research

Timeripple: Accelerating vDiTs by Understanding the Spatio-Temporal Correlations in Latent Space

arXiv:2511.12035v2 Announce Type: replace-cross Abstract: The recent surge in video generation has shown the growing demand for high-quality video synthesis using large vision models. Existing video g

Research

Total Variation Distance Estimation in Autoregressive Models

DGX agent

arXiv:2607.19510v1 Announce Type: new Abstract: Modern LLM deployments use a number of implementation choices and inference optimizations (e.g., batching, custom kernels, and quantization) on top of f

researcharxiv-cs-lg

23 Jul 2026

Toward Reliable RGB-D Semantic Segmentation: Handling Missing Modalities via Condition Dropout

arXiv:2607.20326v1 Announce Type: cross Abstract: RGB-D semantic segmentation has achieved remarkable progress, yet most models assume that RGB and depth are always available. In practice, failures or

Toward Seasonal Guidelines for Robust Deep-Learning Sentinel-2 Building Detection in Different Area Types

arXiv:2607.19994v2 Announce Type: new Abstract: Sentinel-2 imagery offers open access, global coverage, and frequent revisit times, making it attractive for practical building mapping at scale; howeve

Towards Miniature Humanoid Tele-Loco-Manipulation Using Virtual Reality and Reinforcement Learning

arXiv:2607.20399v1 Announce Type: cross Abstract: Full-sized humanoid robot capabilities have grown exponentially in recent years, aiming towards general-purpose deployment in human environments. A po

Trace: A Taxonomy-Guided Environment for Multidomain Visual Reasoning

arXiv:2607.19790v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has substantially improved language-model reasoning, yet its extension to vision-language models r

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI

arXiv:2603.07466v2 Announce Type: replace-cross Abstract: Cloud-based infrastructure has become the dominant platform for deploying large models, particularly large language models (LLMs). Fine-tuning

Two-Step Occupation Coding

arXiv:2607.20101v1 Announce Type: new Abstract: Occupation coding links job titles in free text to occupational taxonomies and is a core task in labor market research. Existing approaches typically ad

researcharxiv-cs-cl

Understanding Developer Pain Points in Federated Learning: Insights from Stack Overflow and GitHub

arXiv:2607.19621v1 Announce Type: cross Abstract: Federated Learning (FL) enables collaborative model training without centralizing raw data, but building and operating FL systems remains difficult du

User-Centric Modeling of Transactional Sequences with Explainable State Space Models

arXiv:2607.20228v1 Announce Type: new Abstract: We propose a hybrid approach for user-centric modeling of transactional event sequences that combines contrastive representation learning (CoLES) with S

UVFaceFusion: Fast Multi-view Topologically Consistent Face Reconstruction in the Wild via UV-space Neural Fusion

arXiv:2607.18798v1 Announce Type: new Abstract: Reconstructing high-fidelity facial geometry with an assigned topology is essential for digital avatar creation and animation, yet existing automated me

V2F: Vision-Informed Grasp Force Prediction for Damage-Aware Robotic Handling of Date Fruits

arXiv:2607.19804v1 Announce Type: new Abstract: This paper presents a vision-informed grasp force prediction framework for robotic handling of date fruits. Addressing the dual challenge of high detach

Vera: Identity-Faithful Human Subject-to-Video Generation

arXiv:2607.20247v1 Announce Type: new Abstract: Subject-to-video (S2V) generation has made substantial progress in preserving reference subjects across diverse categories, yet generic subject consiste

VizRAG: Enhancing Retrieval-Augmented Generation with Hypergraph Visualization

arXiv:2607.19830v1 Announce Type: new Abstract: Hypergraph-based RAG systems surpass traditional graph-based approaches by organizing complex n-ary atomic facts among entities, rather than relying sol

researcharxiv-cs-cl

VQ-Transplant: Efficient VQ-Module Integration for Pre-trained Visual Tokenizers

arXiv:2607.19575v1 Announce Type: new Abstract: Vector Quantization (VQ) underpins modern discrete visual tokenization. However, training quantization modules for state-of-the-art VQ-based models requ

WanSong v1.0 Technical Report

arXiv:2607.14749v3 Announce Type: replace-cross Abstract: Music generation foundation models have recently attracted significant industry attention. However, achieving efficient generation and high-fi

Wavefront Parallelization for Efficient Learned Image Compression

arXiv:2607.19082v1 Announce Type: cross Abstract: Autoregressive context models are foundational for learned image compression,but they suffer from slow serial inference. Existing acceleration methods

