models (LLMs) have become the predominant paradigm in NLP, advancing both research and industry. As model sizes and pretraining data gr

Private analytics via zero-trust aggregation

Google Research presents a zero-trust approach to private analytics that combines cryptographic and hardware protection mechanisms to reduce trust in any single entity. The solution uses a cryptograph

researchgoogle-research

Probabilistic Recurrent Intention Switching Model

arXiv:2605.26998v1 Announce Type: new Abstract: Inverse reinforcement learning (IRL) recovers reward functions from observed behavior, yet traditional methods assume a single stationary reward that ca