research

DivCon-NeRF: Diverse and Consistent Ray Augmentation for Few-Shot NeRF

arXiv:2503.12947v3 Announce Type: replace Abstract: Neural Radiance Field (NeRF) has shown remarkable performance in novel view synthesis but requires numerous multi-view images, limiting its practica

Domain Adaptation Under Wireless Network Constraints: When Does It Become Green?

DGX agent

arXiv:2606.23047v1 Announce Type: cross Abstract: The deployment of data-driven models in 6G wireless networks is increasingly challenged by frequent distribution shifts that degrade performance over

researcharxiv-cs-lg

23 Jun 2026

Domain-incremental audio classification using domain-specific experts and prototype classifier

arXiv:2606.22952v1 Announce Type: cross Abstract: This technical report presents submission systems for Task 7(domain-incremental audio classification) of the DCASE 2026 Challenge. The main obstacle i

DP-FedSOFIM: Differentially Private Federated Stochastic Optimization using Regularized Fisher Information Matrix

arXiv:2601.09166v3 Announce Type: replace Abstract: Differentially private federated learning (DP-FL) often suffers from slow convergence under tight privacy budgets because the noise required for pri

DPLAN: Minimal Connectivity to Floorplan Generation

arXiv:2606.21159v1 Announce Type: cross Abstract: Automated floor plan generation is an important problem in computational architectural design. The goal is to construct a floor plan from user-defined

researcharxiv-cs-ro

DPO Unchained: Your Training Algorithm is Secretly Disentangled in Human Choice Theory (and its Loss' Convexity is Dispensable)

arXiv:2507.07855v4 Announce Type: replace Abstract: Normative theories allow one to elicit key parts of a ML algorithm from first principles, which is crucial at a time of championed scrutiny for ML w

Dual-Stream EEG Decoding for 3D Visual Perception

arXiv:2606.22182v1 Announce Type: new Abstract: This paper explores a novel brain decoding model for 3D shape perception through a dual pathway architecture mirroring biological vision. Our bio-inspir

Dynamic estimation of slowly varying sequences

arXiv:2606.23655v1 Announce Type: new Abstract: We consider the problem of sequentially approximating functions of each element in a slowly-varying sequence, i.e. one where the magnitude alpha_i of th

ECGFlowCMR: Pretraining with ECG-Generated Cine CMR Helps Cardiac Disease Classification and Phenotype Prediction

arXiv:2601.20904v3 Announce Type: replace-cross Abstract: Cardiac Magnetic Resonance (CMR) imaging provides a comprehensive assessment of cardiac structure and function but remains constrained by high

EchoingPixels: Aliasing-Resistant Joint Token Reduction for Audio-Visual LLMs

arXiv:2512.10324v2 Announce Type: replace Abstract: Audio-Visual Large Language Models (AV-LLMs) face prohibitive computational costs of processing massive, redundant audio-visual tokens. Existing uni

Efficient Network Inference via Hardware-Aware Architecture Search, Model Pruning & Quantization

arXiv:2606.23210v1 Announce Type: new Abstract: Embedded global navigation satellite system (GNSS) interference monitoring requires fast and memory-efficient inference to process large volumes of raw

Elephant alert! AI warning systems aim to avoid deadly clashes

India is home to about 60% of the world’s wild Asian elephants, and around 80% of the animals’ habitat lies outside protected areas, according to the Ministry of Environment, Forest, and Climate Chang

researchmit-tech-review

Embedding Linear Equality Constraints in Probabilistic Neural Networks for Dynamic Modelling

arXiv:2606.21728v1 Announce Type: new Abstract: Machine learning models are increasingly used to model chemical process systems, yet they often lack principled uncertainty quantification and mechanism

EML Trees Are Universal Approximators

arXiv:2606.23179v1 Announce Type: new Abstract: The recently introduced EML (Exp-Minus-Log) function acts as continuous analogue of NAND gates, providing a compositional building block capable of repr

Energy Injection Identification enabled Disaggregation with Deep Multi-Task Learning

arXiv:2508.14600v4 Announce Type: replace Abstract: Non-Intrusive Load Monitoring (NILM) offers a cost-effective method to obtain fine-grained appliance-level energy consumption in smart homes and bui

