🏢 Hong Kong University of Science and Technology

GaussianAvatar-Editor enables photorealistic, text-driven editing of animatable 3D heads, solving motion occlusion and ensuring temporal consistency.

Diffusion as Shader (DaS) achieves versatile video control by using 3D tracking videos as control signals in a unified video diffusion model, enabling precise manipulation across diverse tasks.

TransPixar generates high-quality videos with transparency by jointly training RGB and alpha channels, outperforming sequential generation methods.

VideoAnydoor: High-fidelity video object insertion with precise motion control, achieved via an end-to-end framework leveraging an ID extractor and a pixel warper for robust detail preservation and fi…

Android Agent Arena (A3): A novel evaluation platform for mobile GUI agents offering diverse tasks, flexible action space, and automated LLM-based evaluation, advancing real-world AI agent research.

Edicho: a novel training-free method for consistent image editing across diverse images, achieving precise consistency by leveraging explicit correspondence.

M-STAR: a novel self-evolving training framework significantly boosts multimodal reasoning in large models without human annotation, achieving state-of-the-art results.

B-STAR dynamically balances exploration and exploitation in self-taught reasoners, achieving superior performance in mathematical, coding, and commonsense reasoning tasks.

MegaPairs synthesizes 26M+ high-quality multimodal retrieval training examples, enabling state-of-the-art zero-shot performance and surpassing existing methods trained on 70x more data.

LeviTor: Revolutionizing image-to-video synthesis with intuitive 3D trajectory control, generating realistic videos from static images by abstracting object masks into depth-aware control points.

Enhance image captions significantly with DCE, a novel engine leveraging visual specialists to generate comprehensive, detailed descriptions surpassing LMM and human-annotated captions.

AniDoc automates cartoon animation line art video colorization, making animation creation easier!

Training-free method adds physical properties to 3D models using vision-language models.

Lyra: An efficient, speech-centric framework for omni-cognition, achieving state-of-the-art results across various modalities while being highly efficient.

VideoGen-of-Thought (VGoT) creates high-quality, multi-shot videos by collaboratively generating scripts, keyframes, and video clips, ensuring narrative consistency and visual coherence.

OmniCreator: Self-supervised unified image+video generation & universal editing.

MagicDriveDiT generates high-resolution, long street-view videos with precise control, exceeding limitations of previous methods in autonomous driving.

Golden Touchstone, a new bilingual benchmark, comprehensively evaluates financial LLMs across eight tasks, revealing model strengths and weaknesses and advancing FinLLM research.