research

arXiv:2605.29592v1 Announce Type: new Abstract: Class-Incremental Learning (CIL) with pre-trained models (PTMs) aims to sequentially adapt PTMs to new categories without forgetting old knowledge. Buil

arXiv:2605.29657v1 Announce Type: cross Abstract: Vision-language models (VLMs) rely on long visual token sequences for visual understanding, making the prefill stage expensive in both computation and

arXiv:2605.30168v1 Announce Type: new Abstract: Change detection (CD) in remote sensing is vital for applications such as urban monitoring and disaster assessment, yet traditional methods struggle wit

arXiv:2602.12304v4 Announce Type: replace-cross Abstract: Existing mainstream video customization methods focus on generating identity-consistent videos based on given reference images and textual pro

arXiv:2605.29496v1 Announce Type: new Abstract: Post-training has greatly improved reasoning in frontier vision-language models, yet its gains for perception remain comparatively limited, creating a b

arXiv:2605.30324v1 Announce Type: cross Abstract: We study language generation in the limit under bounded memory. In this task, a learner observes examples from an unknown target language one at a tim

arXiv:2605.29387v1 Announce Type: cross Abstract: The scaling exponent alpha in neural scaling laws L(N) propto N^{-alpha} is commonly treated as a fixed constant set by architecture and data. We pres

arXiv:2605.29429v1 Announce Type: new Abstract: Cell instance segmentation models trained on cell-specific datasets suffer severe performance drops on out-of-distribution cell types, while interactive

arXiv:2605.29834v1 Announce Type: new Abstract: Data stream processing has become a landmark in modern machine learning applications, with concept drifts and novel class appearances posing the primary

arXiv:2605.29556v1 Announce Type: new Abstract: Building mathematical optimization models is critical in operations research (OR), while it requires substantial human expertise. Recent advancements ha

arXiv:2605.29148v1 Announce Type: new Abstract: We study stochastic decision-theoretic online learning with full information and event-level pure differential privacy. A COLT open problem of Hu and Me

arXiv:2605.28952v1 Announce Type: cross Abstract: E-values have attracted considerable interest in recent years as flexible tools for enabling anytime-valid and adaptive data analysis. Hypothesis test

arXiv:2602.03582v3 Announce Type: replace Abstract: Aerodynamic inverse design can improve vehicle and aircraft efficiency, but practical design rarely seeks performance alone: vehicle refinement must

arXiv:2605.29417v1 Announce Type: new Abstract: This study addresses the partial-to-complete geometry reconstruction of deformable objects (DOs) from point-cloud observations toward precise DO manipul

arXiv:2503.00779v2 Announce Type: replace Abstract: Training general-purpose robots requires learning from large and diverse data sources. Current approaches rely heavily on teleoperated demonstration

arXiv:2605.30123v1 Announce Type: cross Abstract: Homomorphic encryption (HE) enables privacy-preserving aggregation in federated learning (FL) by allowing the server to operate on encrypted data with

arXiv:2601.21725v2 Announce Type: replace Abstract: Pretraining language models directly on web-scale corpora is the de facto paradigm. We study an alternative where the model is initially exposed to

arXiv:2605.30054v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to generate software artifacts across many software engineering (SE) tasks, yet ensuring the semant

arXiv:2510.04758v2 Announce Type: replace Abstract: In this work, we establish the sufficient conditions under which nonlinear Canonical Correlation Analysis (CCA) recovers ground-truth latent factors

arXiv:2601.22347v2 Announce Type: replace-cross Abstract: Recent post-training quantization (PTQ) methods have adopted block rotations to diffuse outliers prior to rounding. While this reduces the ove

arXiv:2602.06791v2 Announce Type: replace Abstract: Being probabilistic models, during inference large language models (LLMs) display rare events: behaviour that is far from typical but highly signifi

arXiv:2602.02909v2 Announce Type: replace Abstract: Inference-time scaling via chain-of-thought (CoT) reasoning is a major driver of state-of-the-art LLM performance, but it comes with substantial lat

arXiv:2605.29911v1 Announce Type: cross Abstract: We propose a machine learning approach for image regression from sparse experimental measurements. We show the application of the proposed method on f

arXiv:2605.30244v1 Announce Type: cross Abstract: While Reinforcement Learning with Verifiable Rewards (RLVR) is effective for deterministically checkable tasks, many vision-language tasks are partial

