45 articles mentioning Ising-Calibration-1-35B-A3B
arXiv:2603.10093v2 Announce Type: replace-cross Abstract: Recent 3D molecular generation methods primarily use asynchronous auto-regressive or synchronous diffusion models. While auto-regressive models build molecules sequentially, they're limited by a short horizon and a discrepancy between trainin
arXiv:2604.12799v2 Announce Type: replace-cross Abstract: The rise of automated bidding strategies in online advertising presents new challenges in designing and analyzing efficient auction mechanisms. In this paper, we focus on proportional mechanisms within the context of auto-bidding and study th
arXiv:2604.22446v1 Announce Type: new Abstract: Individual agent capabilities have advanced rapidly through modular skills and tool integrations, yet multi-agent systems remain constrained by fixed team structures, tightly coupled coordination logic, and session-bound learning. We argue that this re
arXiv:2604.19791v2 Announce Type: replace Abstract: Attitude change - the process by which individuals revise their evaluative stances - has been explained by a set of influential but competing verbal theories. These accounts often function as mechanism sketches: rich in conceptual detail, yet lacki
arXiv:2604.20313v1 Announce Type: new Abstract: This technical note provides a first-order formalisation of the logit shift and fact-margin change induced by Low-Rank Adaptation (LoRA). Using a first-order Fr\'echet approximation around the base model trajectory, we show that the multi-layer LoRA ef
arXiv:2604.20041v1 Announce Type: cross Abstract: Normalizing Flows (NFs) are a classical family of likelihood-based methods that have received revived attention. Recent efforts such as TARFlow have shown that NFs are capable of achieving promising performance on image modeling tasks, making them vi
arXiv:2604.18839v1 Announce Type: cross Abstract: Looped transformers scale computational depth without increasing parameter count by repeatedly applying a shared transformer block and can be used for iterative refinement, where each loop rewrites a full fixed-size prediction in parallel. On difficu
ChatGPT Images 2.0, the newest image-generation model from OpenAI, shows just how much AI capabilities have evolved over the last few years.
arXiv:2604.17388v1 Announce Type: new Abstract: We introduce JuRe (Just Repair), a minimal denoising network for time series anomaly detection that exposes a central finding: architectural complexity is unnecessary when the training objective correctly implements the manifold-projection principle. J
arXiv:2603.26771v2 Announce Type: replace Abstract: Masked diffusion language models (MDLMs) generate text by iteratively unmasking tokens from a fully masked sequence. Their standard confidence-based unmasking strategy systematically defers high-entropy logical connective tokens, degrading reasonin
arXiv:2604.16258v1 Announce Type: new Abstract: Competency Questions (CQs) are a cornerstone of requirement elicitation in ontology engineering. CQs represent requirements as a set of natural language questions that an ontology should satisfy; they are traditionally modelled by ontology engineers to
arXiv:2604.15459v1 Announce Type: cross Abstract: Medical image denoising (MID) lacks absolutely clean images for supervision, leading to a noisy reference problem that fundamentally limits denoising performance. Existing simulated-supervised discriminative learning (SimSDL) and simulated-supervised
arXiv:2604.16821v1 Announce Type: new Abstract: Reach and Frequency (R&F) contract advertising is an important form of widely used brand advertising. Unlike performance advertising, R&F contracts emphasize controllable delivery of UV and PV under given targeting, scheduling, and frequency control co
arXiv:2604.16966v1 Announce Type: cross Abstract: The evolution from static ranking models to Agentic Recommender Systems (Agentic RecSys) empowers AI agents to maintain long-term user profiles and autonomously plan service tasks. While this paradigm shift enhances personalization, it introduces a v
arXiv:2604.15783v1 Announce Type: new Abstract: Urban bike-sharing systems require strategic station expansion to meet growing demand. Traditional allocation approaches rely on explicit demand modelling that may not capture the urban characteristics distinguishing successful stations. This study add
