Search: “research”

Lakestream: A Consistent and Brokerless Data Plane for Large Foundation Model Training

arXiv:2605.09994v1 Announce Type: cross Abstract: Modern Large Foundation Model (LFM) training has transformed the data pipeline from a static ingestion layer into a dynamic component that must co-evo

Language-Conditioned Visual Grounding with CLIP Multilingual

DGX agent

arXiv:2605.09060v1 Announce Type: new Abstract: Multilingual vision-language models exhibit systematic performance gaps across languages, but the mechanism remains ambiguous: cross-language divergence

researcharxiv-cs-cl

12 May 2026

Laplacian Heads Improve Transformers by Smoothing Token Representations

arXiv:2602.09297v2 Announce Type: replace Abstract: Transformers update token representations through multi-head attention and residual connections as X leftarrow X + sum_{i} P^{(i)}XW_{V_i}W_{o_i}, w

LBI: Parallel Scan Backpropagation via Latent Bounded Interfaces

arXiv:2605.09204v1 Announce Type: new Abstract: Backpropagation is inherently sequential across depth, creating an O(K)-deep dependency chain that bottlenecks parallel training. While parallel-scan fo

Learnability and Competition in High-Dimensional Multi-Component ICA

arXiv:2605.08552v1 Announce Type: cross Abstract: Independent Component Analysis (ICA) is a foundational tool for unsupervised representation learning, yet its high-dimensional theory remains largely

Learngene Search Across Multiple Datasets for Building Variable-Sized Models

arXiv:2605.08209v1 Announce Type: new Abstract: Deep learning methods are widely used under diverse resource constraints, resulting in models of varying sizes, such as the Vision Transformer (ViT) ser

Learning Graph Foundation Models on Riemannian Graph-of-Graphs

arXiv:2605.09993v1 Announce Type: new Abstract: Graph foundation models (GFMs), pretrained on massive graph data, have transformed graph machine learning by supporting general-purpose reasoning across

Learning More from Less: Exploiting Counterfactuals for Data-Efficient Chart Understanding

arXiv:2605.10855v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have demonstrated remarkable progress in chart understanding, largely driven by supervised fine-tuning (SFT) on increasing

Learning Polyhedral Conformal Sets for Robust Optimization

arXiv:2605.08506v1 Announce Type: new Abstract: Robust optimization (RO) provides a principled framework for decision-making under uncertainty, but its performance critically depends on the choice of

Learning Rate Scheduling with Matrix Factorization for Private Training

arXiv:2511.17994v2 Announce Type: replace Abstract: We study differentially private model training with stochastic gradient descent under learning rate scheduling and correlated noise. Although correl

Learning stochastic multiscale models through normalizing flows

arXiv:2605.09718v1 Announce Type: cross Abstract: Many systems in physics, engineering, and biology exhibit multiscale stochastic dynamics, where low-dimensional slow variables evolve under the influe

Learning Strategic Value and Cooperation in Multi-Player Stochastic Games through Side Payments

arXiv:2303.05307v2 Announce Type: replace-cross Abstract: We study general-sum, multi-player stochastic games with transferable utility, motivated by settings where agents can use side payments to mak

Learning the Interaction Prior for Protein-Protein Interaction Prediction: A Model-Agnostic Approach

arXiv:2605.09964v1 Announce Type: new Abstract: Protein-protein interactions (PPIs) are fundamental to cellular function and disease mechanisms. Current learning-based PPI predictors focus on learning

Learning Theory of Transformers: Local-to-Global Approximation via Softmax Partition of Unity

arXiv:2605.08811v1 Announce Type: cross Abstract: This paper investigates the learning theory of Transformer networks for regression tasks on the compact Euclidean domain [0,1]^d and d-dimensional com

Learning When to Trust LLM Priors: A Validated Framework for Semantic Prior Integration

arXiv:2601.21410v3 Announce Type: replace-cross Abstract: Large language models (LLMs) encode rich semantic knowledge that can be useful for supervised learning, but their outputs are unreliable as st

Lecture Notes on Statistical Physics and Neural Networks

arXiv:2605.06394v1 Announce Type: cross Abstract: These lecture notes introduce some topics of classical statistical physics, particularly those that are relevant for neural networks and deep learning

