Search: “research”

arXiv:2503.17897v2 Announce Type: replace-cross Abstract: We present a real-time global illumination approach along with a pipeline for dynamic 3D Gaussian models and meshes. Building on a formulated

arXiv:2604.26903v1 Announce Type: cross Abstract: This paper provides a concise yet comprehensive review of recent advancements in millimeter-wave (mm-wave) oscillators below 100 GHz and sub-terahertz

arXiv:2604.26242v1 Announce Type: cross Abstract: Digital biomarkers for depression have largely relied on static acoustic descriptors, pooled summary statistics, or conventional machine learning repr

arXiv:2507.21420v3 Announce Type: replace-cross Abstract: The computational cost of training multimodal large language models (MLLMs) grows rapidly with the number of processed tokens. Existing effici

arXiv:2604.26031v1 Announce Type: new Abstract: This report summarizes the objectives, datasets, and top-performing methodologies of the 2026 Pixel-level Video Understanding in the Wild (PVUW) Challen

arXiv:2604.26851v1 Announce Type: cross Abstract: When generative AI (genAI) systems are used in high-stakes decision-making, its recommended role is to aid, rather than replace, human decision-making

arXiv:2604.25975v1 Announce Type: cross Abstract: Key-value (KV) caching is essential for large language model inference, yet its memory overhead poses a critical bottleneck for long-context generatio

arXiv:2603.10225v3 Announce Type: replace-cross Abstract: Cross-entropy loss has long been the standard choice for training deep neural networks, yet it suffers from interpretability limitations, unbo

arXiv:2604.00809v2 Announce Type: replace Abstract: Building on existing approaches, we revisit Human-in-the-Loop Object Retrieval, a task that consists of iteratively retrieving images containing obj

arXiv:2508.12672v4 Announce Type: replace-cross Abstract: Federated Learning (FL) enables collaborative model training across multiple clients without sharing private data. We consider FL scenarios wh

arXiv:2604.26506v1 Announce Type: new Abstract: As Large Language Models (LLMs) are increasingly integrated into academic peer review, their vulnerability to adversarial prompts -- adversarial instruc

Sakana AIは、SMBCグループと共同で「提案書自動生成アプリケーション」を開発。三井住友銀行にて実務への適用を開始します。 https://sakana.ai/smbc-proposal-ai/ 複数の「AIエージェント」が自律的に連携し、情報収集から仮説構築、提案構成までを支援。日本を支える基幹産業のDXを、独自の技術で強力に 後押しします。 2025年のパートナーシップ締結以来、検討を

arXiv:2604.26116v1 Announce Type: new Abstract: Federated learning is a machine learning paradigm in which multiple devices collaboratively train a model under the supervision of a central server whil

arXiv:2604.26368v1 Announce Type: new Abstract: In several applications it is desired to have 3D models not only from the outdoor spaces but also from inside the building. In the context of First Resp

arXiv:2502.14912v2 Announce Type: replace Abstract: We present a framework for generating universal semantic embeddings of chemical elements to advance materials inference and discovery. This framewor

arXiv:2604.26262v1 Announce Type: new Abstract: Modern scene reconstruction methods, such as 3D Gaussian Splatting, enable photo-realistic novel view synthesis at real-time speeds. However, their adop

arXiv:2604.26818v1 Announce Type: new Abstract: This paper proposes a novel algorithm for semisupervised learning. This algorithm learns graph cuts that maximize the margin with respect to the labels

arXiv:2604.26375v1 Announce Type: cross Abstract: We describe our system for SemEval-2026 Task 6 (CLARITY: Unmasking Political Question Evasions), which classifies English political interview response

arXiv:2604.26057v1 Announce Type: cross Abstract: Supervised contrastive learning (SupCon) is widely used to shape representations, but has seen limited targeted study for audio deepfake detection. Ex

arXiv:2511.13285v2 Announce Type: replace Abstract: Artistic design, particularly poster design, often demands rapid yet precise modification of textual content while preserving visual harmony and typ

arXiv:2604.26620v1 Announce Type: new Abstract: Depth ambiguity and joint uncertainty are the two main obstacles in obtaining accurate human pose predictions by 2D-to-3D lifting methods proposed in th

arXiv:2511.03691v2 Announce Type: replace Abstract: Conventional fluid-driven soft grippers typically depend on external sources, which limit portability and long-term autonomy. This work introduces a

