Knowledge catalogue
arXiv:2606.31413v1 Announce Type: new Abstract: Composing independently trained LoRA adapters into a single large language model is useful for multi-domain adaptation, especially when the original tra
arXiv:2601.14251v2 Announce Type: replace Abstract: We present LightOnOCR-2-1B, a 1B-parameter end-to-end multilingual vision--language model that converts document images (e.g., PDFs) into clean, nat
arXiv:2606.31943v1 Announce Type: new Abstract: Is the sense of touch a mechanism for human babies' learning of visual concepts? If so, can we quantify its importance, and to what extent do babies rel
arXiv:2606.31167v1 Announce Type: cross Abstract: VLA models have emerged as a powerful paradigm for transferring semantic knowledge from web-scale data to physical robotic control. However, current s
arXiv:2606.31135v1 Announce Type: new Abstract: We present LINet (Linear Integration Network), a Multi-Stream Neural Network (MSNN) for RGB-D scene classification. Current multi-modal architectures tr
arXiv:2511.11270v2 Announce Type: replace Abstract: While foundation models have emerged as general-purpose visual backbones, their representations are primarily optimized for semantics and lack expli
arXiv:2606.30673v1 Announce Type: cross Abstract: Autoregressive Transformers dominate high-quality mesh generation by producing artist-worthy topologies, yet their inherent sequential decoding induce
arXiv:2606.31148v1 Announce Type: cross Abstract: 3D Visual Grounding (3DVG) aims to localize target objects in 3D scenes given natural language descriptions. Existing approaches typically perform rea
arXiv:2509.17246v2 Announce Type: replace Abstract: We introduce SPFSplatV2, an efficient feed-forward framework for 3D Gaussian splatting from sparse multi-view images, requiring no ground-truth pose
arXiv:2602.23721v2 Announce Type: replace-cross Abstract: Vision-language-action (VLA) models integrate visual observations and language instructions to predict robot actions, demonstrating promising
arXiv:2606.31259v1 Announce Type: cross Abstract: Diffusion-based text-to-audio (TTA) models achieve impressive synthesis quality but suffer from high inference latency due to iterative multi-step den
arXiv:2606.31648v1 Announce Type: new Abstract: We present LuckyStar 111B, a 111B-parameter hybrid reasoning model developed through a collaboration between Cohere and LG CNS for Korean-English enterp
arXiv:2604.04050v2 Announce Type: replace Abstract: Flow-matching methods for 3D shape assembly learn point-wise velocity fields that transport parts toward assembled configurations, yet they receive
arXiv:2601.00260v2 Announce Type: replace Abstract: While foundation models in radiology are expected to be applied to various clinical tasks, computational cost constraints remain a major challenge w
arXiv:2606.31839v1 Announce Type: new Abstract: Volumetric medical image segmentation is essential for both preoperative diagnosis and intraoperative guidance. While recent years have witnessed rapid
arXiv:2606.31184v1 Announce Type: cross Abstract: Adaptive experiments for average treatment effects (ATE) require randomized allocations balancing valid inference with statistical efficiency. The ora
arXiv:2606.30777v1 Announce Type: new Abstract: The growing availability of trajectory datasets has fueled major advances in data-driven motion prediction. Yet, models trained on one dataset often fai
arXiv:2603.16271v3 Announce Type: replace Abstract: Video diffusion models lack explicit geometric supervision during training, leading to inconsistency artifacts such as object deformation, spatial d
arXiv:2606.31258v1 Announce Type: new Abstract: Projection-conditioned novel view synthesis (NVS) warps an explicit 3D reconstruction of the input view into the target camera and conditions a generato
arXiv:2606.31456v1 Announce Type: new Abstract: With an increasing number of Object Detection (OD) models being deployed on edge devices, Zero-Shot Quantization for OD (ZSQ-OD) aims to quantize these
arXiv:2606.29166v1 Announce Type: cross Abstract: Adaptive video streaming is a widely used technique for delivering video content over the internet. One of the key challenges is determining the optim
arXiv:2511.01472v2 Announce Type: replace Abstract: The rapid progress of vision--language models (VLMs) has sparked growing interest in robotic control, where natural language can express the operati
arXiv:2606.29335v1 Announce Type: cross Abstract: Multimodal speaker identification systems face two key challenges in real-world deployment: missing modalities and language mismatch between training
arXiv:2606.29167v1 Announce Type: new Abstract: Finding dense correspondences between 3D shapes is a fundamental yet unresolved challenge, especially in real-world environments. These environments pre
arXiv:2509.15001v3 Announce Type: replace-cross Abstract: Child-centered daylong recordings are essential for studying early language development, but existing speech models trained on clean adult dat
arXiv:2512.02453v2 Announce Type: replace Abstract: Existing stylized motion generation models have shown their remarkable ability to understand specific style information from the style motion, and i
arXiv:2606.28361v1 Announce Type: cross Abstract: Multi-step retrieval-augmented generation (RAG) has been widely deployed as LLM-powered web services for complex question answering, where iterative r
arXiv:2606.29014v1 Announce Type: new Abstract: Recent advancements in generative artificial intelligence (AI) and large language models (LLMs) have shown significant promise in automating complex rea
arXiv:2606.28524v1 Announce Type: new Abstract: Recent work suggests that Large Language Models (LLMs) are sensitive to the belief states of agents described by text, as measured by the false belief t
arXiv:2606.29522v1 Announce Type: cross Abstract: A central hope behind process supervision is that models can expose intermediate variables that matter for their later behavior. For this to help with
