research

arXiv:2607.03784v1 Announce Type: cross Abstract: While prior studies have successfully compressed vision Transformers (ViTs) through various pruning techniques, most have concentrated on width prunin

arXiv:2607.03148v1 Announce Type: cross Abstract: Activation functions are considered an essential primitive for neural nonlinearity, i.e., they enable neural networks to serve as universal approximat

arXiv:2607.04236v1 Announce Type: cross Abstract: Bayes-assisted conformal prediction combines the strengths of Bayesian modelling with exact, distribution-free frequentist coverage guarantees. Althou

arXiv:2501.05795v4 Announce Type: replace-cross Abstract: In recent years, explainability in machine learning has gained importance. In this context, counterfactual explanation (CE), which is an expla

arXiv:2607.02584v1 Announce Type: new Abstract: In extbf{DiT-based video generation models equipped with 3D Rotary Position Embeddings (3D RoPE)}, the attention mechanism remains a primary computation

arXiv:2607.05281v1 Announce Type: cross Abstract: Present-day quantum computing is cloud-based, where a user submits a circuit to a service provider's proprietary backend hardware. While providers may

arXiv:2602.23820v2 Announce Type: replace Abstract: SAR supports all-day-and-night oceanic observation, yet vessel identification from SAR images is hampered by speckle noise, intricate land-sea backg

arXiv:2607.05035v1 Announce Type: cross Abstract: Few-shot brain tumor segmentation remains challenging due to noisy support masks, inter-patient variations between support and query images, and the l

arXiv:2607.03207v1 Announce Type: new Abstract: Automatic speech recognition (ASR) has advanced remarkably for standard speech, yet speech affected by neurological conditions remains a challenge. We p

arXiv:2601.03024v3 Announce Type: replace Abstract: We propose Self-Augmented Residual 3D Gaussian Splatting (SA-ResGS), a novel framework to stabilize uncertainty quantification and enhancing uncerta

arXiv:2607.03612v1 Announce Type: new Abstract: Feed-forward 3D reconstruction (F3R) transformers have recently achieved remarkable success. However, scaling them to long image sequences remains chall

Sakana AI has launched a translation service that captures the nuanced 'tone and temperature' of Japanese expressions like '恐縮ですが' (apologetic) and 'それな' (casual agreement), going beyond literal trans

Sakana AI will have both researchers and recruiters attending ICML (International Conference on Machine Learning). The company is open to inquiries about their work and opportunities, with interested

Sakana AIが翻訳機能「Sakana Translate」をリリース、日英中の双方向翻訳に対応＆カジュアル・簡潔・大阪弁などに変換可能 https://gigazine.net/news/20260707-sakana-translate/?utm_source=x&utm_medium=sns&utm_campaign=x_post&utm_content=20260707-sakana-

arXiv:2607.04206v1 Announce Type: cross Abstract: Diffusion language models (dLLMs) generate text by iteratively denoising a masked response and can commit multiple output positions per model invocati

arXiv:2607.03761v1 Announce Type: new Abstract: Computed Tomography (CT) is indispensable in clinical diagnostics, yet minimizing radiation dose without compromising image quality remains a critical c

arXiv:2602.04728v3 Announce Type: replace-cross Abstract: We propose a cross-attention Transformer for joint decoding of uplink OFDM signals received by multiple coordinated access points. A shared pe

arXiv:2607.03392v1 Announce Type: cross Abstract: The ever-increasing collection of personal data has created mounting pressure to develop technologies that protect sensitive aspects of individual ide

arXiv:2607.03188v1 Announce Type: cross Abstract: Episode mining aims to extract subsequences of events that possess certain distinctive properties and constitute facts valuable to the user. Maximal f

arXiv:2607.04595v1 Announce Type: new Abstract: Most classification problems assume the classes are roughly separable, so that an individual sample can usually be assigned to one class. Single-cell pe

arXiv:2511.17812v3 Announce Type: replace-cross Abstract: Flow matching models effectively represent complex distributions, yet estimating expectations of functions of their outputs remains challengin

arXiv:2607.02912v1 Announce Type: new Abstract: Despite the high accuracy of EEG-based emotion recognition, existing models remain opaque 'black boxes', lacking semantic grounding between abstract neu

arXiv:2607.04079v1 Announce Type: cross Abstract: Recent Multi-modal Large Language Models (MLLMs) have demonstrated remarkable performance on 2D question answering tasks. However, extending these mod

