Consistent Diffusion Language Models
arXiv:2605.00161v1 Announce Type: new Abstract: Diffusion language models (DLMs) are an attractive alternative to autoregressive models because they promise sublinear-time, parallel generation, yet pr
Knowledge catalogue
arXiv:2605.00161v1 Announce Type: new Abstract: Diffusion language models (DLMs) are an attractive alternative to autoregressive models because they promise sublinear-time, parallel generation, yet pr
arXiv:2601.07326v2 Announce Type: replace-cross Abstract: This paper studies the AdamW-style Shampoo optimizer, an effective implementation of classical Shampoo that notably won the external tuning tr
arXiv:2501.06540v2 Announce Type: replace Abstract: The advancement of AI-assisted myopia screening necessitates the joint diagnosis of both-eye (OU) high myopia (HM) status and the prediction of axia
arXiv:2605.00070v1 Announce Type: new Abstract: We present CRADIPOR, a numerical dispersion prediction tool for automotive crash simulations. Finite Element (FE) crash models are widely used throughou
arXiv:2605.00119v1 Announce Type: new Abstract: There is a significant gap in evaluating cultural reasoning in LLMs using conversational datasets that capture culturally rich and dialectal contexts. M
arXiv:2605.00610v1 Announce Type: new Abstract: SFT and RLVR represent two fundamental yet distinct paradigms for LLM post-training, each excelling in distinct dimensions. SFT expands knowledge breadt
arXiv:2605.00708v1 Announce Type: new Abstract: Effectively stratifying patient risk in chronic diseases like glaucoma is a major clinical challenge. Clinicians need tools to identify patients at high
arXiv:2504.18015v4 Announce Type: replace-cross Abstract: Face recognition poses serious privacy risks due to its reliance on sensitive and immutable biometric data. While modern systems mitigate priv
arXiv:2507.18654v2 Announce Type: replace-cross Abstract: Diffusion models are powerful tools for sampling from high-dimensional distributions by progressively transforming pure noise into structured
arXiv:2605.00776v1 Announce Type: new Abstract: The language in online platforms, influence operations, and political rhetoric frequently directs a mix of pro-social sentiment (e.g., advocacy, helpful
arXiv:2601.01082v5 Announce Type: replace Abstract: Quality diversity (QD) optimization searches for a collection of solutions that optimize an objective while attaining diverse outputs of a user-spec
arXiv:2405.13901v4 Announce Type: replace Abstract: Self-attention is central to the success of Transformer architectures; however, learning the query, key, and value projections from random initializ
arXiv:2501.04757v2 Announce Type: replace-cross Abstract: We develop a new class of distance-aware error bounds that tightly characterize the approximation error of spline neural networks. Our bottom-
arXiv:2605.00490v1 Announce Type: new Abstract: Anomaly detection methods can be very useful in identifying unusual or interesting patterns in data. A recently proposed conditional anomaly detection f
arXiv:2605.00195v1 Announce Type: new Abstract: Supervised Fine-Tuning (SFT) is essential for aligning Large Language Models (LLMs) with user intent, yet it is believed to suppress generative diversit
arXiv:2605.00675v1 Announce Type: new Abstract: Medical imaging datasets are often characterized by extreme class imbalances, where rare pathologies are significantly underrepresented compared to comm
arXiv:2605.00733v1 Announce Type: cross Abstract: Federated Multimodal Learning (FML) trains multimodal models across decentralized clients while keeping their image-text pairs private. However, joint
arXiv:2309.06577v5 Announce Type: replace Abstract: We present two algorithms to initialize layers of tensorized neural networks and general tensor network algorithms using partial computations of the
arXiv:2605.00278v1 Announce Type: cross Abstract: We introduce the package exttt{EliminationTemplates} for the Macaulay2 computer algebra system, which provides tools for constructing automatic solver
arXiv:2605.00321v1 Announce Type: new Abstract: Vision-Language-Action (VLA) policies often fail under distribution shift, suggesting that decisions may depend on spurious visual correlations rather t
arXiv:2605.00503v1 Announce Type: new Abstract: Autoregressive image modeling relies on visual tokenizers to compress images into compact latent representations. We design an end-to-end training pipel
arXiv:2605.00435v1 Announce Type: new Abstract: Mode collapse is a persistent challenge in generative modeling and appears in autoregressive text generation as behaviors ranging from explicit looping
arXiv:2605.00722v1 Announce Type: new Abstract: Single-point supervised infrared small target detection (IRSTD) drastically reduces dense annotation costs. Current state-of-the-art (SOTA) methods achi
arXiv:2605.00458v1 Announce Type: new Abstract: Federated learning using mobile and Internet of Things devices requires not only the ability to handle heterogeneity of clients' data distributions but
arXiv:2605.00322v1 Announce Type: new Abstract: Federated weather modeling on sensor data is a distributed system underpinned by federated learning, enabling multiple sensor data sources, including gr
arXiv:2510.16620v3 Announce Type: replace-cross Abstract: We consider reversely-degraded secure-communication channels, for which the secrecy capacity is zero if there is no channel feedback. Specific
arXiv:2605.00367v1 Announce Type: new Abstract: Developing robust techniques for super-resolution of satellite imagery involves navigating commonly observed trade-offs between spectral fidelity and pe
arXiv:2605.00337v1 Announce Type: new Abstract: Sampling the free energy surface, namely, the distribution of collective variables (CVs), is a crucial problem in statistical physics, as it underpins a
arXiv:2605.00474v1 Announce Type: new Abstract: Modern vision models achieve remarkable accuracy, but explaining where evidence arises, what the model encodes, and how internal computations assemble t
arXiv:2605.00120v1 Announce Type: new Abstract: Online signature verification (OSV) requires distinguishing skilled forgeries from genuine samples under high intra-class variability and with very few
arXiv:2605.00423v1 Announce Type: new Abstract: In wireless communications, recovering the optimal solution to the multiple-input multiple-output (MIMO) detection problem is NP-hard. Obtaining high-qu
arXiv:2605.00800v1 Announce Type: new Abstract: Generating diverse, readable statistical charts from tabular data remains challenging for LLMs, as many failures become apparent after rendering and are
arXiv:2605.00799v1 Announce Type: new Abstract: Gaze estimation methods commonly use facial appearances to predict the direction of a person gaze. However, previous studies show three major challenges
arXiv:2605.00581v1 Announce Type: cross Abstract: Gradient Boosting Decision Trees (GBDTs) dominate tabular machine learning, with modern implementations like XGBoost, LightGBM, and CatBoost being bas
arXiv:2411.17429v2 Announce Type: replace Abstract: Graph Neural Networks are powerful models for learning from graph-structured data, yet their effectiveness is often limited by two critical challeng
arXiv:2605.00631v1 Announce Type: new Abstract: We present H-RAG, our submission to SemEval-2026 Task 8 (MTRAGEval), addressing both Task A (Retrieval) and Task C (Generation with Retrieved Passages).
