Synthesizing high-fidelity frozen 3D scenes from monocular Mannequin-Challenge (MC) videos is a unique problem distinct from standard dynamic scene reconstructi...
Reward models are critical for aligning vision-language systems with human preferences, yet current approaches suffer from hallucination, weak visual grounding,...
We introduce ShadowDraw, a framework that transforms ordinary 3D objects into shadow-drawing compositional art. Given a 3D object, our system predicts scene par...
Standard diffusion corrupts data using Gaussian noise whose Fourier coefficients have random magnitudes and random phases. While effective for unconditional or ...
All-in-One Image Restoration (AiOIR) tasks often involve diverse degradation that require robust and versatile strategies. However, most existing approaches typ...
Video generation models are rapidly advancing, but can still struggle with complex video outputs that require significant semantic branching or repeated high-le...
In recent years, Image Quality Assessment (IQA) for AI-generated images (AIGI) has advanced rapidly; however, existing methods primarily target portraits and ar...
Ever struggle to get accurate motion capture when hands are intertwined, hidden behind objects, or even just slightly out of view? Standard computer vision syst...
Normalizing Flows (NFs) learn invertible mappings between the data and a Gaussian distribution. Prior works usually suffer from two limitations. First, they add...
We introduce the 'single-life' learning paradigm, where we train a distinct vision model exclusively on egocentric videos captured by one individual. We leverag...
Graphic design forms the cornerstone of modern visual communication, serving as a vital medium for promoting cultural and commercial events. Recent advances hav...
We introduce radiance meshes, a technique for representing radiance fields with constant density tetrahedral cells produced with a Delaunay tetrahedralization. ...
Vision Language Models (VLMs) demonstrate strong qualitative visual understanding, but struggle with metrically precise spatial reasoning required for embodied ...
Sign Language Production (SLP) is the process of converting the complex input text into a real video. Most previous works focused on the Text2Gloss, Gloss2Pose,...
A truly interactive world model requires three key ingredients: real-time long-horizon streaming, consistent spatial memory, and precise user control. However, ...
This thesis presents novel contributions in two primary areas: advancing the efficiency of generative models, particularly normalizing flows, and applying gener...
We present Jina-VLM, a 2.4B parameter vision-language model that achieves state-of-the-art multilingual visual question answering among open 2B-scale VLMs. The ...
Generating high‑quality visuals with state‑of‑the‑art models is becoming increasingly accessible. Open‑source models run on laptops, and cloud services turn tex...
Attention mechanisms are the core of foundation models, but their quadratic complexity remains a critical bottleneck for scaling. This challenge has driven the ...
Sketches are simple human hand-drawn abstractions of complex scenes and real-world objects. Although the field of sketch representation learning has advanced si...
We propose MagicQuill V2, a novel system that introduces a layered composition paradigm to generative image editing, bridging the gap between the sema...
Multi-view diffusion models have recently emerged as a powerful paradigm for novel view synthesis, yet the underlying mechanism that enables their view-consiste...
Reinforcement learning (RL) has recently achieved remarkable success in eliciting visual reasoning within Multimodal Large Language Models (MLLMs). However, exi...
We introduce PPTArena, a benchmark for PowerPoint editing that measures reliable modifications to real slides under natural-language instructions. In contrast t...
