Search: “research”

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

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

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

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

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

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

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

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

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

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_balestr). The math is clean, but it is rarely explained from fi

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 if 100 companies get to defend themselves because they got o

Fara1.5-27B is a multimodal computer use agent (CUA) for web browsers, from Microsoft Research AI Frontiers. It observes the browser through screenshots and acts on the user's behalf by emitting struc

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 a session a few weeks back to demo the power of multimodal p

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).

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

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.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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.

arXiv:2607.13796v1 Announce Type: cross Abstract: This paper establishes a direct analogue of the classical Coding Theorem in the setting of symmetry groups. We consider computable bijections on the s

arXiv:2607.13508v1 Announce Type: new Abstract: Quantifying directional influence between node populations is a fundamental problem in graph-based modeling, particularly in spatial biological systems

arXiv:2607.13976v1 Announce Type: new Abstract: Detecting ambivalence and hesitancy (AH) in unconstrained video is challenging because the target signal is inherently ambiguous and expressed through s

arXiv:2607.13216v1 Announce Type: cross Abstract: Humans recognize movements effortlessly, even from noisy and complex visual input. But what information in the stimulus allows humans to rapidly class

arXiv:2607.13437v1 Announce Type: new Abstract: Recent vision models such as CLIP and SAM enable training-free segmentation and semantic encoding for fine-grained classification. A common approach is

arXiv:2512.10948v2 Announce Type: replace Abstract: All-in-One Image Restoration (AiOIR) aims to recover high-quality images from diverse degradations within a unified framework. However, existing met

arXiv:2607.13544v1 Announce Type: new Abstract: During wind farm operation, Supervisory Control and Data Acquisition (SCADA) systems record numerous anomalies, transients, and specific operational mod

arXiv:2510.14317v2 Announce Type: replace-cross Abstract: Column generation and branch-and-price (B&P) are leading mathematical optimization methods for large-scale exact optimization, iterating betwe

arXiv:2607.13188v1 Announce Type: new Abstract: Human cognition does not separate understanding and generation. A teacher at a whiteboard speaks and draws extit{together}, each modality reshapes the o