Finding matching keypoints between images is a core problem in 3D computer vision. However, modern matchers struggle with large in-plane rotations. A straightfo...
Generating high-fidelity 3D indoor scenes remains a significant challenge due to data scarcity and the complexity of modeling intricate spatial relations. Curre...
We have witnessed remarkable advances in LLM reasoning capabilities with the advent of DeepSeek-R1. However, much of this progress has been fueled by the abunda...
In this work, we study Human-Object Interaction Video Generation (HOIVG), which aims to synthesize high-quality human-object interaction videos conditioned on t...
Accurate delineation of the Clinical Target Volume (CTV) is essential for radiotherapy planning, yet remains time-consuming and difficult to assess, especially ...
We present SyncFix, a framework that enforces cross-view consistency during the diffusion-based refinement of reconstructed scenes. SyncFix formulates refinemen...
Despite rapid progress in video generation, existing models are incapable of producing vector animation, a dominant and highly expressive form of multimedia on ...
High dynamic range (HDR) imagery offers a rich and faithful representation of scene radiance, but remains challenging for generative models due to its mismatch ...
Large Multimodal Models (LMMs) have achieved remarkable progress in general-purpose vision--language understanding, yet they remain limited in tasks requiring p...
GUI agents drive applications through their visual interfaces instead of programmatic APIs, interacting with arbitrary software via taps, swipes, and keystrokes...
Automation underpins progress across scientific and industrial disciplines. Yet, automating tasks requiring interpretation of abstract visual information remain...
Deep learning underpins a wide range of applications in MRI, including reconstruction, artifact removal, and segmentation. However, progress has been driven lar...
Using behavioural science, health interventions focus on behaviour change by providing a framework to help patients acquire and maintain healthy habits that imp...
Tired of spending hours manually measuring photos, sourcing material prices, and calculating quotes? For handyman businesses, this back‑office work is a major p...
Image classification sounds easy until you remember that a computer never sees “objects.” It only sees pixel arrays. This post explains why that makes k‑NN a us...
Prompt learning is a parameter-efficient approach for vision-language models, yet its robustness under label noise is less investigated. Visual content contains...
Vision-language models (VLMs) still struggle with visual perception tasks such as spatial understanding and viewpoint recognition. One plausible contributing fa...
Large Vision Language Models (LVLMs) achieve strong multimodal reasoning but frequently exhibit hallucinations and incorrect responses with high certainty, whic...
Human body fitting, which aligns parametric body models such as SMPL to raw 3D point clouds of clothed humans, serves as a crucial first step for downstream tas...
Free-form bones, that conform closely to the surface, can effectively capture non-rigid deformations, but lack a kinematic structure necessary for intuitive con...
The advent of agentic multimodal models has empowered systems to actively interact with external environments. However, current agents suffer from a profound me...
Text-to-video diffusion models have enabled open-ended video synthesis, but often struggle with generating the correct number of objects specified in a prompt. ...
Event cameras offer multiple advantages in monocular egocentric 3D human pose estimation from head-mounted devices, such as millisecond temporal resolution, hig...
Robotic manipulation with deformable objects represents a data-intensive regime in embodied learning, where shape, contact, and topology co-evolve in ways that ...
This paper addresses the task of large-scale 3D scene reconstruction from long video sequences. Recent feed-forward reconstruction models have shown promising r...
Multimodal Mixture-of-Experts (MoE) models have achieved remarkable performance on vision-language tasks. However, we identify a puzzling phenomenon termed Seei...
Text-to-Audio-Video (T2AV) generation is rapidly becoming a core interface for media creation, yet its evaluation remains fragmented. Existing benchmarks largel...
Group Relative Policy Optimization (GRPO) has emerged as the de facto Reinforcement Learning (RL) objective driving recent advancements in Multimodal Large Lang...
We introduce RewardFlow, an inversion-free framework that steers pretrained diffusion and flow-matching models at inference time through multi-reward Langevin d...
Spatiotemporal neural dynamics and oscillatory synchronization are widely implicated in biological information processing and have been hypothesized to support ...
Large Chunk Test-Time Training (LaCT) has shown strong performance on long-context 3D reconstruction, but its fully plastic inference-time updates remain vulner...
Generating motion-controlled videos--where user-specified actions drive physically plausible scene dynamics under freely chosen viewpoints--demands two capabili...
We propose TC-AE, a ViT-based architecture for deep compression autoencoders. Existing methods commonly increase the channel number of latent representations to...
Recent advances in vision-language models (VLMs) have improved image captioning for cultural heritage. However, inferring structured cultural metadata (e.g., cr...
3D Gaussian Splatting (3DGS) has revolutionized fast novel view synthesis, yet its opacity-based formulation makes surface extraction fundamentally difficult. U...
Scaling up robot learning will likely require human data containing rich and long-horizon interactions in the wild. Existing approaches for collecting such data...
Photon-counting CT (PCCT) provides superior image quality with higher spatial resolution and lower noise compared to conventional energy-integrating CT (EICT), ...
Existing dynamic data pruning methods often fail under noisy-label settings, as they typically rely on per-sample loss as the ranking criterion. This could mist...
Multiple Instance Learning (MIL) is the dominant framework for gigapixel whole-slide image (WSI) classification in computational pathology. However, current MIL...
Automated face recognition has made rapid strides over the past decade due to the unprecedented rise of deep neural network (DNN) models that can be trained for...
World action models (WAMs) have emerged as a promising direction for robot policy learning, as they can leverage powerful video backbones to model the future st...
Large vision-language models can produce object hallucinations in image descriptions, highlighting the need for effective detection and mitigation strategies. P...
Most digital videos are stored in 8-bit low dynamic range (LDR) formats, where much of the original high dynamic range (HDR) scene radiance is lost due to satur...
The Character Error Rate (CER) is a key metric for evaluating the quality of Optical Character Recognition (OCR). However, this metric assumes that text has bee...
MLLMs have been successfully applied to multimodal embedding tasks, yet their generative reasoning capabilities remain underutilized. Directly incorporating cha...
This paper introduces the Polynomial Mixer (PoM), a novel token mixing mechanism with linear complexity that serves as a drop-in replacement for self-attention....
This study proposes a lightweight multimodal adaptation framework to bridge the representation gap between RGB-pretrained VLMs and thermal infrared imagery, and...
Scalable generation of outdoor driving scenes requires 3D representations that remain consistent across multiple viewpoints and scale to large areas. Existing s...