arXiv:2604.14379v1 Announce Type: new Abstract: Reinforcement learning (RL) has emerged as a powerful tool for aligning diffusion models with human preferences, typically by optimizing a single reward function under a KL regularization constraint. In practice, however, human preferences are inherent
arXiv:2604.14324v1 Announce Type: new Abstract: Large language models (LLMs) often exhibit hallucinations due to their inability to accurately perceive their own knowledge boundaries. Existing abstention fine-tuning methods typically partition datasets directly based on response accuracy, causing mo
arXiv:2604.13316v1 Announce Type: cross Abstract: Neural operators have emerged as fast surrogate models for physics simulations, yet they remain acutely vulnerable to adversarial perturbations, a critical liability for safety-critical digital twin deployments. We present a synergistic defense that
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. Recently, inspired by classical diffusion frameworks, the quantum denoising diffusion probabilistic model (
arXiv:2604.12208v1 Announce Type: cross Abstract: Global navigation information and local scene understanding are two crucial components of autonomous driving systems. However, our experimental results indicate that many end-to-end autonomous driving systems tend to over-rely on local scene understa
arXiv:2604.12459v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in politically sensitive environments, where memorisation of personal data or confidential content raises regulatory concerns under frameworks such as the GDPR and its Right to be Forgotten. Transl
arXiv:2510.01544v2 Announce Type: replace Abstract: Diffusion-based large language models offer a non-autoregressive alternative for text generation, but enabling them to perform complex reasoning remains challenging. Reinforcement learning has recently emerged as an effective post-training strategy
arXiv:2604.08557v2 Announce Type: replace-cross Abstract: Safety alignment in diffusion language models (dLLMs) relies on a single load-bearing assumption: that committed tokens are permanent. We show that violating this assumption, by re-masking committed refusal tokens and injecting a short affirm
arXiv:2604.02340v2 Announce Type: replace-cross Abstract: Recent advances in masked diffusion language models (MDLMs) narrow the quality gap to autoregressive LMs, but their sampling remains expensive because generation requires many full-sequence denoising passes with a large Transformer and, unlik
arXiv:2604.10054v1 Announce Type: new Abstract: This study addresses a key limitation in deep learning Automatic Modulation Classification (AMC) models, which perform well at high signal-to-noise ratios (SNRs) but degrade under noisy conditions due to conventional feature extraction suppressing both
arXiv:2602.03402v3 Announce Type: replace Abstract: Vision language models (VLMs) extend the reasoning capabilities of large language models (LLMs) to cross-modal settings, yet remain highly vulnerable to multimodal jailbreak attacks. Existing defenses predominantly rely on safety fine-tuning or agg
arXiv:2510.00491v3 Announce Type: replace-cross Abstract: Learning diverse manipulation skills for real-world robots is severely bottlenecked by the reliance on costly and hard-to-scale teleoperated demonstrations. While human videos offer a scalable alternative, effectively transferring manipulatio
arXiv:2604.09041v1 Announce Type: cross Abstract: AI-based weather forecasting now rivals traditional physics-based ensembles, but state-of-the-art (SOTA) models rely on specialized architectures and massive computational budgets, creating a high barrier to entry. We demonstrate that such complexity
arXiv:2604.08639v1 Announce Type: cross Abstract: Uncertainty quantification (UQ) is essential for deploying deep learning models in safety critical applications, yet no consensus exists on which UQ method performs best across different data modalities and distribution shifts. This paper presents a
arXiv:2604.07885v1 Announce Type: new Abstract: This work explores the connection between (non-)literalness and plausibility at the example of subject-verb-object events in English. We design a systematic setup of plausible and implausible event triples in combination with abstract and concrete cons