arXiv:2607.04163v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have achieved remarkable progress in visual understanding tasks such as image captioning and visual question answ

arXiv:2606.12913v2 Announce Type: replace-cross Abstract: The rapid growth of modern training datasets has significantly increased computational cost, motivating dataset pruning~(DP) methods which ret

arXiv:2607.05353v1 Announce Type: cross Abstract: Watermarking methods embed imperceptible and verifiable signals into text generated by large language models (LLMs). Existing approaches include zero-

arXiv:2607.02895v1 Announce Type: cross Abstract: Learning-based approaches for selectivity estimation in databases have gained significant traction in recent years. However, theoretical studies of th

arXiv:2602.02381v2 Announce Type: replace Abstract: Joint-embedding self-supervised learning (SSL), the key paradigm for unsupervised representation learning from visual data, learns from invariances

arXiv:2607.04144v1 Announce Type: new Abstract: Removing unwanted objects from reconstructed 3D scenes is an important task in computer vision, supporting applications in AR/VR, robotics, and digital

arXiv:2607.04832v1 Announce Type: new Abstract: In recent years, studies have revealed a decline in semantic variety across popular music lyrics, particularly in English-language songs on streaming pl

arXiv:2607.03253v1 Announce Type: cross Abstract: As hematoxylin & eosin (H&E) staining constitutes the primary entry point in routine diagnostic workflows, computer-aided diagnosis from whole-slide H

arXiv:2401.10927v3 Announce Type: replace-cross Abstract: In this paper, we consider the problem of partitioning a small data sample of size n drawn from a mixture of 2 sub-gaussian distributions in R

arXiv:2607.04949v1 Announce Type: new Abstract: We study the problem of k-means clustering on large datasets. The state-of-the-art for the problem is given by coresets-based approaches, which build sm

arXiv:2607.04011v1 Announce Type: cross Abstract: While decoders have rapidly scaled, encoders have remained largely unchanged since BERT. We revisit this disparity by frozen backbone evaluation via p

arXiv:2607.03660v1 Announce Type: cross Abstract: Modern sequence models have a striking capacity for in-context learning (ICL); they can perform new tasks based only on examples given in the prompt.

arXiv:2505.16388v2 Announce Type: replace Abstract: The serious games between humans and AI have only just begun. Evolutionary Game Theory (EGT) models the competitive and cooperative strategies of bi

arXiv:2607.04336v1 Announce Type: new Abstract: Modern video games are becoming more complex day by day. Most of these modern games are multiplayer first-person shooter (FPS) games. The rising popular

arXiv:2607.03883v1 Announce Type: new Abstract: The rapid advancement of deepfakes necessitates robust face forgery detection. Although forged faces may lack obvious artifacts, they often contain subt

arXiv:2607.03872v1 Announce Type: new Abstract: Reconstructing high-fidelity 3D building models from UAV imagery is essential for large-scale digital twin development. However, existing 3D Gaussian Sp

arXiv:2607.05260v1 Announce Type: cross Abstract: Conventional modeling approaches for LiDAR-based above-ground biomass (AGB) estimation rely on discrete plot-level inventory aggregates. This methodol

arXiv:2607.03055v1 Announce Type: new Abstract: HiPPO gives recurrent states memory semantics as coefficients of online polynomial projections, but in fixed channel coordinates. Modern selective SSMs,

arXiv:2208.00657v2 Announce Type: cross Abstract: Building detection and change detection using remote sensing images can help urban and rescue planning. Moreover, they can be used for building damage

arXiv:2607.01698v2 Announce Type: replace Abstract: 3D Gaussian Splatting has demonstrated remarkable potential in novel view synthesis. In contrast to small-scale scenes, large-scale scenes inevitabl

arXiv:2607.03999v1 Announce Type: cross Abstract: Estimating heterogeneous treatment effects (CATE) requires simultaneously detecting effect modification and quantifying estimation uncertainty. Existi

arXiv:2607.04851v1 Announce Type: cross Abstract: Generalizing sleep staging models to unseen datasets is challenging, and typical domain generalization (DG) methods often rely on multiple source doma

arXiv:2607.03881v1 Announce Type: cross Abstract: Codon harmonization aims to adapt the coding sequences for heterologous expression while preserving the native-like patterns of frequent and rare codo