Text-to-image generation models have advanced rapidly, yet achieving fine-grained control over generated images remains difficult, largely due to limited unders...
While large-scale diffusion models have revolutionized video synthesis, achieving precise control over both multi-subject identity and multi-granularity motion ...
Humans perceive and understand real-world spaces through a stream of visual observations. Therefore, the ability to streamingly maintain and update spatial evid...
Multi-modal large language models (MLLMs) have advanced general-purpose video understanding but struggle with long, high-resolution videos -- they process every...
Recently, Multimodal Large Language Models (MLLMs) have been widely integrated into diffusion frameworks primarily as text encoders to tackle complex tasks such...
Existing video depth estimation faces a fundamental trade-off: generative models suffer from stochastic geometric hallucinations and scale drift, while discrimi...
Constructing scientific multimodal document reasoning datasets for foundation model training involves an inherent trade-off among scale, faithfulness, and reali...
Acceleration methods for diffusion models (e.g., token merging or downsampling) typically optimize synthesis quality under reduced compute, yet often ignore dis...
Salient object detection (SOD) in remote sensing images faces significant challenges due to large variations in object sizes, the computational cost of self-att...
We propose a fully automated AI system that produces short comedic videos similar to sketch shows such as Saturday Night Live. Starting with character reference...
We propose a 3D latent representation that jointly models object geometry and view-dependent appearance. Most prior works focus on either reconstructing 3D geom...
In this paper, we propose Agentar-Fin-OCR, a document parsing system tailored to financial-domain documents, transforming ultra-long financial PDFs into semanti...
We propose Neural Field Thermal Tomography (NeFTY), a differentiable physics framework for the quantitative 3D reconstruction of material properties from transi...
Generating music that temporally aligns with video events is challenging for existing text-to-music models, which lack fine-grained temporal control. We introdu...
We propose DynVLA, a driving VLA model that introduces a new CoT paradigm termed Dynamics CoT. DynVLA forecasts compact world dynamics before action generation,...
VLMs have become increasingly proficient at a range of computer vision tasks, such as visual question answering and object detection. This includes increasingly...
Recent advances in text-to-image (T2I) generation have greatly improved visual quality, yet producing images that appear visually authentic to real-world photog...
Vision Language Models (VLMs) exhibit persistent hallucinations in counting tasks, with accuracy substantially lower than other visual reasoning tasks (excludin...
Foundation models (FMs) show great promise for robust downstream performance across medical imaging tasks and modalities, including cardiac magnetic resonance (...
A central idea in mechanistic interpretability is that neural networks represent more features than they have dimensions, arranging them in superposition to for...
Online novel view synthesis remains challenging, requiring robust scene reconstruction from sequential, often unposed, observations. We present ReCoSplat, an au...
Language-conditioned local navigation requires a robot to infer a nearby traversable target location from its current observation and an open-vocabulary, relati...
Self-supervised visual pre-training methods face an inherent tension: contrastive learning (CL) captures global semantics but loses fine-grained detail, while m...
Multiple Instance Learning (MIL) has been widely applied in histopathology to classify Whole Slide Images (WSIs) with slide-level diagnoses. While the ground tr...
Conventional clinical CMR pipelines rely on a sequential 'reconstruct-then-analyze' paradigm, forcing an ill-posed intermediate step that introduces avoidable a...
In interventional radiology, Cone-Beam Computed Tomography (CBCT) is a helpful imaging modality that provides guidance to practicians during minimally invasive ...
Multimodal neuroimaging provides complementary insights for Alzheimer's disease diagnosis, yet clinical datasets frequently suffer from missing modalities. We p...
Text-motion retrieval aims to learn a semantically aligned latent space between natural language descriptions and 3D human motion skeleton sequences, enabling b...
Chamfer distance is the standard training loss for point cloud reconstruction, completion, and generation, yet directly optimizing it can produce worse Chamfer ...
Flatness measures based on the spectrum or the trace of the Hessian of the loss are widely used as proxies for the generalization ability of deep networks. Howe...
Diffusion models degrade images through noise, and reversing this process reveals an information hierarchy across timesteps. Scale-space theory exhibits a simil...
CLIP-based prompt tuning enables pretrained Vision-Language Models (VLMs) to efficiently adapt to downstream tasks. Although existing studies have made signific...
Autoregressive (AR) diffusion offers a promising framework for generating videos of theoretically infinite length. However, a major challenge is maintaining tem...
Single-stage multi-person pose estimation aims to jointly perform human localization and keypoint prediction within a unified framework, offering advantages in ...
We tackle the challenging task of generating complete 3D facial animations for two interacting, co-located participants from a mixed audio stream. While existin...
Recent advancements in 3D Gaussian Splatting (3DGS) have shifted the focus toward balancing reconstruction fidelity with computational efficiency. In this work,...
As video content creation shifts toward long-form narratives, composing short clips into coherent storylines becomes increasingly important. However, prevailing...
Template-free animatable head avatars can achieve high visual fidelity by learning expression-dependent facial deformation directly from a subject's capture, av...
Ensuring trustworthiness in open-world visual recognition requires models that are interpretable, fair, and robust to distribution shifts. Yet modern vision sys...
Streaming video understanding often involves time-sensitive scenarios where models need to answer exactly when the supporting visual evidence appears: answering...
High‑Stakes Explainability in Medical Diagnostics In high‑stakes settings like medical diagnostics, users often want to know what led a computer‑vision model t...
Multimodal Large Language Models (MLLM) classification performance depends critically on evaluation protocol and ground truth quality. Studies comparing MLLMs w...
While recent multimodal large language models (MLLMs) have made impressive strides, they predominantly employ a conventional autoregressive architecture as thei...
Incremental Few-Shot (IFS) segmentation aims to learn new categories over time from only a few annotations. Although widely studied in 2D, it remains underexplo...
Surgeons don't just see -- they interpret. When an expert observes a surgical scene, they understand not only what instrument is being used, but why it was chos...
Vision Language Model (VLM) development has largely relied on scaling model size, which hinders deployment on compute-constrained mobile and edge devices such a...
Next-generation autonomous vehicles (AVs) rely on large volumes of multisource and multimodal (M^2) data to support real-time decision-making. In practice, data...
We introduce SurgFormer, a multiresolution gated transformer for data driven soft tissue simulation on volumetric meshes. High fidelity biomechanical solvers ar...