When Does Consensus Beat Voting? A Critical Analysis of Statistical Label Fusion in Medical Image Segmentation

arXiv:2607.19402v1 Announce Type: new Abstract: This paper provides a rigorous, self-contained investigation of consensus segmentation. We derive the mathematical foundations from first principles --

World Modeling with JEPA has recently gained traction thanks to a novel anti-collapse mechanism called 'SIGReg' (by @ylecun and @randall_bal…

World Modeling with JEPA has recently gained traction thanks to a novel anti-collapse mechanism called 'SIGReg' (by @ylecun and @randall_balestr). The math is clean, but it is rarely explained from fi

Zero-Observation User Reactivation with Gap-Driven Dimensional Gating

arXiv:2607.19802v1 Announce Type: cross Abstract: Sequential recommendation (SR) models capture continuously observed behavior, but a returning user may have no interactions for months or years. We de

Closed source safeguards that infantalize us all and leave American companies defenseless are a menace. Gated access is a menace. Who cares …

Closed source safeguards that infantalize us all and leave American companies defenseless are a menace. Gated access is a menace. Who cares if 100 companies get to defend themselves because they got o

22 Jul 2026

Accelerating Text-to-Video Generation with Calibrated Sparse Attention

researchapple-ml-research

Recent diffusion models enable high-quality video generation, but suffer from slow runtimes. The large transformer-based backbones used in these models are bottlenecked by spatiotemporal attention. In

Highly performant open weights frontier models such as Kimi are a competitive threat to OpenAI & Anthropic, but probably for everyone else t…

Highly performant open weights frontier models such as Kimi are a competitive threat to OpenAI & Anthropic, but probably for everyone else these are a win. Hope more US entities will release top quali

Not because Andrej is saying it but I think voice is goated. And you can mix it with other modalities for even richer prompting. I recorded …

Not because Andrej is saying it but I think voice is goated. And you can mix it with other modalities for even richer prompting. I recorded a session a few weeks back to demo the power of multimodal p

researchdair-ai--x

Open-source is not the cause of the cybersecurity crisis, it's the solution! https://huggingface.co/fdtn-ai

In July 2026, Clement Delangue tweeted that “Open‑source is not the cause of the cybersecurity crisis, it’s the solution!” linking to the Hugging Face page *fdtn‑ai* (https://huggingface.co/fdtn-ai).

Tri-Net v2: Open-source implementation of our Scientific Reports paper on unified skin lesion and symptom-based monkeypox detection [R]

researchr-machinelearning

Hi everyone, We've open-sourced Tri-Net v2, the official implementation accompanying our recently published Scientific Reports (Nature Portfolio) paper: 'Tri-Net: Unified Deep Learning for Skin Lesion

A 3DGS-Driven Dynamic Viewpoint and Vibrotactile Framework for Subsea Teleoperation Validated via fNIRS

arXiv:2607.13067v1 Announce Type: new Abstract: Teleoperating remotely operated vehicles (ROVs) in flooded, cluttered infrastructure is fundamentally limited by narrow 2D egocentric views and subsea c

A Bayesian framework for the uncanny valley in humanoid robot design

arXiv:2607.13060v1 Announce Type: new Abstract: The uncanny valley is a long-standing empirical rule in humanoid robot design: making robots more human-like can reduce, rather than increase, affinity.

A Hybrid Mamba for Audio-Visual Navigation

arXiv:2607.13110v1 Announce Type: cross Abstract: Since the paradigm centered on convolutional neural networks and recurrent architectures was established in 2020, the fundamental backbone networks fo

A novel network for classification of cuneiform tablet metadata

arXiv:2603.03892v2 Announce Type: replace-cross Abstract: In this paper, we present a network structure for classifying metadata of cuneiform tablets. The problem is of practical importance, as the si

A novel unsupervised machine learning strategy to handle multimodal cardiac PET/MRI data

arXiv:2607.13936v1 Announce Type: new Abstract: Arrhythmogenic left ventricular cardiomyopathy is a genetic myocardial disease difficult to diagnose due to the lack of gold standard criteria. Simultan

A Space-Time Transformer for Precipitation Nowcasting

arXiv:2511.11090v3 Announce Type: replace Abstract: Until recently, numerical weather prediction (NWP) models have stood rivalless in operational forecasting despite a few limitations. Namely, physica

