Search: “research”

Improving Sparse Autoencoder with Dynamic Attention

arXiv:2604.14925v1 Announce Type: new Abstract: Recently, sparse autoencoders (SAEs) have emerged as a promising technique for interpreting activations in foundation models by disentangling features i

JoyVASA: Portrait and Animal Image Animation with Diffusion-Based Audio-Driven Facial Dynamics and Head Motion Generation

DGX agent

arXiv:2411.09209v5 Announce Type: replace Abstract: Audio-driven portrait animation has made significant advances with diffusion-based models, improving video quality and lipsync accuracy. However, th

researcharxiv-cs-cv

17 Apr 2026

Just Pass Twice: Efficient Token Classification with LLMs for Zero-Shot NER

arXiv:2604.05158v2 Announce Type: replace Abstract: Large language models encode extensive world knowledge valuable for zero-shot named entity recognition. However, their causal attention mechanism, w

Kernel Neural Operators (KNOs) for Scalable, Memory-efficient, Geometrically-flexible Operator Learning

arXiv:2407.00809v3 Announce Type: replace Abstract: This paper introduces the Kernel Neural Operator (KNO), a provably convergent operator-learning architecture that utilizes compositions of deep kern

KVNN: Learnable Multi-Kernel Volterra Neural Networks

arXiv:2604.15141v1 Announce Type: new Abstract: Higher-order learning is fundamentally rooted in exploiting compositional features. It clearly hinges on enriching the representation by more elaborate

Latent Wavelet Diffusion For Ultra-High-Resolution Image Synthesis

arXiv:2506.00433v4 Announce Type: replace Abstract: High-resolution image synthesis remains a core challenge in generative modeling, particularly in balancing computational efficiency with the preserv

Learning and Generating Mixed States Prepared by Shallow Channel Circuits

arXiv:2604.01197v2 Announce Type: replace-cross Abstract: Learning quantum states from measurement data is a central problem in quantum information and computational complexity. In this work, we study

Learning to Concatenate Quantum Codes

arXiv:2604.14931v1 Announce Type: cross Abstract: Concatenating quantum error correction codes scales error correction capability by driving logical error rates down double-exponentially across levels

Leveraging graph neural networks and mobility data for COVID-19 forecasting

arXiv:2501.11711v2 Announce Type: replace Abstract: The COVID-19 pandemic has claimed millions of lives, spurring the development of diverse forecasting models. In this context, the true utility of co

Listening Alone, Understanding Together: Collaborative Context Recovery for Privacy-Aware AI

arXiv:2604.13348v1 Announce Type: new Abstract: We introduce CONCORD, a privacy-aware asynchronous assistant-to-assistant (A2A) framework that leverages collaboration between proactive speech-based AI

researcharxiv-cs-ai

Low-Cost System for Automatic Recognition of Driving Pattern in Assessing Interurban Mobility using Geo-Information

arXiv:2604.15216v1 Announce Type: cross Abstract: Mobility in urban and interurban areas, mainly by cars, is a day-to-day activity of many people. However, some of its main drawbacks are traffic jams

M3D-Net: Multi-Modal 3D Facial Feature Reconstruction Network for Deepfake Detection

arXiv:2604.14574v1 Announce Type: new Abstract: With the rapid advancement of deep learning in image generation, facial forgery techniques have achieved unprecedented realism, posing serious threats t

MapSR: Prompt-Driven Land Cover Map Super-Resolution via Vision Foundation Models

arXiv:2604.14582v1 Announce Type: new Abstract: High-resolution (HR) land-cover mapping is often constrained by the high cost of dense HR annotations. We revisit this problem from the perspective of m

MedVerse: Efficient and Reliable Medical Reasoning via DAG-Structured Parallel Execution

arXiv:2602.07529v3 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated strong performance and rapid progress in a wide range of medical reasoning tasks. However, their sequ

MEME-Fusion@CHiPSAL 2026: Multimodal Ablation Study of Hate Detection and Sentiment Analysis on Nepali Memes

arXiv:2604.14218v1 Announce Type: new Abstract: Hate speech detection in Devanagari-scripted social media memes presents compounded challenges: multimodal content structure, script-specific linguistic

MinShap: A Modified Shapley Value Approach for Feature Selection

arXiv:2604.15107v1 Announce Type: cross Abstract: Feature selection is a classical problem in statistics and machine learning, and it continues to remain an extremely challenging problem especially in

