Video Diffusion Transformers (DiTs) generate high-quality videos but demand substantial compute due to wide blocks, deep architectures, and iterative sampling. ...
Flowcharts are widely used in industrial requirements, but usually remain embedded as static images. Vision Language Models (VLMs) show promise in the conversio...
Video spatial reasoning requires accumulating viewpoint-dependent evidence over time while retaining information useful to the question being asked. Existing sp...
Chart question-answering (QA) benchmarks aim to pose questions that require visual reasoning to correctly answer, but models can often reach solutions through s...
Sparse-view 3D reconstruction is increasingly addressed with feed-forward splatting networks that predict explicit primitives directly from images. Yet most exi...
Generating high-fidelity and controllable synthetic data is critical for advancing end-to-end autonomous driving, particularly for addressing the long tail of r...
Subject-driven image generation aims to synthesize new images that preserve the identity of the given subject while following textual instructions. Existing app...
Multimodal Large Language Models (MLLMs) achieve versatility by reformulating diverse tasks into a unified instruction-following framework via instruction tunin...
Current video-to-4D methods struggle with complex topology changes, transparent materials, thin structures, and inner surfaces. We present Helix4D, a dynamic me...
Recent advances in few-step diffusion distillation have enabled efficient image generation, yet aligning these models with human preferences remains challenging...
Autoregressive video generators are attractive for streaming, long-horizon, and interactive applications, but distilling strong black-box teachers into causal s...
Fine-tuning MLLMs for Video Temporal Grounding (VTG) often improves in-domain performance but degrades sharply under domain shift. In this work, we find that th...
Structure-from-Motion -- the process of simultaneously estimating camera poses and 3D scene structure from a collection of images -- remains a central challenge...
In this paper, we introduce InstructSAM, a unified and streamlined framework designed for multi-instance segmentation under arbitrary instructions. We formulate...
We present Channel-wise Vector Quantization (CVQ), a novel image tokenization paradigm that replaces patch-wise tokens with channel-wise tokens. Unlike conventi...
Camera-controlled video generation has achieved remarkable progress in recent years. However, existing video-to-video re-rendering methods primarily rely on Sup...
Most practical high-resolution text-to-image systems, including latent diffusion and autoregressive models, perform generation in a compact latent space, and a ...
Multimodal Large Language Models have advanced visual reasoning, yet a purely textual chain of thought remains a bottleneck for questions that require fine-grai...
Identifying which brain regions represent a visual concept in the human brain is a central challenge in neuroscience. Existing approaches have localized coarse ...
Visual geometry transformers have become powerful architectures for multi-view 3D reconstruction, enabling joint prediction of multiple 3D attributes in a feed-...
Mask-free video object insertion has emerged as a challenging task, requiring harmonious integration of reference objects into source videos. However, existing ...
Online 3D reconstruction requires estimating camera pose and scene geometry under strict causal and bounded-memory constraints. Existing methods often suffer fr...
We introduce a new approach to high-fidelity 3D scene reconstruction from multi-view RGB images that tightly couples reconstruction with a strong generative 3D ...
Despite remarkable progress in Multimodal Large Language Models (MLLMs), these models still struggle with fine-grained understanding tasks. In this work, we pro...
Modern video generators produce visually compelling clips but still struggle with physical and motion consistency, limiting their use as reliable world simulato...
Causal generative modeling is essential for developing reliable and transparent AI systems capable of counterfactual reasoning. While existing approaches focus ...
Keyframe selection is a direct way to provide verifiable visual evidence for long-video question answering (QA). Queries differ in what they require, and findin...
Video Large Language Models (Video-LLMs) have made rapid progress on temporal video understanding, yet many fail at a basic perceptual primitive: signed image-p...
Camera pose matters. The position and orientation of each viewpoint define a shared spatial coordinate frame that relates observations across video frames. Yet ...
Current motion-controlled image-to-video generation models rigidly follow user-provided trajectories that are often sparse, imprecise, and causally incomplete. ...
Vision-and-Language Navigation (VLN) requires an agent to ground language instructions to its own movement within a visual environment. While state-of-the-art m...
Vision-Language-Action (VLA) models have shown strong potential for general-purpose robot manipulation by unifying perception and action. However, existing VLA ...
Robust training and validation of Autonomous Driving Systems (ADS) require massive, diverse datasets. Proprietary data collected by Autonomous Vehicle (AV) flee...
Representation Autoencoders (RAEs) leverage frozen vision foundation models (VFMs) as tokenizer encoders, providing robust high-level representations that facil...
Children with rare genetic diseases often exhibit distinctive facial phenotypes, yet developing computer vision systems for early diagnosis remains challenging ...
As generative image models evolve rapidly, the perceptual gap between generated and real images continues to narrow, making AI-generated image detection increas...
Autoregressive video diffusion models have enabled real-time, action-conditioned world generation. However, sustaining a persistent world, where revisiting a pr...
As wearable and mobile devices become increasingly embedded in daily life, they offer a practical way to continuously sense human motion in the wild. But inerti...
We observe that existing model interpretation methods generally ignore the baseline, and such neglect often results in imprecise or even incorrect interpretatio...
Pretrained diffusion models serve as frozen teachers feeding downstream pipelines such as text-to-3D, single-step distillation, and data attribution. The teache...
Currently, enhancing Unified Multimodal Models (UMMs) with image understanding, generation, and editing capabilities mainly relies on mixed multi-task training....
Discrete diffusion models excel at visual synthesis but rely on slow, iterative decoding. Existing single-step distillation methods attempt to bypass this bottl...
Visual Question Answering (VQA) benchmarks have largely emphasized perception-based tasks that can be solved from visual content alone. In contrast, many real-w...
Pose-driven full-body avatars built on neural rendering produce high-quality novel views of a captured subject. Yet loose clothing and other dynamic elements de...
View-conditioned 3D generators such as SAM 3D, TRELLIS and Hunyuan3D produce high-quality object reconstructions from a single view, but real-world visual obser...
Although existing video editing methods are generally feasible, they often require many costly iterations and still struggle to deliver high-quality yet satisfy...
We introduce ProtoPathway, an interpretable-by-design multimodal framework for cancer survival prediction that unifies whole slide imaging and transcriptomics t...
Vision-language models (VLMs) are increasingly being explored for video game quality assurance, especially gameplay glitch detection. Most existing evaluations,...
