Search: “research”

arXiv:2608.20375v1 Announce Type: new Abstract: Tree-based speculative decoding raises the mean accepted tokens of standard speculative decoding by verifying multiple draft paths, and existing tree bu

arXiv:2407.02765v4 Announce Type: replace-cross Abstract: We study the distributed optimization problem over a graphon with a continuum of nodes, which is regarded as the limit of the distributed netw

arXiv:2608.20534v1 Announce Type: new Abstract: Generating egocentric video from a single exocentric video is an emerging and important topic for AR/VR and physical AI. Compared with conventional nove

arXiv:2608.20962v1 Announce Type: new Abstract: In household manipulation, pose uncertainty often results in off-centre or partial initial contact, making reliable object acquisition difficult. Roller

arXiv:2608.20891v1 Announce Type: cross Abstract: We present a vision-only state estimation system for X-configuration quadcopters equipped with a canonical stereo camera pair and no inertial sensors.

arXiv:2602.06621v2 Announce Type: replace-cross Abstract: This paper introduces a rigorous framework for defining generative diffusion models in infinite dimensions via Doob's h-transform. Rather than

arXiv:2608.20910v1 Announce Type: new Abstract: With large pretrained models, existing methods have effectively improved instruction-based video editing. However, most of them rely on an in-place edit

arXiv:2608.20348v1 Announce Type: cross Abstract: Electronic health records now routinely exceed 100,000 tokens per patient. Yet large language models exhibit the lost-in-the-middle (LitM) effect: inf

arXiv:2602.13586v2 Announce Type: replace Abstract: Clustering is a fundamental unsupervised learning technique for uncovering data structures to facilitate knowledge discovery and decision-making. Wh

arXiv:2608.20380v1 Announce Type: cross Abstract: Resting-state functional magnetic resonance imaging (rs-fMRI) has enabled non-invasive mapping of functional brain interactions for computer-aided dia

arXiv:2608.20384v1 Announce Type: new Abstract: Multimodal affect and behaviour classifiers that fuse heterogeneous text, audio, and visual streams must simultaneously achieve competitive accuracy and

arXiv:2603.23463v2 Announce Type: replace-cross Abstract: Recent diffusion-based models achieve photorealism in image inpainting but require many sampling steps, limiting practical use. Few-step text-

arXiv:2608.20557v1 Announce Type: new Abstract: Domain shift across clinical centers using different imaging hardware or acquisition protocols remains a fundamental barrier to deploying deep learning

arXiv:2606.15765v2 Announce Type: replace Abstract: Vision foundation models (VFMs) exhibit complementary strengths shaped by their pretraining objectives. Yet prevailing methods for multi-task dense

arXiv:2608.20659v1 Announce Type: new Abstract: Methods that transfer predictions from two-dimensional foundation models into three-dimensional segmentation are commonly grouped by task or representat

こちらのポジション、とても面白い環境でLLMの研究開発に取り組めます！意外と小規模なチームで取り組んでおり、様々な能力を持った優秀なメンバーがいるので学びもめちゃくちゃ多いです！最近は論文やProductなどいろいろな形で成果を公開できるのも魅力だと思います！少しでもご興味ある方はぜひ🙌 【採用情報】Member of Technical Staff (LLM Development) の募集を開

arXiv:2510.13922v2 Announce Type: replace-cross Abstract: Clinical notes contain unstructured text provided by clinicians during patient encounters. These notes are usually accompanied by a sequence o

arXiv:2608.20788v1 Announce Type: new Abstract: Deep learning-based Multi-View Stereo (MVS) has advanced significantly but often generalizes poorly to unseen scenes, particularly in occluded areas or

arXiv:2608.21133v1 Announce Type: new Abstract: Medical image-text data can expose protected health information (PHI) through both visible image content as well as accompanying text, creating a barrie

arXiv:2608.21265v1 Announce Type: new Abstract: Large language models often rely on Chain-of-Thought (CoT) reasoning to solve complex tasks, but verbose reasoning traces introduce substantial inferenc

arXiv:2608.20927v1 Announce Type: cross Abstract: Cross-model latent guidance lets a frozen large mentor encode an input once and a frozen small student generate from the resulting signal. Existing me

arXiv:2608.20653v1 Announce Type: new Abstract: Clustering methods have been used to identify distinct groups of milk samples, cows, or herds. Fourier-transform infrared (FTIR) spectroscopy, particula

arXiv:2608.20635v1 Announce Type: cross Abstract: Discrete diffusion models have demonstrated strong performance across a range of datasets, including natural language data and graph-structured data.