LENS: LLM-Enabled Narrative Synthesis for Mental Health by Aligning Multimodal Sensing with Language Models

arXiv:2512.23025v2 Announce Type: replace-cross Abstract: Multimodal health sensing offers rich behavioral signals for assessing mental health, yet translating these numerical time-series measurements

Less is More: Towards Simple Graph Contrastive Learning

arXiv:2509.25742v4 Announce Type: replace Abstract: Graph Contrastive Learning (GCL) has shown strong promise for unsupervised graph representation learning, yet its effectiveness on heterophilic grap

Model Releases

LEVI: Stronger Search Architectures Can Substitute for Larger LLMs in Evolutionary Search

model-releasesarxiv-cs-ai

arXiv:2605.09764v1 Announce Type: cross Abstract: LLM-guided evolutionary methods such as AlphaEvolve have proven effective in domains like math, systems research, and algorithmic discovery, but their

LLM-FE: Automated Feature Engineering for Tabular Data with LLMs as Evolutionary Optimizers

arXiv:2503.14434v3 Announce Type: replace-cross Abstract: Automated feature engineering plays a critical role in improving predictive model performance for tabular learning tasks. Traditional automate

Local LMO: Constrained Gradient Optimization via a Local Linear Minimization Oracle

arXiv:2605.08850v1 Announce Type: cross Abstract: We design Local LMO - a new projection-free gradient-type method for constrained optimization. The key algorithmic idea is to replace the global linea

Loom: Hybrid Retrieval-Scoring Outfit Recommendation with Semantic Material Compatibility and Occasion-Aware Embedding Priors

arXiv:2605.09830v1 Announce Type: cross Abstract: We present Loom, an outfit recommendation system that combines neural embedding retrieval with structured domain scoring to generate complete, coheren

Lost in Translation? Exploring the Shift in Grammatical Gender from Latin to Occitan

arXiv:2605.09156v1 Announce Type: cross Abstract: The diachronic evolution from Latin to the Romance languages involved a restructuring of the grammatical gender system from a tripartite configuration

Low-Cost Neural Radiance Fields

arXiv:2605.09312v1 Announce Type: new Abstract: Neural Radiance Fields (NeRF) achieve high-quality novel-view synthesis, but their long training times and reliance on dense input views limit accessibi

LPT: Less-overfitting Prompt Tuning for Vision-Language Model

arXiv:2410.10247v3 Announce Type: replace-cross Abstract: Vision-language models (VLMs) have demonstrated exceptional generalization capabilities for downstream tasks. Due to its efficiency, prompt le

Machine Learning-Based Graph Simplification for Symbolic Accelerators

arXiv:2605.08996v1 Announce Type: new Abstract: Graph-based accelerators have been widely adopted in symbolic data processing applications such as genomics, cybersecurity, and artificial intelligence.

Majority Bit-Aware Watermarking For Large Language Models

arXiv:2508.03829v2 Announce Type: replace Abstract: The growing deployment of Large Language Models (LLMs) has raised concerns about their misuse in generating harmful or deceptive content. To address

Many Needles in a Haystack: Active Hit Discovery for Perturbation Experiments

arXiv:2605.10196v1 Announce Type: new Abstract: High-throughput gene perturbation experiments can test several genetic interventions in parallel, yet experimental budgets remain limited. A central goa

Tutorials

Markerless Head Tracking for Accurate and Accessible Neuronavigation

arXiv:2602.07052v2 Announce Type: replace Abstract: Neuronavigation is widely used in biomedical research and interventions to guide the precise placement of instruments around the head to support pro

tutorialsarxiv-cs-cv

Masked Generative Transformer Is What You Need for Image Editing

arXiv:2605.10859v1 Announce Type: new Abstract: Diffusion models dominate image editing, yet their global denoising mechanism entangles edited regions with surrounding context, causing modifications t

Matching Meaning at Scale: Evaluating Semantic Search for 18th-Century Intellectual History through the Case of Locke

arXiv:2605.09236v1 Announce Type: cross Abstract: While digitized corpora have transformed the study of intellectual transmission, current methods rely heavily on lexical text reuse detection, capturi

Matrix Factorization for Practical Continual Mean Estimation Under User-Level Differential Privacy

arXiv:2601.22320v2 Announce Type: replace Abstract: We study continual mean estimation, where data vectors arrive sequentially and the goal is to maintain accurate estimates of the running mean. We ad