Accuracy-Preserving Stability Regularization for Large-Scale Retail Demand Forecasting

arXiv:2607.13331v1 Announce Type: new Abstract: Retail demand forecasts are reused across replenishment, capacity, labor, and transportation planning cycles. Point-error objectives do not constrain ab

AeroMap3D: Anchoring Monocular UAV 6-DoF Localization to Visual-Geometric-Semantic Map Priors

arXiv:2607.14009v1 Announce Type: new Abstract: We present AeroMap3D, a monocular 6-DoF UAV localization system that anchors onboard imagery to visual, geometric, and semantic map priors for GNSS-deni

AffectFlow-DINO: Uncertainty-Aware Multi-Task Affect Estimation via Conditional Rectified Flow

arXiv:2607.13250v1 Announce Type: new Abstract: We present extbf{AffectFlow-DINO}, a multi-task learning system for the 11th ABAW challenge that extends a standard deterministic architecture with a co

AI advice suppresses people's willingness to say 'I don't know', even when the advice is wrong and accuracy is incentivized

arXiv:2607.13562v1 Announce Type: new Abstract: Knowing when to say 'I don't know' is fundamental to human judgment, yet AI assistants offer a fluent answer to almost any question. In five experiments

AI-Augmented Human Resource Management? Insights from German companies

arXiv:2607.13839v1 Announce Type: cross Abstract: This study examines the integration of AI into Human Resource Management in German companies. We ask if and how AI-based technologies are enquote{augm

AI in Cyberpsychology: A systematic literature review of Cybersecurity enhancement by using AI for analyzing psychology of Victims, Attackers, and Defenders

arXiv:2607.13123v1 Announce Type: cross Abstract: Cybersecurity is the practice of protecting systems, networks, and data from digital attacks. Cyberpsychology (CPSY) is defined as the use of psycholo

Algebraic Representability as the Limiting Regime of Grokking: An Exactly Solvable Model with Holomorphic Activations

arXiv:2607.13749v1 Announce Type: new Abstract: Neural networks trained on modular arithmetic exhibit grokking, a delayed transition from memorisation to generalisation known to depend on model capaci

An Efficient Newton Algorithm for Nonnegative Matrix Factorization with the Kullback-Leibler Divergence

arXiv:2607.13919v1 Announce Type: new Abstract: Nonnegative Matrix Factorization (NMF) is a fundamental tool in unsupervised learning, which approximates a nonnegative matrix by the product of two low

Analyzing Curricular Pattern Complexity Using AI to Improve On-Time Graduation Rates

arXiv:2607.13094v1 Announce Type: cross Abstract: The rise of Artificial Intelligence (AI) enables automatic analysis of large amounts of data. Previously time-consuming and labor-intensive tasks can

Attentive multilayer fusion for vision transformers

arXiv:2601.09322v2 Announce Type: replace Abstract: With the rise of large-scale foundation models, efficiently adapting them to downstream tasks remains a central challenge. Linear probing, which fre

Audio-Text Cross-Attention with Psycholinguistic Support Features for Ambivalence/Hesitancy Recognition

arXiv:2607.13345v1 Announce Type: new Abstract: We present an audio-text system for the Ambivalence/Hesitancy Video Recognition Challenge of the 11th ABAW Competition. The method excludes visual frame

Bandit PCA with Minimax Optimal Regret

arXiv:2607.10936v2 Announce Type: replace Abstract: We study the bandit-feedback version of online principal component analysis (Bandit PCA): in each round t = 1,ots,T, the adversary selects a d imes

Beyond Backbone Backpropagation: A Decoupled Strategy for Efficient Transfer Learning

arXiv:2607.13043v1 Announce Type: cross Abstract: Deep learning models achieve state-of-the-art image classification but face deployment challenges due to computational costs and energy demands. We pr

Beyond the d^{2.5}-mixing bound for Dikin walks on polytopes

arXiv:2607.13943v1 Announce Type: cross Abstract: Inspired by interior-point methods (IPM) for structured convex optimization, Kannan and Narayanan introduced the Dikin walk for sampling uniformly fro

Boltzmann MapReduce: A Partition-Function Reduce for Forkable Sandboxes

arXiv:2607.09689v2 Announce Type: replace Abstract: To leading order under local asymptotic normality (LAN), the confidence density a worker emits over a chunk of size n is a Gibbs--Boltzmann measure

Bring Music The Horizon: Music-Driven 360^irc Video Generation

arXiv:2607.13471v1 Announce Type: new Abstract: Music visualization offers a powerful way to enhance listeners' understanding and experience of music by translating auditory signals into visual forms.