Engineered “mini livers” could be injected as an alternative to transplantation

A technology developed by Professor Sangeeta Bhatia, SM ’93, PhD ’97, and colleagues could offer new hope to the thousands of Americans with chronic liver disease who are waiting for an organ transpla

researchmit-tech-review

Enhancing Cognitive Workload Classification Using Integrated LSTM Layers and CNNs for fNIRS Data Analysis

arXiv:2407.15901v2 Announce Type: replace Abstract: Functional near-infrared spectroscopy (fNIRS) is employed as a non-invasive method to monitor functional brain activation by capturing changes in th

Enhancing Differentially Private Mechanisms via Empirical Bayes

arXiv:2606.21107v1 Announce Type: new Abstract: Differential privacy (DP) has become the gold standard for ensuring the privacy protection of machine learning and statistical algorithms in recent deca

Escaping the Variance Trap: Jacobian-Free Dynamics for Root-Finding Bilevel Optimization

arXiv:2606.22433v1 Announce Type: new Abstract: Many central machine learning tasks, from entropy tuning in reinforcement learning to equilibrating generative adversarial networks, are fundamentally s

Evaluating Document-Tuned Transformer Representations for Person-level Mental Health Assessment

arXiv:2606.21622v1 Announce Type: cross Abstract: Person-level psychological assessment requires aggregating meaning across many messages from the same individual, a task that document-level training

Evaluating self-supervised echocardiographic representations across downstream extraction strategies for left-ventricular segmentation and ejection fraction estimation

arXiv:2606.22943v1 Announce Type: new Abstract: Self-supervised learning (SSL) is increasingly used in medical imaging to reduce annotation requirements, but representation quality is often judged usi

Evolutionary Optimization Reveals Structural Constraints on Reservoir Architecture for Spatiotemporal Chaos

arXiv:2606.22765v1 Announce Type: cross Abstract: Biological systems maintain function in fluctuating environments by transforming past stimulation into internal dynamical states that support future-o

Exact and Approximate Range Queries for Efficient Ball Mapper Construction

arXiv:2601.01405v2 Announce Type: replace-cross Abstract: Ball Mapper is a tool in topological data analysis that summarizes a finite metric dataset by covering it with metric balls and encoding their

Explainable AI for Mental Health Prediction in Drug-Affected Populations with Dragonfly Algorithm and GAN Oversampling

arXiv:2606.22780v1 Announce Type: new Abstract: Mental illnesses among drug users are an increasing international issue, particularly in regions where early detection cannot be easily undertaken. The

Exploration of LLMs, EEG, and behavioral data to measure and support attention and sleep

arXiv:2408.07822v2 Announce Type: replace-cross Abstract: We explore the application of large language models (LLMs), pre-trained models with massive textual data for detecting and improving attention

Expressivity Saturation: Reduced Affine Region Usage Under Increasing Task Complexity

arXiv:2606.21687v1 Announce Type: new Abstract: Piecewise-affine neural networks (e.g., with ReLU or LeakyReLU activations) implement continuous piecewise-affine maps, and the number of affine regions

Failure Analysis in Transition: An Industry Survey of Challenges, Priorities, and Standardization Needs in Advanced Packaging and Heterogeneous Integration

arXiv:2606.22149v1 Announce Type: cross Abstract: Failure analysis is being reshaped by heterogeneous integration, chiplet-based architectures, hybrid bonding, backside technologies, & increasingly bu

Faithful Grounded Visual Reasoning via Learned Proxy-Tokens

arXiv:2606.23354v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable success in Visual Question Answering (VQA), yet their 'black-box' nature hinders deplo

FARM: Find Anything using Relational Spatial Memory

arXiv:2606.15476v2 Announce Type: replace Abstract: Robots operating in homes, warehouses, and other object-rich environments need memory systems that can find specific object instances on demand. Obj

researcharxiv-cs-ro

FCR: Investigating Generative AI models for Forensic Craniofacial Reconstruction

arXiv:2508.18031v2 Announce Type: replace Abstract: Craniofacial reconstruction in forensics is one of the processes to identify victims of crime and natural disasters. Identifying an individual from

Federated Learning for Global Carbon Emission Forecasting: A Hybrid Time-Series Approach with Statistical and Neural Models

arXiv:2606.22618v1 Announce Type: new Abstract: Climate change, primarily driven by carbon dioxide (CO2) emissions, requires accurate forecasting tools to support effective mitigation policies and sus

FedOT: Ownership Verification and Leakage Tracing via Watermarks for Federated LDMs

arXiv:2606.22875v1 Announce Type: new Abstract: Training Latent Diffusion Models (LDMs) within Federated Learning (FL) has attracted increasing attention due to its ability to combine the powerful gen