MIOFlow 2.0: A unified framework for inferring cellular stochastic dynamics from single cell and spatial transcriptomics data

arXiv:2603.22564v2 Announce Type: replace Abstract: Understanding cellular trajectories via time-resolved single-cell transcriptomics is vital for studying development, regeneration, and disease. A ke

ML-based approach to classification and generation of structured light propagation in turbulent media

arXiv:2604.14208v1 Announce Type: cross Abstract: This work develops machine learning approaches to classify structured light wave beams developing random speckle disturbances as they propagate throug

MLDAS: Machine Learning Dynamic Algorithm Selection for Software-Defined Networking Security

arXiv:2604.14957v1 Announce Type: cross Abstract: Network security is a critical concern in the digital landscape of today, with users demanding secure browsing experiences and protection of their per

Model-Based Reinforcement Learning Exploits Passive Body Dynamics for High-Performance Biped Robot Locomotion

arXiv:2604.14565v1 Announce Type: new Abstract: Embodiment is a significant keyword in recent machine learning fields. This study focused on the passive nature of the body of a biped robot to generate

researcharxiv-cs-ro

NEAT-NC: NEAT guided Navigation Cells for Robot Path Planning

arXiv:2604.15076v1 Announce Type: new Abstract: To navigate a space, the brain makes an internal representation of the environment using different cells such as place cells, grid cells, head direction

researcharxiv-cs-ro

Safety

NLP needs Diversity outside of 'Diversity'

arXiv:2604.14595v1 Announce Type: new Abstract: This position paper argues that recent progress with diversity in NLP is disproportionately concentrated on a small number of areas surrounding fairness

safetyarxiv-cs-cl

No More Guessing: a Verifiable Gradient Inversion Attack in Federated Learning

arXiv:2604.15063v1 Announce Type: new Abstract: Gradient inversion attacks threaten client privacy in federated learning by reconstructing training samples from clients' shared gradients. Gradients ag

NTIRE 2026 Challenge on Video Saliency Prediction: Methods and Results

arXiv:2604.14816v1 Announce Type: new Abstract: This paper presents an overview of the NTIRE 2026 Challenge on Video Saliency Prediction. The goal of the challenge participants was to develop automati

On the Expressive Power and Limitations of Multi-Layer SSMs

arXiv:2604.14501v1 Announce Type: new Abstract: We study the expressive power and limitations of multi-layer state-space models (SSMs). First, we show that multi-layer SSMs face fundamental limitation

One-shot Compositional 3D Head Avatars with Deformable Hair

arXiv:2604.14782v1 Announce Type: new Abstract: We propose a compositional method for constructing a complete 3D head avatar from a single image. Prior one-shot holistic approaches frequently fail to

OptEMA: Adaptive Exponential Moving Average for Stochastic Optimization with Zero-Noise Optimality

arXiv:2603.09923v3 Announce Type: replace Abstract: The Exponential Moving Average (EMA) is a cornerstone of widely used optimizers such as Adam. However, existing theoretical analyses of Adam-style m

Optimal last-iterate convergence in matrix games with bandit feedback using the log-barrier

arXiv:2604.15242v1 Announce Type: new Abstract: We study the problem of learning minimax policies in zero-sum matrix games. Fiegel et al. (2025) recently showed that achieving last-iterate convergence

OVT-MLCS: An Online Visual Tool for MLCS Mining from Long or Big Sequences

arXiv:2604.13037v1 Announce Type: cross Abstract: Mining multiple longest common subsequences (extit{MLCS}) from a set of sequences of three or more over a finite alphabet Sigma (a classical NP-hard p

researcharxiv-cs-ai

Path-Sampled Integrated Gradients

arXiv:2604.14338v1 Announce Type: new Abstract: We introduce path-sampled integrated gradients (PS-IG), a framework that generalizes feature attribution by computing the expected value over baselines

Physics-Informed Machine Learning for Pouch Cell Temperature Estimation

arXiv:2604.14566v1 Announce Type: new Abstract: Accurate temperature estimation of pouch cells with indirect liquid cooling is essential for optimizing battery thermal management systems for transport