arXiv:2605.00496v1 Announce Type: new Abstract: Understanding human actions from visual observations is essential for human--robot interaction, particularly when semantic interpretation of unfamiliar
arXiv:2605.00068v1 Announce Type: new Abstract: Inertial Confinement Fusion (ICF) holds transformative promise for sustainable, near-limitless clean energy, yet remains constrained by prohibitively hi
arXiv:2605.00250v1 Announce Type: cross Abstract: Standard diffusion models for graph generation typically rely on uniform time-stepping, an approach that overlooks the non-homogeneous dynamics of dis
arXiv:2605.00064v1 Announce Type: new Abstract: Information-theoretic generalization bounds analyze stochastic optimization by relating expected generalization error to the mutual information between
arXiv:2605.00591v1 Announce Type: new Abstract: Contrastive vision-language models like CLIP exhibit remarkable zero-shot generalization. However, prompt tuning remains highly sensitive to label noise
arXiv:2605.00618v1 Announce Type: new Abstract: We investigate the extent to which cosine similarity between paragraph embeddings is invariant under machine translation, using the Manifesto Corpus of
arXiv:2601.00090v2 Announce Type: replace Abstract: Contemporary text-to-image models exhibit a surprising degree of mode collapse, as can be seen when sampling several images given the same text prom
arXiv:2605.00640v1 Announce Type: new Abstract: Prevailing machine-learned interatomic potential (MLIP) uncertainty-quantification methods rely on ensembles of independently trained backbones. These m
arXiv:2403.02290v2 Announce Type: replace-cross Abstract: The Bellman equation and its continuous form, the Hamilton-Jacobi-Bellman equation, are ubiquitous in reinforcement learning and control theor
arXiv:2511.08156v2 Announce Type: replace Abstract: Land Use and Land Cover (LULC) mapping is a fundamental task in Earth Observation (EO). However, current LULC models are typically developed for a s
arXiv:2605.00777v1 Announce Type: cross Abstract: A speaker encoder used in multilingual voice cloning should treat the same speaker identically regardless of which script the audio was uttered in. Of
arXiv:2510.22819v2 Announce Type: replace Abstract: The convergence analysis of online learning algorithms is central to machine learning theory, where the last-iterate convergence is particularly imp
arXiv:2605.00644v1 Announce Type: new Abstract: Energy-based models (EBMs) are a flexible class of deep generative models and are well-suited to capture complex dependencies in multimodal data. Howeve
arXiv:2605.00809v1 Announce Type: new Abstract: In this paper, we present extbf{Gen}erative extbf{L}anguage-extbf{I}mage extbf{P}re-training (GenLIP), a minimalist generative pretraining framework for
arXiv:2605.00480v1 Announce Type: new Abstract: Active learning aims to reduce annotation cost by selectively querying informative samples for supervision under a limited labeling budget. In this work
arXiv:2509.24496v3 Announce Type: replace Abstract: The explosive growth of large language models (LLMs) has created a vast but opaque landscape: millions of models exist, yet their evolutionary relat
arXiv:2605.00253v1 Announce Type: new Abstract: Mamba's recurrent state h_t is, by construction, a compressed summary of every token seen so far. This raises a tempting hypothesis: if we extract token
arXiv:2605.00342v1 Announce Type: new Abstract: Tree-based speculative decoding accelerates autoregressive generation by verifying multiple draft candidates in parallel, but this advantage weakens for
arXiv:2605.00201v1 Announce Type: cross Abstract: The standard oracle model for matroid algorithms assumes that each independence query can be answered in constant time, regardless of the size of the
arXiv:2501.14660v2 Announce Type: replace-cross Abstract: In this work, we study the asymptotic behavior of Mixture of Experts (MoE) trained via gradient flow on supervised learning problems. Our main
arXiv:2605.00431v1 Announce Type: cross Abstract: Although recent video-to-audio (V2A) models excelled at synthesizing semantically plausible sounds from visual inputs, they do not explicitly model ro
arXiv:2605.00764v1 Announce Type: new Abstract: Urban perception describes how people subjectively evaluate urban environments, shaping how cities are experienced and understood. Existing computationa
arXiv:2605.00473v1 Announce Type: new Abstract: Multi-task learning (MTL) has emerged as a pivotal paradigm in machine learning by leveraging shared structures across multiple related tasks. Despite i
arXiv:2512.16762v3 Announce Type: replace Abstract: Generative Pre-trained Transformer (GPT) architectures are the most popular design for language modeling. Energy-based modeling is a different parad