arXiv:2608.20448v1 Announce Type: cross Abstract: Digital 3D objects used in games and animation are often required to be compositional; that is, decomposed into semantically meaningful parts. Recent

arXiv:2608.20639v1 Announce Type: new Abstract: Multi-View Pedestrian Detection (MVPD) aims to detect pedestrians in the form of a bird's eye view map from multi-view images. Recent MVPD methods adopt

arXiv:2608.20354v1 Announce Type: cross Abstract: This study introduces NeuroStrata, a connectivity-aware deep representation learning framework for EEG-based mental stress analysis using Time-Varying

arXiv:2409.16322v4 Announce Type: replace-cross Abstract: Alzheimer's Disease (AD) detection commonly employs machine learning classification models to distinguish between individuals with AD and thos

arXiv:2608.20640v1 Announce Type: cross Abstract: Multi-merchant e-commerce catalogs contain equivalent and related products under different merchant-scoped identifiers, fragmenting behavioral evidenc

arXiv:2410.08875v3 Announce Type: replace Abstract: Designing a network (e.g., a telecommunication or transport network) is mainly done offline, in a planning phase, prior to the operation of the netw

arXiv:2608.20856v1 Announce Type: new Abstract: Document-Level Relation Extraction (DocRE) relies heavily on costly manually annotated datasets, while large distant supervision resources such as DocRE

arXiv:2608.20569v1 Announce Type: new Abstract: Are frontier models able to introspect about their internal states? Recent work suggests that under certain conditions a complex enough model can audit

arXiv:2608.21349v1 Announce Type: cross Abstract: Scarce data and tumor heterogeneity limit patient-level cancer treatment-response prediction. Existing approaches predict response from pretreatment m

arXiv:2608.20626v1 Announce Type: cross Abstract: Soft, wearable robotic devices can deliver haptic feedback to support a wide range of tasks, such as extended reality, training various skills, and re

arXiv:2608.20387v1 Announce Type: cross Abstract: While recent text-to-speech (TTS) models achieve high naturalness, controlling fine-grained expression via natural-language instructions remains chall

arXiv:2608.20660v1 Announce Type: cross Abstract: Simulating a continuous-time quantum walk (CTQW) on a graph in the circuit model of quantum computing requires decomposing its Hamiltonian into terms

arXiv:2608.20712v1 Announce Type: cross Abstract: We propose a novel object detection method that enables us to protect sensitive visual information of test images. Previous studies considering visual

arXiv:2608.21315v1 Announce Type: new Abstract: That a prompt's effect is not a property of the prompt is established: prompts optimised for one model degrade on another, and rankings reorder under ne

arXiv:2507.19290v2 Announce Type: replace-cross Abstract: We study the problem of learning a structured approximation (low-rank, sparse, banded, etc.) to an unknown matrix A given access to matrix-vec

I'm one of the co-authors of this paper. It's a seminal work in exploring the properties of 3D generated by LLMs via spatial programming. I've set up visual demonstrations of such 3D objects at: https

arXiv:2608.21236v1 Announce Type: new Abstract: Representation engineering offers a lightweight means of controlling language-model behavior by modifying intermediate hidden states, but its direct app

arXiv:2608.20870v1 Announce Type: new Abstract: Infrared small target detection is still challenging in remote sensing imagery, because the targets are extremely small, exhibit weak local contrast, an

arXiv:2608.21022v1 Announce Type: new Abstract: Micro-actions are subtle, short, low-amplitude body movements, such as a fidgeting hand or a slight head tilt, that humans perform with little conscious

arXiv:2504.13988v2 Announce Type: replace Abstract: This work defends the 'Whole Hog Thesis': sophisticated Large Language Models (LLMs) like ChatGPT are full-blown linguistic and cognitive agents, po

arXiv:2608.21308v1 Announce Type: new Abstract: Test-Time Training (TTT) enables long-context processing via continuous weight updates during inference, but current methods struggle to balance the exp

arXiv:2608.20404v1 Announce Type: cross Abstract: The discovery of governing partial differential equations (PDEs) directly from spatiotemporal data has emerged as a powerful tool for understanding th

arXiv:2608.20839v1 Announce Type: new Abstract: Watermarking diffusion language models (DLMs) requires mechanisms compatible with iterative parallel unmasking rather than autoregressive decoding. Exis