Knowledge catalogue
arXiv:2604.13307v1 Announce Type: new Abstract: An unsupervised framework for hyperspectral image (HSI) clustering is proposed that incorporates masked deep representation learning with diffusion-base
arXiv:2604.13589v1 Announce Type: new Abstract: We present Dehaze-then-Splat, a two-stage pipeline for multi-view smoke removal and novel view synthesis developed for Track~2 of the NTIRE 2026 3D Rest
arXiv:2511.13417v2 Announce Type: replace Abstract: Accurate delineation of agricultural field boundaries from satellite imagery is essential for land management and crop monitoring, yet existing meth
arXiv:2512.17326v2 Announce Type: replace Abstract: Vision-language models (VLMs) have the potential to become co-pilots for pathologists. However, most VLMs either focus on small regions of interest
arXiv:2604.13131v1 Announce Type: cross Abstract: Satellite sea surface temperature (SST) products underpin global coral bleaching monitoring, yet they measure only the ocean skin. Corals inhabit dept
arXiv:2604.13761v1 Announce Type: new Abstract: Sparse mixture-of-experts (MoE) layers have been shown to substantially increase model capacity without a proportional increase in computational cost an
arXiv:2604.13088v1 Announce Type: new Abstract: In sparse termination rewards, intra-group comparisons have become the dominant paradigm for fine-tuning reasoning models via reinforcement learning. Ho
Destroying a library brings the dark ages. Destroying the @InternetArchive's @WayBackMachine would be the equivalent of the burning of the Library of Alexandria - one of the worst losses of knowledge
arXiv:2604.13841v1 Announce Type: new Abstract: Text-conditioned image editing has greatly benefitted from the advancements in Image Diffusion Models. However, extending these techniques to facial vid
arXiv:2604.13366v1 Announce Type: new Abstract: Accurate modeling of robot dynamics is essential for model-based control, yet remains challenging under distributional shifts and real-time constraints.
arXiv:2604.13509v1 Announce Type: new Abstract: Recent advances in video generation models has significantly accelerated video generation and related downstream tasks. Among these, video stylization h
arXiv:2604.13230v1 Announce Type: new Abstract: Exploratory Landscape Analysis (ELA) provides numerical features for characterizing black-box optimization problems. In high-dimensional settings, howev
arXiv:2604.14129v1 Announce Type: new Abstract: While Audio-Visual Language Models (AVLMs) have achieved remarkable progress over recent years, their reliability is bottlenecked by cross-modal halluci
arXiv:2604.13797v1 Announce Type: new Abstract: Few-shot Font Generation aims to generate stylistically consistent glyphs from a few reference glyphs. However, capturing complex font styles from a few
arXiv:2604.13278v1 Announce Type: new Abstract: Aerial object detection in UAV imagery presents unique challenges due to the high prevalence of tiny objects, adverse environmental conditions, and stri
arXiv:2604.14030v1 Announce Type: new Abstract: Product bundling boosts e-commerce revenue by recommending complementary item combinations. However, existing methods face two critical challenges: (1)
arXiv:2604.13371v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly described as possessing strong reasoning capabilities, supported by high performance on mathematical, logi
arXiv:2604.13286v1 Announce Type: new Abstract: Despite the widespread multilingual deployment of large language models, post-training pipelines remain predominantly English-centric, contributing to p
arXiv:2604.13508v1 Announce Type: new Abstract: Sparse Upcycling provides an efficient way to initialize a Mixture-of-Experts (MoE) model from pretrained dense weights instead of training from scratch
arXiv:2604.13426v1 Announce Type: new Abstract: Existing Vision Mamba-based RGB-Event(RGBE) tracking methods suffer from using static state transition matrices, which fail to adapt to variations in ev
arXiv:2604.13050v1 Announce Type: cross Abstract: Urban areas are intricate systems shaped by socioeconomic, environmental, and infrastructural factors, with land use patterns serving as aspects of ur
arXiv:2604.13453v1 Announce Type: new Abstract: Traffic forecasting requires modeling complex temporal dynamics and long-range spatial dependencies over large sensor networks. Existing methods typical
arXiv:2604.13540v1 Announce Type: new Abstract: Unified Multimodal Models (UMMs) aim to integrate visual understanding and generation within a single structure. However, these models exhibit a notable
arXiv:2604.13460v1 Announce Type: new Abstract: A central challenge in continual learning is forgetting, the loss of performance on previously learned tasks induced by sequential adaptation to new one
arXiv:2604.13667v1 Announce Type: new Abstract: DNA-based storage has emerged as a promising approach to the global data crisis, offering molecular-scale density and millennial-scale stability at low
arXiv:2604.13398v1 Announce Type: new Abstract: While Aspect-based Sentiment Analysis (ABSA) systems have achieved high accuracy in identifying sentiment polarities, they often operate as 'black boxes
arXiv:2604.13793v1 Announce Type: new Abstract: Exo-to-Ego video generation aims to synthesize a first-person video from a synchronized third-person view and corresponding camera poses. While paired s
arXiv:2507.13942v2 Announce Type: replace Abstract: Forecasting future events is a fundamental capability for general-purpose systems that plan or act across different levels of abstraction. Yet, eval
arXiv:2506.23640v2 Announce Type: replace-cross Abstract: Recently, researchers have explored ML-based Traffic Engineering (TE), leveraging neural networks to solve TE problems traditionally addressed
arXiv:2604.14141v1 Announce Type: new Abstract: Streaming 3D reconstruction aims to recover 3D information, such as camera poses and point clouds, from a video stream, which necessitates geometric acc