Max-pooling Network Revisited: Analyzing the Role of Semantic Probability in Multiple Instance Learning for Hallucination Detection

arXiv:2605.08863v1 Announce Type: new Abstract: Hallucination detection has become increasingly important for improving the reliability of large language models (LLMs). Recently, hybrid approaches suc

Measurement-Adapted Eigentask Representations for Photon-Limited Optical Readout

arXiv:2605.10008v1 Announce Type: cross Abstract: Optical readout in low-light imaging is fundamentally limited by measurement noise, including photon shot noise, detector noise, and quantization erro

Measuring and Decomposing Mode Separation via the Canonical Diffusion

arXiv:2605.08777v1 Announce Type: cross Abstract: Mode separation, namely how sharply a distribution fragments into barrier-separated clusters, is a fundamental geometric property of densities, diffic

Measuring Embedding Sensitivity to Authorial Style in French: Comparing Literary Texts with Language Model Rewritings

arXiv:2605.10606v1 Announce Type: cross Abstract: Large language models (LLMs) can convincingly imitate human writing styles, yet it remains unclear how much stylistic information is encoded in embedd

Mechanistic Independence: A Principle for Identifiable Disentangled Representations

arXiv:2509.22196v2 Announce Type: replace Abstract: Disentangled representations seek to recover latent factors of variation underlying observed data, yet their identifiability is still not fully unde

MedThink: Enhancing Diagnostic Accuracy in Small Models via Teacher-Guided Reasoning Correction

arXiv:2605.08094v1 Announce Type: cross Abstract: Accurate clinical diagnosis requires extensive domain knowledge and complex clinical reasoning capabilities. Although large language models (LLMs) hol

Mela: Test-Time Memory Consolidation based on Transformation Hypothesis

arXiv:2605.10537v1 Announce Type: new Abstract: Memory consolidation, the process by which transient experiences are transformed into stable, structured representations, is a foundational organizing p

Memorize Theorems, Not Instances: Probing SFT Generalization through Mathematical Reasoning

arXiv:2605.09270v1 Announce Type: cross Abstract: Supervised Fine-Tuning (SFT) is widely used for task-specific adaptation, yet recent work shows it systematically undermines reasoning generalization.

MeshFIM: Local Low-Poly Mesh Editing via Fill-in-the-Middle Autoregressive Generation

arXiv:2605.08744v1 Announce Type: cross Abstract: Autoregressive (AR) models can generate high-quality low-poly meshes from point clouds, but they still operate in an all-or-nothing manner: when a loc

Metacognitive Behavioral Tuning of Large Language Models for Multi-Hop Question Answering

arXiv:2602.22508v2 Announce Type: replace Abstract: Large Language Models (LLMs) often produce incorrect answers on multi-hop question answering even when the reasoning trace already contains a correc

METBRA25Y: Brazil Surface Meteorology Archive with Harmonized Variables and Quality Control

arXiv:2605.08701v1 Announce Type: new Abstract: This data paper describes METBRA25Y, a harmonized archive of hourly surface meteorological observations from Brazil derived from public historical recor

Micro-Defects Expose Macro-Fakes: Detecting AI-Generated Images via Local Distributional Shifts

arXiv:2605.09296v1 Announce Type: cross Abstract: Recent generative models can produce images that appear highly realistic, raising challenges in distinguishing real and AI-generated images. Yet exist

MicroDiffuse3D: A Foundation Model for 3D Microscopy Imaging Restoration

arXiv:2605.08566v1 Announce Type: new Abstract: Chemical imaging enables label-free visualization of cells, tissues and living systems while providing direct biochemical information that is difficult

MicroViTv2: Beyond the FLOPS for Edge Energy-Friendly Vision Transformers

arXiv:2605.10148v1 Announce Type: new Abstract: The Vision Transformer (ViT) achieves remarkable accuracy across visual tasks but remains computationally expensive for edge deployment. This paper pres

Mind the Gap No More: Achieving Zero-Gap Multimodal Integration via One Tokenizer

arXiv:2602.12286v2 Announce Type: replace-cross Abstract: A central challenge in developing Multimodal Large Language Models (MLLMs) is effectively integrating heterogeneous inputs into a cohesive rea

MineEvolve: Self-Evolution with Accumulated Knowledge for Long-Horizon Embodied Minecraft Agents

arXiv:2603.13131v3 Announce Type: replace Abstract: Long-horizon embodied intelligence requires agents to improve through interaction, not merely to execute plans generated from static goals. A centra