Feed-forward Motion In-betweening for Any 4D

arXiv:2606.22131v1 Announce Type: new Abstract: 4D dynamics (3D geometry evolving over time) is a fundamental representation of the physical world and plays a crucial role in world modeling (e.g., ani

FetSelect: Task-Specific Architectures and Self-Supervised Learning for Automated Fetal Ultrasound Frame Selection

arXiv:2606.22487v1 Announce Type: new Abstract: Automated frame selection for fetal biometry remains under addressed, with most prior work targeting generic quality assessment or downstream measuremen

Few-Shot Hyperspectral Aphid Detection via FastGAN Synthetic Data Generation, Transformer-Based Classification and Explainable AI

arXiv:2606.21267v1 Announce Type: new Abstract: Early detection of aphid infestation in crops is essential for preventing yield loss and reducing unnecessary pesticide use. Hyperspectral imaging combi

Fidelity- and Perception-Aware Local Implicit Attention for Arbitrary-Scale Image Super-Resolution

arXiv:2606.21910v1 Announce Type: new Abstract: Arbitrary-scale image super-resolution (ASISR) aims to reconstruct high-resolution images from low-resolution inputs over a continuous range of upscalin

Fine-grained Human Motion Understanding with Language Models

arXiv:2606.20888v1 Announce Type: new Abstract: In this work, we propose methodname, an LLM-based model for fine-grained human motion understanding that represents motion as a sequence of skeletal pos

Fine-Grained Uncertainty Quantification for Long-Form Language Model Outputs: A Comparative Study

arXiv:2602.17431v2 Announce Type: replace-cross Abstract: Uncertainty quantification has emerged as an effective approach to closed-book hallucination detection for LLMs, but existing methods are larg

FlexServe: A Fast and Secure LLM Serving System for Mobile Devices with Flexible Resource Isolation

arXiv:2606.23370v1 Announce Type: cross Abstract: Device-side Large Language Models (LLMs) have grown explosively, offering stronger privacy and higher availability than their cloud-side counterparts.

Flow Annealing Posterior Sampling for Function-Space Regression and Inverse Problems

arXiv:2606.22346v1 Announce Type: cross Abstract: Principled regression for stochastic processes is a long-standing challenge with deep connections to scientific inverse problems. We introduce Flow An

Flow Matching for Efficient and Scalable Data Assimilation

arXiv:2508.13313v5 Announce Type: replace-cross Abstract: Data assimilation (DA) estimates a dynamical system's state from noisy observations. Recent generative models like the ensemble score filter (

FoMoE: Breaking the Full-Replica Barrier with a Federation of MoEs

arXiv:2606.19025v2 Announce Type: replace Abstract: Pre-training Large Language Models (LLMs) typically demands large-scale infrastructure with tightly coupled hardware accelerators. Mixture-of-Expert

ForeHOI: Feed-forward 3D Object Reconstruction from Daily Hand-Object Interaction Videos

arXiv:2602.06226v2 Announce Type: replace Abstract: The ubiquity of monocular videos capturing daily hand-object interactions presents a valuable resource for embodied intelligence. While 3D hand reco

FORGE: Fused On-Register Gradient Elimination for Memory-Efficient LLM Training

arXiv:2606.22932v1 Announce Type: new Abstract: Reverse-mode differentiation computes every weight gradient, writes it to memory, and only then lets the optimizer read it back. This two-phase schedule

Foundation Models for Epileptogenic Zone Identification in Drug-Resistant Epilepsy

arXiv:2606.22657v1 Announce Type: new Abstract: Accurate identification of the epileptogenic zone (EZ) is essential for seizure freedom after resective surgery in drug-resistant epilepsy, yet seizure

FPGA-Accelerated Neuromorphic Vision System for Real-Time Orbital Object Detection

arXiv:2606.20727v1 Announce Type: cross Abstract: The escalating congestion in orbital space demands advanced monitoring solutions. This work presents a comprehensive open-source framework for neuromo

Frequency-Domain Neural ODEs for Modeling Non-Linear Dynamical Systems

arXiv:2606.22075v1 Announce Type: new Abstract: Standard continuous-depth models, such as Neural Ordinary Differential Equations (NODEs), offer significant advantages in modeling physical systems by l

Frequency Response Identification of Low-Order Systems: Finite-Sample Analysis

arXiv:2508.17142v3 Announce Type: replace-cross Abstract: This paper proposes a frequency-domain estimator for low-order systems from repeated noisy measurements. The estimator minimizes a quadratic d