arXiv:2606.29614v1 Announce Type: cross Abstract: This study examines whether supervised fine-tuning remains necessary for Turkish sentiment analysis in the era of large language models. We compare cl
arXiv:2510.25013v2 Announce Type: replace-cross Abstract: Mechanistic interpretability aims to reverse-engineer large language models (LLMs) into human-understandable computational circuits. However,
arXiv:2606.29384v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have become an important paradigm of embodied AI. However, existing VLA models typically assume well-lit and stable
arXiv:2606.28980v1 Announce Type: cross Abstract: Ovarian cancer is frequently diagnosed at an advanced stage, making preoperative contrast-enhanced computed tomography (CT) central to staging and sur
arXiv:2606.29859v1 Announce Type: cross Abstract: With the rise of data-intensive science, algorithms have become central to scientific research. In academic papers, algorithms are mentioned for diffe
arXiv:2507.06764v5 Announce Type: replace-cross Abstract: In this work, we propose Fast Equivariant Imaging (FEI), a novel unsupervised learning framework to rapidly and efficiently train deep imaging
arXiv:2603.13326v2 Announce Type: replace-cross Abstract: Multimodal Transformers often produce predictions without clarifying how different modalities jointly support a decision. Most existing multim
arXiv:2606.28933v1 Announce Type: new Abstract: Venture capital (VC) investment decisions face distinct challenges, such as multi-source heterogeneous data, non-stationary time series, and the demand
arXiv:2510.01878v2 Announce Type: replace Abstract: Low-rank gradient optimization for large language models is currently divided into two categories: structured methods that rigorously identify subsp
arXiv:2505.20928v2 Announce Type: replace Abstract: Manually refining radiological segmentation masks is highly resource-intensive. To determine when this expert commitment is truly justified for the
arXiv:2606.30460v1 Announce Type: new Abstract: In this paper, we aim to combine the advantages of existing sequence parallelism paradigms and overcomes their drawbacks, the most serious of which is t
arXiv:2603.10604v3 Announce Type: replace Abstract: Generative models are increasingly used in video game engines to enhance the photorealism of rendered images for visual synthetic data generation an
arXiv:2606.29874v1 Announce Type: cross Abstract: Data-driven material modeling techniques have gained significant attention due to their ability to capture complex constitutive behaviors beyond the l
arXiv:2606.28991v1 Announce Type: new Abstract: Cardiac magnetic resonance imaging (CMR) routinely records structured acquisition metadata, yet most CMR foundation models rely primarily on image-only
arXiv:2606.30537v1 Announce Type: cross Abstract: Autonomous driving policies should be able to improve continually as deployment exposes them to increasingly diverse and long-tail traffic situations.
arXiv:2606.29498v1 Announce Type: new Abstract: Weakly supervised video anomaly detection (WSVAD) has predominantly focused on temporal localization, identifying when anomalies occur while largely neg
arXiv:2606.28670v1 Announce Type: cross Abstract: We introduce MACROCAST, a lightweight Time Series Foundation Model (TSFM) for real-time macroeconomic forecasting. Existing TSFMs suffer from data lea
arXiv:2606.28537v1 Announce Type: cross Abstract: Multiview mammography relies on paired craniocaudal (CC) and mediolateral oblique (MLO) views to provide complementary projections of a 3D breast volu
arXiv:2606.29066v1 Announce Type: new Abstract: Masked diffusion language models (MDLMs) generate text by iteratively unmasking tokens, but their standard decoder reduces each step to a binary action:
arXiv:2606.28697v1 Announce Type: cross Abstract: Pathology foundation models (PFMs) have demonstrated strong potential across clinical and scientific applications, yet their performance is often hind
arXiv:2510.03142v2 Announce Type: replace-cross Abstract: Visual navigation policy is widely regarded as a promising direction, as it mimics humans by using egocentric visual observations for navigati
arXiv:2606.29013v1 Announce Type: new Abstract: Leveraging capabilities of large language models (LLMs) in text-to-image (T2I) synthesis is an important research direction. In this work we investigate
arXiv:2606.30638v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) has emerged at the forefront of 3D scene reconstruction. Extending 3DGS with language-driven, open-vocabulary understanding
arXiv:2606.29717v1 Announce Type: cross Abstract: Predicting a material's properties from its structure is a central, fast-advancing problem in computational materials science. A decade of work has pr
arXiv:2606.29465v1 Announce Type: new Abstract: Class-incremental learning requires a model to learn new classes while preserving decision regions for old ones. This is difficult when raw old samples
arXiv:2606.29577v1 Announce Type: cross Abstract: Positron Emission Tomography (PET) reveals brain metabolism and is clinically central to neurodegenerative disease assessment, yet existing 3D brain f
arXiv:2606.30611v1 Announce Type: new Abstract: Understanding facial expressions in videos requires modeling subtle and localized facial dynamics under unconstrained conditions. Although recent Vision
arXiv:2507.00263v2 Announce Type: replace Abstract: The rapid growth of vacation rental (VR) platforms has led to an increasing volume of property images, often uploaded without structured categorizat
The food delivery leader in China just dropped an open weights 1.6 trillion parameter model while half the USA was sleeping … 🫨 🇨🇳 Meituan, China's largest food delivery platform, open-sourced a 1.6 t
arXiv:2606.30308v1 Announce Type: new Abstract: 4D hand motion reconstruction from egocentric video is bottlenecked by clear limitations of existing methods: image-based pipelines depend on a detector