5 citations · 11 across the 15 of their papers we have counts for
14 papers · 1 filter
Intern Lumina U2: A Multi-Codebook Diffusion Large Language Model for Omni-Visual Understanding and Image Generation
Qian Yu, Zongyang Qiu, Juncheng Yan +40
Unified multimodal generation covers discrete, continuous, and hybrid paradigms. Discrete approaches with single-codebook visual tokenizers align naturally with text modeling but h…
EvoGUI: An Evolution-Aware Benchmark for GUI State-Transition Understanding
Yaohan Yang, Minglei Shi, Borui Zhang +2
GUI agents must reason about how actions transform interface states, but end-to-end success rates entangle this ability with perception, grounding, planning, and recovery. We intro…
BAMI: Training-Free Bias Mitigation in GUI Grounding
Borui Zhang, Bo Zhang, Bo Wang +6
GUI grounding is a critical capability for enabling GUI agents to execute tasks such as clicking and dragging. However, in complex scenarios like the ScreenSpot-Pro benchmark, exis…
AdaZoom-GUI: Adaptive Zoom-based GUI Grounding with Instruction Refinement
Siqi Pei, Liang Tang, Tiaonan Duan +9
GUI grounding is a critical capability for vision-language models (VLMs) that enables automated interaction with graphical user interfaces by locating target elements from natural…
SFTok: Bridging the Performance Gap in Discrete Tokenizers
Qihang Rao, Borui Zhang, Wenzhao Zheng +2
Recent advances in multimodal models highlight the pivotal role of image tokenization in high-resolution image generation. By compressing images into compact latent representations…
SVG-T2I: Scaling Up Text-to-Image Latent Diffusion Model Without Variational Autoencoder
Minglei Shi, Haolin Wang, Borui Zhang +11
Visual generation grounded in Visual Foundation Model (VFM) representations offers a highly promising unified pathway for integrating visual understanding, perception, and generati…
Quantize-then-Rectify: Efficient VQ-VAE Training
Borui Zhang, Qihang Rao, Wenzhao Zheng +2
Visual tokenizers are pivotal in multimodal large models, acting as bridges between continuous inputs and discrete tokens. Nevertheless, training high-compression-rate VQ-VAEs rema…
Preventing Local Pitfalls in Vector Quantization via Optimal Transport
Borui Zhang, Wenzhao Zheng, Jie Zhou +1
Vector-quantized networks (VQNs) have exhibited remarkable performance across various tasks, yet they are prone to training instability, which complicates the training process due…
Path Choice Matters for Clear Attribution in Path Methods
Borui Zhang, Wenzhao Zheng, Jie Zhou +1
Rigorousness and clarity are both essential for interpretations of DNNs to engender human trust. Path methods are commonly employed to generate rigorous attributions that satisfy t…
SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction
Yuanhui Huang, Wenzhao Zheng, Borui Zhang +2
3D occupancy prediction is an important task for the robustness of vision-centric autonomous driving, which aims to predict whether each point is occupied in the surrounding 3D spa…
OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving
Wenzhao Zheng, Weiliang Chen, Yuanhui Huang +3
Understanding how the 3D scene evolves is vital for making decisions in autonomous driving. Most existing methods achieve this by predicting the movements of object boxes, which ca…
Bort: Towards Explainable Neural Networks with Bounded Orthogonal Constraint
Borui Zhang, Wenzhao Zheng, Jie Zhou +1
Deep learning has revolutionized human society, yet the black-box nature of deep neural networks hinders further application to reliability-demanded industries. In the attempt to u…
Attributable Visual Similarity Learning
Borui Zhang, Wenzhao Zheng, Jie Zhou +1
This paper proposes an attributable visual similarity learning (AVSL) framework for a more accurate and explainable similarity measure between images. Most existing similarity lear…
Deep Relational Metric Learning
Wenzhao Zheng, Borui Zhang, Jiwen Lu +1
This paper presents a deep relational metric learning (DRML) framework for image clustering and retrieval. Most existing deep metric learning methods learn an embedding space with…