arXiv:2510.02213v2 Announce Type: replace Abstract: Density map estimation enables accurate object counting in heavily occluded, and densely packed scenes where detection-based counting fails. In mult
arXiv:2604.13870v1 Announce Type: cross Abstract: We consider the well-studied setting of minimizing a convex Lipschitz function using either gradient descent (GD) or its stochastic variant (SGD), and
arXiv:2604.13722v1 Announce Type: new Abstract: We address the challenge of synthetic-to-real transfer in forestry perception where real data have only coarse Tree labels while synthetic data provide
arXiv:2604.13127v1 Announce Type: new Abstract: The need to selectively and efficiently erase learned information from deep neural networks is becoming increasingly important for privacy, regulatory c
arXiv:2604.13947v1 Announce Type: new Abstract: We present lightweight and efficient architectures to detect weather conditions from RGB images, predicting the weather type (sunny, rain, snow, fog) an
arXiv:2604.05808v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents have demonstrated strong capabilities in complex interactive decision-making tasks. However, existing LLM ag
arXiv:2604.13981v1 Announce Type: new Abstract: Interpretability is essential for deploying object detection systems in critical applications, especially under low-quality imaging conditions that degr
arXiv:2604.13977v1 Announce Type: new Abstract: Synthetic data is a standard component in training large language models, yet systematic comparisons across design dimensions, including rephrasing stra
arXiv:2604.13627v1 Announce Type: cross Abstract: Supervised fine-tuning (SFT) is a common first stage of LLM post-training, teaching the model to follow instructions and shaping its behavior as a hel
arXiv:2604.13179v1 Announce Type: cross Abstract: This paper presents HUANet, a constrained deep neural network architecture that unrolls the iterations of the Alternating Direction Method of Multipli
arXiv:2509.25549v2 Announce Type: replace Abstract: Choroidal nevi are common benign pigmented lesions in the eye, with a small risk of transforming into melanoma. Early detection is critical to impro
I defended my thesis today! Sincere thanks to my advisors @sainingxie @ylecun and committee members: @mengyer @YiMaTweets @LukeZettlemoyer @liuzhuang1234. I could not have wished for a better PhD life
arXiv:2604.13218v1 Announce Type: cross Abstract: Causal representation learning (CRL) aims to identify the underlying latent variables from high-dimensional observations, even when variables are depe
arXiv:2604.13268v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have demonstrated strong cross-modal reasoning capabilities, yet their potential for vision-only tasks remain
Last week, news outlets reported that Microsoft was pausing carbon removal purchases. It was something of a bombshell. The thing is, Microsoft is the carbon removal market. The company has single-hand
JD Vance is lecturing the Pope on Catholicism and Pierre Poilievre is lecturing Mark Carney on economics and RFK Jr is lecturing scientists about vaccines and Donald Trump is lecturing the world on ta
arXiv:2603.12021v2 Announce Type: replace Abstract: Label projection is an effective technique for cross-lingual transfer, extending span-annotated datasets from a high-resource language to low-resour
arXiv:2512.17654v3 Announce Type: replace Abstract: We present three variants of a lightweight, fully connected artificial neural network, suited for interactive estimation of three-dimensional, spati
arXiv:2604.13546v1 Announce Type: new Abstract: Conventional neural networks strictly separate learning and inference because if parameters are updated during inference, outputs become unstable and ev
arXiv:2601.17740v2 Announce Type: replace Abstract: Sewing patterns define the structural foundation of garments and are essential for applications such as fashion design, fabrication, and physical si
arXiv:2604.13520v1 Announce Type: new Abstract: Metal-organic frameworks (MOFs) are highly promising for carbon capture, yet navigating their vast design space remains challenging. Recent deep generat
arXiv:2604.13386v1 Announce Type: new Abstract: Linear probes can detect when language models produce outputs they 'know' are wrong, a capability relevant to both deception and reward hacking. However
MAGA has a Europe problem. Not the real Europe. The one they invented. The one with sharia courts and no-go zones and zero tech companies and miserable citizens begging for permission to cross the str
The AI boom has hit across industries, and public sector organizations are facing pressure to accelerate adoption. At the same time, government institutions face distinct constraints around security,
arXiv:2604.13414v1 Announce Type: new Abstract: Majority-vote ensembles achieve variance reduction by averaging over diverse, approximately independent base learners. When training data exhibits Marko
arXiv:2512.06695v2 Announce Type: replace Abstract: Quantum generative models exploit quantum superposition and entanglement to enhance learning efficiency for both classical and quantum data. Recentl
This paper was accepted at the Workshop on Navigating and Addressing Data Problems for Foundation Models (NADPFM) at ICLR 2026. Principled domain reweighting can substantially improve sample efficienc
arXiv:2506.09207v4 Announce Type: replace Abstract: Accurately solving partial differential equations (PDEs) is essential across many scientific disciplines. However, high-fidelity solvers can be comp
arXiv:2510.05786v3 Announce Type: replace-cross Abstract: Mobius inversion and Shapley values are two mathematical tools for characterizing and decomposing higher-order structure in complex systems. T
arXiv:2604.14108v1 Announce Type: new Abstract: Recent work suggests that (stochastic) gradient descent self-organizes near an instability boundary, shaping both optimization and the solutions found.