Pie Day 2026

Ellie’s Pi Day post: https://mitadmissions.org/blogs/entry/pi-day-2026-food-institute/ How Ellie orchestrated the baking of 30 pies: https://mitadmissions.org/blogs/entry/behind-the-scenes-of-thirty-p

researchmit-tech-review

PixelDiT: Pixel Diffusion Transformers for Image Generation

arXiv:2511.20645v2 Announce Type: replace Abstract: Latent-space modeling has been the standard for Diffusion Transformers (DiTs). However, it relies on a two-stage pipeline where the pretrained autoe

Polyformer: a generative framework for thermodynamic modeling of polymeric molecules

arXiv:2604.14241v1 Announce Type: cross Abstract: The classic paradigm of structural biology is that the sequence of a biomolecule (protein, nucleic acid, lipid, etc) determines its conformation (shap

Portfolio Optimization Proxies under Label Scarcity and Regime Shifts via Bayesian and Deterministic Students under Semi-Supervised Sandwich Training

arXiv:2604.14206v1 Announce Type: new Abstract: This paper proposes a machine learning assisted portfolio optimization framework designed for low data environments and regime uncertainty. We construct

Predicting Post-Traumatic Epilepsy from Clinical Records using Large Language Model Embeddings

arXiv:2604.14547v1 Announce Type: new Abstract: Objective: Post-traumatic epilepsy (PTE) is a debilitating neurological disorder that develops after traumatic brain injury (TBI). Early prediction of P

Psychological Steering of Large Language Models

arXiv:2604.14463v1 Announce Type: new Abstract: Large language models (LLMs) emulate a consistent human-like behavior that can be shaped through activation-level interventions. This paradigm is conver

PUFFIN: Protein Unit Discovery with Functional Supervision

arXiv:2604.14796v1 Announce Type: cross Abstract: Proteins carry out biological functions through the coordinated action of groups of residues organized into structural arrangements. These arrangement

Q-MambaIR: Accurate Quantized Mamba for Efficient Image Restoration

arXiv:2503.21970v3 Announce Type: replace Abstract: State-Space Models (SSMs) have attracted considerable attention in Image Restoration (IR) due to their ability to scale linearly sequence length whi

QualiaNet: An Experience-Before-Inference Network

arXiv:2604.14193v1 Announce Type: new Abstract: Human 3D vision involves two distinct stages: an Experience Module, where stereo depth is extracted relative to fixation, and an Inference Module, where

Quantitative Approximation Rates for Group Equivariant Learning

arXiv:2602.20370v2 Announce Type: replace Abstract: The universal approximation theorem establishes that neural networks can approximate any continuous function on a compact set. Later works in approx

Quantization of Spiking Neural Networks Beyond Accuracy

arXiv:2604.14487v1 Announce Type: new Abstract: Quantization is a natural complement to the sparse, event-driven computation of Spiking Neural Networks, reducing memory bandwidth and arithmetic cost f

Quantum-inspired tensor networks in machine learning models

arXiv:2604.14287v1 Announce Type: new Abstract: Tensor networks were developed in the context of many-body physics as compressed representations of multiparticle quantum states. These representations

RACER: Retrieval-Augmented Contextual Rapid Speculative Decoding

arXiv:2604.14885v1 Announce Type: new Abstract: Autoregressive decoding in Large Language Models (LLMs) generates one token per step, causing high inference latency. Speculative decoding (SD) mitigate

Random Matrix Theory for Deep Learning: Beyond Eigenvalues of Linear Models

arXiv:2506.13139v2 Announce Type: replace-cross Abstract: Modern Machine Learning (ML) and Deep Neural Networks (DNNs) often operate on high-dimensional data and rely on overparameterized models, wher

ReasonScaffold: A Scaffolded Reasoning-based Annotation Protocol for Human-AI Co-Annotation

arXiv:2603.21094v3 Announce Type: replace Abstract: Human annotation is central to NLP evaluation, yet subjective tasks often exhibit substantial variability across annotators. While large language mo

Rethinking LLM-Driven Heuristic Design: Generating Efficient and Specialized Solvers via Dynamics-Aware Optimization

arXiv:2601.20868v2 Announce Type: replace Abstract: Large Language Models (LLMs) have advanced the field of Combinatorial Optimization through automated heuristic generation. Instead of relying on man

Revisiting Token Compression for Accelerating ViT-based Sparse Multi-View 3D Object Detectors

arXiv:2604.14563v1 Announce Type: new Abstract: Vision Transformer (ViT)-based sparse multi-view 3D object detectors have achieved remarkable accuracy but still suffer from high inference latency due