12 citations · 13 across the 5 of their papers we have counts for
6 papers · 1 filter
WinARDet: Compressed Window Auto-Regression for Long-Horizon Vision-Language Grounding
Chenxu Wang, Hangyi Kuang, Bo-Wen Yin +6
MLLM-based detectors formulate vision-language grounding as autoregressive coordinate generation, yet in dense scenes, they often collapse into a box repetition loop, repeatedly em…
Accelerating Masked Image Generation by Learning Controlled Latent Dynamics
Kaiwen Zhu, Quansheng Zeng, Yuandong Pu +9
Masked Image Generation Models (MIGMs) have achieved great success, yet their efficiency is hampered by the multiple steps of bi-directional attention. In fact, there exists notabl…
A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models
Quan-Sheng Zeng, Yunheng Li, Qilong Wang +4
Visual token compression is critical for Large Vision-Language Models (LVLMs) to efficiently process high-resolution inputs. Existing methods that typically adopt fixed compression…
High-Quality Mask Tuning Matters for Open-Vocabulary Segmentation
Quan-Sheng Zeng, Yunheng Li, Daquan Zhou +3
Open-vocabulary image segmentation has been advanced through the synergy between mask generators and vision-language models like Contrastive Language-Image Pre-training (CLIP). Pre…
Unbiased Region-Language Alignment for Open-Vocabulary Dense Prediction
Yunheng Li, Yuxuan Li, Quansheng Zeng +3
Pre-trained vision-language models (VLMs), such as CLIP, have demonstrated impressive zero-shot recognition capability, but still underperform in dense prediction tasks. Self-disti…
Cascade-CLIP: Cascaded Vision-Language Embeddings Alignment for Zero-Shot Semantic Segmentation
Yunheng Li, ZhongYu Li, Quansheng Zeng +2
Pre-trained vision-language models, e.g., CLIP, have been successfully applied to zero-shot semantic segmentation. Existing CLIP-based approaches primarily utilize visual features…