research

Sustainable Metal-Organic Framework Water Harvesters in the Artificial Intelligence Era

arXiv:2605.29179v1 Announce Type: cross Abstract: Metal-organic frameworks (MOFs) are excellent candidates for water harvesting due to their tunable pore environments, which can be precisely engineere

Research

Tailoring the Curriculum: Student-Centered Reasoning Distillation via Dynamic Data-Model Compatibility

DGX agent

arXiv:2605.29229v1 Announce Type: new Abstract: Reasoning distillation transfers complex reasoning abilities from large language models (LLMs) to smaller ones, yet its success depends on how well the

researcharxiv-cs-ai

29 May 2026

Taming Data Challenges in ML-based Security Tasks Using Generative AI

arXiv:2507.06092v4 Announce Type: replace-cross Abstract: Machine learning-based supervised classifiers are widely used for security tasks, and their improvement has been largely focused on algorithmi

The Biosecurity Blind Spot: Systematic Dual-use Detection in Open Science Infrastructure

arXiv:2605.28843v1 Announce Type: cross Abstract: AI is transforming life sciences research at unprecedented speed, accelerating discovery across protein structure prediction, genome modeling, and dru

The Complexity of Verifying Feedforward Neural Networks in Quantised Settings

arXiv:2605.29537v1 Announce Type: cross Abstract: We investigate the computational complexity of neural network verification in quantised settings. We distinguish three classes of Feedforward Neural N

The deadly Ebola outbreak is proving difficult to control

The alert was raised on May 5. Four health-care workers in the Ituri Province of the Democratic Republic of the Congo had died from an unknown illness within four days. Rapid response teams were sent

researchmit-tech-review

The Download: unlocking lithium and controlling Ebola

This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. How a new extraction process could unlock the world’s lithium

researchmit-tech-review

The Impact of Semantic Pairs on Self-Supervised Representation Learning

arXiv:2510.08722v3 Announce Type: replace-cross Abstract: Instance discrimination learns visual representations by treating different augmented views of the same image as positive pairs. While this en

The Interplay Between Interpolation and Aggregation in Regression: Optimal Sample Complexity

arXiv:2605.29819v1 Announce Type: new Abstract: This work investigates theoretically the interplay between interpolation and aggregation in regression. We establish that the gamma-graph dimension char

The Little Book of Generative AI Foundations: An Intuitive Mathematical Primer

arXiv:2605.29713v1 Announce Type: cross Abstract: This book provides a compact, derivation-oriented introduction to the mathematical foundations of modern generative artificial intelligence. Rather th

Thinking Before Constraining: A Unified Decoding Framework for Large Language Models

arXiv:2601.07525v2 Announce Type: replace-cross Abstract: Natural generation allows Large Language Models (LLMs) to produce free-form responses with rich reasoning, yet the lack of structure makes out

Token Inflation: How Dishonest Providers Can Overcharge for Large Language Model Usage

arXiv:2605.30040v1 Announce Type: cross Abstract: Per-token billing is now the standard pricing model for commercial large language models (LLMs), so the honesty of reported token counts directly affe

Topological Order in Neural Wavefunctions

arXiv:2512.01863v2 Announce Type: replace-cross Abstract: Topologically ordered states are among the most interesting quantum phases of matter that host emergent quasi-particles having fractional char

Towards a Foundation Model for the Martian Atmosphere

arXiv:2605.28851v1 Announce Type: cross Abstract: The martian atmosphere hosts dynamical phenomena ranging from planet-encircling dust storms to mesoscale orographic clouds and nocturnal low-level jet

Towards Consistent Video Geometry Estimation

arXiv:2605.30060v1 Announce Type: new Abstract: This work presents ViGeo, a feed-forward foundation model for recovering spatially dense and temporally consistent geometry from video sequences. Built

Towards Continuous-time Causal Foundation Models

arXiv:2605.28880v1 Announce Type: new Abstract: Extending discrete-time causal Prior-data Fitted Networks for time series to continuous time invites writing the mechanism as a stochastic differential

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy

arXiv:2509.21190v4 Announce Type: replace-cross Abstract: Time series anomaly detection (TSAD) is a critical task, but developing models that generalize to unseen data in a zero-shot manner remains a

