← Search

weijia wu

17 accepted papers

2026

Learning to Parse and Reconstruct: Bidirectional Modeling of Question-to-Program Mapping

AAAI 2026technical

Neuro-symbolic learning has emerged as a promising paradigm for interpretable visual reasoning, where mapping natural language questions to executable programs plays a central role. However, most existing methods focus exclusively on the forward program generation from questions while overlooking th

Cited by 0SourcePDFScholar
2026

WEAVE: Unleashing and Benchmarking the In-context Interleaved Comprehension and Generation

CVPR 2026

Recent unified multimodal models (UMMs) have achieved remarkable progress in visual comprehension and generation. However, existing datasets and benchmarks focus predominantly on single-turn interactions, overlooking the multi-turn, context-dependent nature of real-world image creation and editing.

Cited by 0SourceScholar
2025

ChatGen: Automatic Text-to-Image Generation From FreeStyle Chatting

CVPR 2025poster

Despite the significant advancements in text-to-image (T2I) generative models, users often face a trial-and-error challenge in practical scenarios. This challenge arises from the complexity and uncertainty of tedious steps such as crafting suitable prompts, selecting appropriate models, and configur…

Cited by 1SourcePDFScholar
2025

MovieBench: A Hierarchical Movie Level Dataset for Long Video Generation

CVPR 2025poster

Recent advancements in video generation models, such as Stable Video Diffusion, have shown promising results, but these works primarily focus on short videos, often limited to a single scene and lacking a rich storyline. These models struggle with generating long videos that involve multiple scenes,…

2024

ControlCap: Controllable Region-level Captioning

ECCV 2024poster

"Region-level captioning is challenged by the caption degeneration issue, which refers to that pre-trained multimodal models tend to predict the most frequent captions but miss the less frequent ones. In this study, we propose a controllable region-level captioning (ControlCap) approach, which intro…

2024

DiverGen: Improving Instance Segmentation by Learning Wider Data Distribution with More Diverse Generative Data

CVPR 2024poster

Instance segmentation is data-hungry and as model capacity increases data scale becomes crucial for improving the accuracy. Most instance segmentation datasets today require costly manual annotation limiting their data scale. Models trained on such data are prone to overfitting on the training set e…

2024

Drag Anything: Motion Control for Anything using Entity Representation

ECCV 2024poster

"We introduce , which utilizes a entity representation to achieve motion control for any object in controllable video generation. Comparison to existing motion control methods, offers several advantages. Firstly, trajectory-based is more user-friendly for interaction, when acquiring other guidance s…

2024

EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models

ICLR 2024spotlight

Diffusion models have demonstrated remarkable capabilities in image synthesis and related generative tasks. Nevertheless, their practicality for low-latency real-world applications is constrained by substantial computational costs and latency issues. Quantization is a dominant way to compress and ac…

2024

MotionDirector: Motion Customization of Text-to-Video Diffusion Models

ECCV 2024oral

"Large-scale pre-trained diffusion models have exhibited remarkable capabilities in diverse video generations. Given a set of video clips of the same motion concept, the task of Motion Customization is to adapt existing text-to-video diffusion models to generate videos with this motion. Adaptation m…

2024

ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification

NeurIPS 2024poster

KV cache stores key and value states from previous tokens to avoid re-computation, yet it demands substantial storage space, especially for long sequences. Adaptive KV cache compression seeks to discern the saliency of tokens, preserving vital information while aggressively compressing those of l…

2023

BiViT: Extremely Compressed Binary Vision Transformers

ICCV 2023poster

Model binarization can significantly compress model size, reduce energy consumption, and accelerate inference through efficient bit-wise operations. Although binarizing convolutional neural networks have been extensively studied, there is little work on exploring binarization of vision Transformers…

Cited by 44PDFScholar
2023

DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models

NeurIPS 2023poster

Current deep networks are very data-hungry and benefit from training on large-scale datasets, which are often time-consuming to collect and annotate. By contrast, synthetic data can be generated infinitely using generative models such as DALL-E and diffusion models, with minimal effort and cost. In…

2023

DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models

ICCV 2023poster

Collecting and annotating images with pixel-wise labels is time-consuming and laborious. In contrast, synthetic data can be freely available using a generative model (e.g., DALL-E, Stable Diffusion). In this paper, we show that it is possible to automatically obtain accurate semantic masks of synthe…

Cited by 189PDFcodeScholar
2023

Generative Prompt Model for Weakly Supervised Object Localization

ICCV 2023poster

Weakly supervised object localization (WSOL) remains challenging when learning object localization models from image category labels. Conventional methods that discriminatively train activation models ignore representative yet less discriminative object parts. In this study, we propose a generative…

Cited by 37PDFcodeScholar
2023

Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models

NeurIPS 2023poster

Public large-scale text-to-image diffusion models, such as Stable Diffusion, have gained significant attention from the community. These models can be easily customized for new concepts using low-rank adaptations (LoRAs). However, the utilization of multiple-concept LoRAs to jointly support multipl…

Cited by 178SourcePDFScholar
2023

PTQD: Accurate Post-Training Quantization for Diffusion Models

NeurIPS 2023poster

Diffusion models have recently dominated image synthesis and other related generative tasks. However, the iterative denoising process is expensive in computations at inference time, making diffusion models less practical for low-latency and scalable real-world applications. Post-training quantizati…

2021

A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer

NeurIPS 2021poster

Most existing video text spotting benchmarks focus on evaluating a single language and scenario with limited data. In this work, we introduce a large-scale, Bilingual, Open World Video text benchmark dataset(BOVText). There are four features for BOVText. Firstly, we provide 1,850+ videos with more t…

Cited by 35SourcecodeScholar