3 citations · 4 across the 8 of their papers we have counts for
11 papers
Game2Real-Bench: Do Toy Games Reveal and Transfer to Real-World Visual Reasoning?
Qingan Liu, Juntong Feng, Yue Zhu +6
Visual reasoning is an important capability for vision-language models (VLMs) to understand visual evidence, spatial structure, constraints, and state changes. Existing evaluations…
ERA: Entropy-Guided Visual Token Pruning with Rectified Attention for Efficient MLLMs
Yuhao Wang, Mu Qiao, Haiwen Diao +5
Multimodal Large Language Models (MLLMs) incur prohibitive inference costs due to long visual token sequences. Training-free visual token reduction provides an efficient solution.…
From Pixels to Words -- Towards Native One-Vision Models at Scale
Haiwen Diao, Jiahao Wang, Penghao Wu +18
Current vision-language models (VLMs) typically stitch together separate image encoders and language decoders via multi-stage alignment, a modular framework that inevitably fragmen…
VISTA-Bench: Do Vision-Language Models Really Understand Visualized Text as Well as Pure Text?
Qing'an Liu, Juntong Feng, Yuhao Wang +6
Vision-Language Models (VLMs) have achieved impressive performance in cross-modal understanding across textual and visual inputs, yet existing benchmarks predominantly focus on pur…
End-to-End Vision Tokenizer Tuning
Wenxuan Wang, Fan Zhang, Yufeng Cui +5
Existing vision tokenization isolates the optimization of vision tokenizers from downstream training, implicitly assuming the visual tokens can generalize well across various tasks…
KARST: Multi-Kernel Kronecker Adaptation with Re-Scaling Transmission for Visual Classification
Yue Zhu, Haiwen Diao, Shang Gao +2
Fine-tuning pre-trained vision models for specific tasks is a common practice in computer vision. However, this process becomes more expensive as models grow larger. Recently, para…
EVEv2: Improved Baselines for Encoder-Free Vision-Language Models
Haiwen Diao, Xiaotong Li, Yufeng Cui +6
Existing encoder-free vision-language models (VLMs) are rapidly narrowing the performance gap with their encoder-based counterparts, highlighting the promising potential for unifie…
Autoregressive Video Generation without Vector Quantization
Haoge Deng, Ting Pan, Haiwen Diao +6
This paper presents a novel approach that enables autoregressive video generation with high efficiency. We propose to reformulate the video generation problem as a non-quantized au…
GSSF: Generalized Structural Sparse Function for Deep Cross-modal Metric Learning
Haiwen Diao, Ying Zhang, Shang Gao +3
Cross-modal metric learning is a prominent research topic that bridges the semantic heterogeneity between vision and language. Existing methods frequently utilize simple cosine or…
SHERL: Synthesizing High Accuracy and Efficient Memory for Resource-Limited Transfer Learning
Haiwen Diao, Bo Wan, Xu Jia +4
Parameter-efficient transfer learning (PETL) has emerged as a flourishing research field for adapting large pre-trained models to downstream tasks, greatly reducing trainable param…
Unveiling Encoder-Free Vision-Language Models
Haiwen Diao, Yufeng Cui, Xiaotong Li +3
Existing vision-language models (VLMs) mostly rely on vision encoders to extract visual features followed by large language models (LLMs) for visual-language tasks. However, the vi…