Towards the automated segmentation of epicardial and mediastinal fats: A multi-manufacturer approach using intersubject registration and random forest

arXiv:2605.29217v1 Announce Type: new Abstract: The amount of fat on the surroundings of the heart is correlated to several health risk factors such as carotid stiffness, coronary artery calcification

Traditional machine learning vs. deep learning from dynamic graph representations of proteins' 3D folds in the task of protein structure classification

arXiv:2605.29228v1 Announce Type: new Abstract: Protein structure classification (PSC) uses supervised learning to predict a protein's CATH/SCOP(e) class from the protein's sequence or 3D structural f

Trajectory Constraints for Imaging Inverse Problems

arXiv:2605.29012v1 Announce Type: new Abstract: Diffusion-based and iterative methods have become effective tools for solving imaging inverse problems. Their reconstruction process naturally forms a t

Transcribing Children's Speech: ASR Performance and Obtaining Reliable Orthographic Transcriptions

arXiv:2605.28833v1 Announce Type: cross Abstract: Automatic speech recognition (ASR) has the potential to substantially reduce manual annotation effort in child speech research by generating automatic

Treatment-Conditioned Diffusion for Forecasting Neurodegenerative Disease Progression

arXiv:2605.29932v1 Announce Type: cross Abstract: Forecasting the progression of neurodegenerative diseases, such as Parkinson's disease, is essential for effective long-term planning and personalized

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models

arXiv:2506.12815v2 Announce Type: replace Abstract: Recent advances in Trajectory Optimization (TO) models have achieved remarkable success in offline reinforcement learning. However, their vulnerabil

Turbulence-Robust Dynamic Object Segmentation with Multi-Signal Priors and SAM2 Refinement

arXiv:2605.29292v1 Announce Type: new Abstract: This technical report presents our solution for the CVPR 2026 UG2+ Challenge Track 3: Dynamic Object Segmentation in Turbulence (DOST). We design a trai

Ultra-Reduced-Impact-Encased-Logging (URIEL): propose a new method for selective sustainable logging and post-harvest silvicultural treatment in tropical forest using airborne robotics systems

arXiv:2605.28883v1 Announce Type: new Abstract: Tropical forests worldwide are under intense deforestation pressure driven by economic and political interests, and scientific evidence suggests this de

Uncertainty-driven 3D Gaussian Splatting Active Mapping via Anisotropic Visibility Field

arXiv:2605.30342v1 Announce Type: new Abstract: We present Gaussian Splatting Anisotropic Visibility Field (GAVIS), a novel framework for uncertainty quantification and active mapping in 3DGS. Our key

Understanding Fact Recall in Language Models: Why Two-Stage Training Encourages Memorization but Mixed Training Teaches Knowledge

arXiv:2505.16178v2 Announce Type: replace Abstract: While fine-tuning is the standard for injecting factual knowledge into large language models (LLMs), the mechanisms enabling reliable fact recall vi

Understanding the Ability of LLMs to Handle Character-Level Perturbation

arXiv:2510.14365v4 Announce Type: replace Abstract: This work investigates the resilience of contemporary large language models (LLMs) against frequent character-level perturbations. We examine three

UniSteer: Text-Guided Flow Matching in Activation Space for Versatile LLM Steering

arXiv:2605.30076v1 Announce Type: new Abstract: Activation-based control steers large language models (LLMs) by intervening on their internal representations during inference, and has emerged as an ef

Unlocking the Working Memory of Large Language Models for Latent Reasoning

arXiv:2605.30343v1 Announce Type: cross Abstract: To improve the reasoning capabilities of large language models, test-time compute is typically scaled by generating intermediate tokens before the fin

Unsupervised Hierarchical Skill Discovery

arXiv:2601.23156v2 Announce Type: replace Abstract: We consider the problem of unsupervised skill segmentation and hierarchical structure discovery in reinforcement learning. While recent approaches h

Unveiling Multi-regime Patterns in SciML: Distinct Failure Modes and Regime-specific Optimization

arXiv:2605.29153v1 Announce Type: cross Abstract: Neural networks trained under different hyperparameter settings can fall into distinct training 'regimes,' with consistent behavior within regimes and

Unveiling the Visual Counting Bottleneck in Vision-Language Models

arXiv:2605.30170v1 Announce Type: cross Abstract: While Large Vision-Language Models (VLMs) excel at interpolation, they suffer catastrophic failures in systematic generalization, most notably in visu