arXiv:2604.07236v2 Announce Type: replace-cross Abstract: Recent LLM-based agents often place world modeling, planning, and reflection inside a single language model loop. This can produce capable behavior, but it makes a basic scientific question difficult to answer: which part of the agent's compe
arXiv:2506.01062v4 Announce Type: replace Abstract: We introduce SealQA, a new challenge benchmark for evaluating SEarch-Augmented Language models on fact-seeking questions where web search yields conflicting, noisy, or unhelpful results. SealQA comes in three flavors: (1) Seal-0 (main) and (2) Seal
arXiv:2604.06198v1 Announce Type: cross Abstract: The rapid rise of generative artificial intelligence (AI) is driving unprecedented growth in global computational demand, placing increasing pressure on electricity systems. This study introduces an AI-energy coupling framework that combines large la
arXiv:2604.07409v1 Announce Type: new Abstract: Layout plays a crucial role in graphic design and poster generation. Recently, the application of deep learning models for layout generation has gained significant attention. This paper focuses on using a GAN-based model conditioned on images to genera
arXiv:2604.06263v1 Announce Type: cross Abstract: Generative advertising in large language model (LLM) responses requires optimizing sponsorship configurations under two strict constraints: the strategic behavior of advertisers and the high cost of stochastic generations. To address this, we propose
arXiv:2503.08028v3 Announce Type: replace-cross Abstract: Denoising diffusions sample from a probability distribution $\mu$ in $\mathbb{R}^d$ by constructing a stochastic process $({\hat{\boldsymbol x}}_t:t\ge 0)$ in $\mathbb{R}^d$ such that ${\hat{\boldsymbol x}}_0$ is easy to sample, but the distr
arXiv:2511.04570v2 Announce Type: replace-cross Abstract: The "Thinking with Text" and "Thinking with Images" paradigms significantly improve the reasoning abilities of large language models (LLMs) and Vision-Language Models (VLMs). However, these paradigms have inherent limitations. (1) Images capt
arXiv:2604.05110v1 Announce Type: cross Abstract: Breast cancer screening relies heavily on mammography, where the craniocaudal (CC) and mediolateral oblique (MLO) views provide complementary information for diagnosis. However, many datasets lack complete paired views, limiting the development of al
arXiv:2604.05257v1 Announce Type: cross Abstract: Diffusion models are increasingly being utilised to create synthetic tabular and time series data for privacy-preserving augmentation. Tabular Denoising Diffusion Probabilistic Models (TabDDPM) generate high-quality synthetic data from heterogeneous
arXiv:2407.14565v2 Announce Type: replace-cross Abstract: App markets have evolved into highly competitive and dynamic environments for developers. While the traditional app life cycle involves incremental updates for feature enhancements and issue resolution, some apps deviate from this norm by und
arXiv:2604.04321v1 Announce Type: cross Abstract: The neural Willmore flow of a closed oriented $2$-surface in $\mathbb{R}^3$ is introduced as a natural evolution process to minimise the Willmore energy, which is the squared $L^2$-norm of mean curvature. Neural architectures are used to model maps f
arXiv:2604.04802v1 Announce Type: cross Abstract: We study compressed sensing when the sampling vectors are chosen from the rows of a unitary matrix. In the literature, these sampling vectors are typically chosen randomly; the use of randomness has enabled major empirical and theoretical advances in
arXiv:2602.16813v2 Announce Type: replace-cross Abstract: Language models based on discrete diffusion have attracted widespread interest for their potential to provide faster generation than autoregressive models. Despite their promise, these models typically produce samples whose quality sharply de
arXiv:2504.01938v2 Announce Type: replace Abstract: Probabilistic generative models based on measure transport, such as diffusion and flow-based models, are often formulated in the language of Markovian stochastic dynamics, where the choice of the underlying process impacts both algorithmic design c
You may be familiar with Gemini as the thing that's in every Google service you use - whether you want it or not. While it's been a constant, sometimes unwelcome presence in Gmail for at least the past year, it's a relatively new addition to Maps. And you know what? It's kind of great. To […]