arXiv:2603.07916v2 Announce Type: replace Abstract: In recent advances, to enable a fully data-driven learning paradigm on relational databases (RDB), relational deep learning (RDL) is proposed to str

arXiv:2605.29687v1 Announce Type: new Abstract: Large Language Models (LLMs) excel at understanding natural language but struggle with optimisation tasks involving multiple constraints and user-define

arXiv:2605.30315v1 Announce Type: new Abstract: Across two public LLM leaderboards, many displayed pairwise rankings do not meet a conventional paired-test resolution target under the actual paired ev

arXiv:2605.29335v1 Announce Type: cross Abstract: Frechet Inception Distance (FID) is widely used to evaluate image generators, yet lower FID does not always correspond to better sample quality. We sh

arXiv:2605.29319v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) achieve strong performance on table reasoning tasks but incur substantial inference cost due to long reasoning traces. Ste

arXiv:2605.30059v1 Announce Type: new Abstract: We connect stochastic resetting from non-equilibrium statistical physics with ridge regularization in statistical learning. For linear gradient flow, re

arXiv:2601.18728v2 Announce Type: replace Abstract: Modern generative modeling methods have demonstrated strong performance in learning complex data distributions from clean samples. In many scientifi

arXiv:2605.29263v1 Announce Type: new Abstract: Low-channel wearable electroencephalography (EEG) is attractive for long-term monitoring, but four frontal electrodes provide only a sparse and spatiall

arXiv:2605.29761v1 Announce Type: new Abstract: Compositional implicit surface representations model scenes as collections of objects, each encoded by a Signed Distance Field (SDF). A fundamental limi

arXiv:2509.21707v3 Announce Type: replace-cross Abstract: Semi-supervised learning (SSL) arises in practice when labeled data are scarce or expensive to obtain, while large quantities of unlabeled dat

Sakana AIは、一般社団法人DEEP DIVEとAIを活用した情報分析に関するパートナーシップを締結しました。 https://sakana.ai/deep-dive-partnership/ ■専門家の知見・オープンデータ × 独自AI技術 ■人手では難しかった規模・速度・解像度での分析を実現 当社が注力する「防衛・インテリジェンス」領域への社会実装を 本格化し、我が国の安全保障環境の発展

arXiv:2605.29219v1 Announce Type: new Abstract: Interaction between humanoids involves bidirectional and nonverbal reactivity, coordination and synchrony. Toward socially aware robots and interactive

arXiv:2602.13600v2 Announce Type: replace Abstract: A line of recent training-free methods for mitigating hallucinations in large vision-language models (LVLMs) operates by amplifying attention to vis

arXiv:2603.23853v3 Announce Type: replace Abstract: Combining multiple Vision-Language Models (VLMs) can enhance multimodal reasoning and robustness, but aggregating heterogeneous models' outputs ampl

arXiv:2605.29543v1 Announce Type: cross Abstract: Pilot readback of Air Traffic Control (ATC) voice instructions is a primary safeguard against miscommunication in air transportation. However, readbac

arXiv:2602.05786v2 Announce Type: replace Abstract: Tree-boosting is a widely used machine learning technique for tabular data. However, its out-of-sample accuracy is critically dependent on multiple

arXiv:2605.30290v1 Announce Type: cross Abstract: Self-improvement at scale has been a longstanding goal for reasoning models, and there are two natural places to do it: at test time, through verifica

arXiv:2603.17945v2 Announce Type: replace Abstract: In multilingual pretraining, the test loss of a pretrained model is heavily influenced by the proportion of each language in the pretraining data, n

arXiv:2507.23270v2 Announce Type: replace Abstract: Reconfigurable multi-robot cells offer a promising approach to meet fluctuating assembly demands. However, the recurrent planning of their configura

arXiv:2605.29547v1 Announce Type: cross Abstract: Deep learning optimization relies heavily on the assumption of smooth loss landscapes, a condition systematically violated by modern architectures due

arXiv:2510.15340v2 Announce Type: replace-cross Abstract: State preparation is a cornerstone of quantum technologies, underpinning applications in computation, communication, and sensing. Its importan

arXiv:2605.29188v1 Announce Type: new Abstract: Dictionary methods, topic models, and embedding-similarity scorers are widely used in CSS and management research to measure constructs such as 'entrepr