Valency Classification of Mapudungun Verbal Roots. Established by the language's own morphotactics

arXiv:2604.00789v3 Announce Type: replace Abstract: In the previous work, a lexical (re)categorisation -- or confirmation of the given category -- of roots identified as verbal was undertaken to deter

Veda: Scalable Video Diffusion via Distilled Sparse Attention

arXiv:2605.30325v1 Announce Type: new Abstract: Scaling Diffusion Transformers to generate high-resolution, long videos is constrained by the quadratic cost of self-attention, and existing sparse atte

ViASNet: A Video Ad Saliency Network for Predicting Dynamic Saliency and Viewer Engagement

arXiv:2605.29302v1 Announce Type: new Abstract: The digital media landscape has seen a pervasive shift toward short-form video advertising on TV, social media and e-commerce platforms. The present stu

Visual Spatial Learning: Single-Field Spatial Interpolation Using Convolutional Neural Networks

arXiv:2605.30167v1 Announce Type: cross Abstract: Predicting a complete spatially correlated field from sparse observations is a fundamental challenge in spatial statistics and environmental modelling

Wait! There's a Way Out: A Decision Mechanism for Forecasting Conversational Derailment

arXiv:2605.29243v1 Announce Type: cross Abstract: Forecasting conversational derailment is the task of predicting, as the conversation unfolds, whether it will eventually derail into personal attacks.

Wasserstein Contraction of Coordinate Ascent Variational Inference

arXiv:2605.30253v1 Announce Type: cross Abstract: We study the contraction in Wasserstein distance of the coordinate ascent variational inference algorithm. This is shown to hold under a transport-inf

WaterSearch: A Quality-Aware Search-based Watermarking Framework for Large Language Models

arXiv:2512.00837v2 Announce Type: replace Abstract: Watermarking acts as a critical safeguard in text generated by Large Language Models (LLMs). By embedding identifiable signals into model outputs, w

Weakly Supervised Detection and Temporal Localization of Whale Calls in Long-Duration Bioacoustic Data

arXiv:2502.20838v3 Announce Type: replace-cross Abstract: Passive acoustic monitoring (PAM) systems generate continuous recordings spanning months, yet automated bioacoustic analysis of whale calls re

What are They Thinking? Delineation, Probing and Tracking of Concepts in LLMs

arXiv:2605.28823v1 Announce Type: new Abstract: As the influence of LLMs expands, it is imperative to gain insight into their decisions. One way to do that is to develop probes that detect the presenc

When Do Graph Foundation Models Transfer? A Data-Centric Theory

arXiv:2605.29828v1 Announce Type: new Abstract: Graph foundation models (GFMs) aim to reuse a single backbone across diverse graph domains, yet their transfer is often uneven and can exhibit negative

When Models Disagree: Rethinking LLM Evaluation for Public Comment Analysis

arXiv:2605.29025v1 Announce Type: new Abstract: Federal agencies are deploying large language models (LLMs) to categorize public comment corpora, where the model's organization of the record shapes wh

When RL Suppresses Its Own Vocabulary: Recovering Reasoning Diversity in Puzzle-to-Math Transfer

arXiv:2605.29190v1 Announce Type: cross Abstract: Reinforcement learning using verifiable rewards (RLVR) improves LLM reasoning, but the conditions under which it transfers across domains -- and why i

When, why, and how do diffusion posterior samplers fail? A finite-sample lens

arXiv:2605.30330v1 Announce Type: new Abstract: Diffusion models have excellent capacity to model complex distributions of natural data, which has made them a popular and effective choice for posterio

Woah. A profound shift in American science is coming. Every federal research grant could soon require sign-off from a political appointee. S…

Woah. A profound shift in American science is coming. Every federal research grant could soon require sign-off from a political appointee. Scientific progress depends on funding decisions grounded in

researchyann-lecun--x

X-GS: An Extensible Framework for Perceiving and Thinking via 3D Gaussian Splatting

arXiv:2603.09632v3 Announce Type: replace-cross Abstract: 3D Gaussian Splatting (3DGS) has emerged as a powerful technique for novel view synthesis, subsequently extending into numerous spatial AI app