arXiv:2604.26341v1 Announce Type: new Abstract: Recent unified image generation models have achieved remarkable success by employing MLLMs for semantic understanding and diffusion backbones for image

arXiv:2604.26133v1 Announce Type: new Abstract: Informal settlements face disproportionate exposure to climate-related health hazards. However, existing methodologies lack systematic approaches to lin

arXiv:2604.25925v1 Announce Type: new Abstract: Autoregressive language models suffer from high inference latency due to their sequential decoding nature. Speculative decoding (SD) mitigates this by e

arXiv:2604.26898v1 Announce Type: cross Abstract: We prove pathwise convergence of the layerwise evolution of tokens in a finite-depth, finite-width transformer model with MultiLayer Perceptron (MLP)

arXiv:2604.26633v1 Announce Type: cross Abstract: The bottleneck in learning-based industrial defect detection is often limited not by model capacity, but by the scarcity of labeled defect data: defec

arXiv:2604.26514v1 Announce Type: cross Abstract: This paper investigates efficient methods for utilizing text-only data to improve speech recognition, focusing on encoder-dominated models that facili

arXiv:2604.26651v1 Announce Type: cross Abstract: With the increasing availability of online information, recommender systems have become an important tool for many web-based systems. Due to the conti

arXiv:2512.20340v3 Announce Type: replace Abstract: Although diffusion transformer (DiT)-based video virtual try-on (VVT) has made significant progress in synthesizing realistic videos, existing metho

arXiv:2602.03467v2 Announce Type: replace Abstract: Explanations are central to human cognition, yet AI systems often produce outputs that are difficult to understand. While symbolic AI offers a trans

arXiv:2507.12549v4 Announce Type: replace Abstract: While machine learning has advanced through massive parallelization, we identify a critical blind spot: some problems are fundamentally sequential.

These folks are trying to ban open source. They're looking to take away your freedom to choose. They're also looking to take away the rights of businesses like Cursor to fine tune and make their produ

arXiv:2505.13963v3 Announce Type: replace Abstract: Quantization methods are widely used to accelerate inference and streamline the deployment of large language models (LLMs). Although quantization's

arXiv:2510.14703v2 Announce Type: replace Abstract: Large language models (LLMs) excel at function calling, but inference scaling has been explored mainly for unstructured generation. We propose an in

arXiv:2604.26501v1 Announce Type: cross Abstract: Generating sports game reports from structured tables is a complex table-to-text task that demands both precise data interpretation and fluent narrati

✨🧠 Tribe v2, our latest model of human brain responses to sound, sight and language can now be (partly) explored on your phone📱: ▶️demo: https://aidemos.atmeta.com/tribev2/ 📄paper: https://ai.meta.com

Trump's war on science. The Trump administration has downsized US science by historic margins — but it's not just via grant or workforce cuts. Our new @nature analysis reveals the government has cut m

arXiv:2604.26951v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) offer parallel decoding and bidirectional context, but state-of-the-art dLLMs require billions of parameters f

Two Heads Are Better Than One: Async Knowledge Injection for Speech AI with Tandem Architecture Blog: https://pub.sakana.ai/kame/ 🐢 KAME: Tandem Architecture for Enhancing Knowledge in Real-Time Speec

arXiv:2412.10679v3 Announce Type: replace Abstract: Blood pressure (BP) measurement is crucial for daily health assessment. Remote photoplethysmography (rPPG), which extracts pulse waves from face vid

arXiv:2604.26489v1 Announce Type: new Abstract: DNNs have gained widespread adoption in feature interaction recommendation models. However, there has been a longstanding debate on their roles. On one

arXiv:2604.26694v1 Announce Type: cross Abstract: We propose X-WAM, a Unified 4D World Model that unifies real-time robotic action execution and high-fidelity 4D world synthesis (video + 3D reconstruc

arXiv:2604.26216v1 Announce Type: new Abstract: This paper addresses the problem of anomaly detection in accounting subject association structures, proposing a structured modeling and unsupervised dis

arXiv:2604.26412v1 Announce Type: new Abstract: Speculative decoding accelerates LLM inference, but SOTA hidden-state-based drafters suffer from long-range decay: draft accuracy degrades as the specul

arXiv:2604.26644v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) achieve strong performance on mathematical reasoning tasks but remain unreliable on challenging instances. Existing test-t