7 papers
TRIO: Token Reduction via Inference-Objective Guidance for Efficient Vision-Language Models
Haokui Zhang, Congyang Ou, Dawei Yan +5
Recently, reducing redundant visual tokens in vision-language models (VLMs) to accelerate VLM inference has emerged as a hot topic. However, most existing methods rely on heuristic…
CC-Pan: Channel-wise Compression based Diffusion for Efficient Pan-Sharpening
Junjie Li, Congyang Ou, Haokui Zhang +3
Recently, diffusion models have brought novel insights to pan-sharpening and notably boosted fusion precision. However, most existing models perform diffusion in the pixel space an…
Teaching Prompts to Coordinate: Hierarchical Layer-Grouped Prompt Tuning for Continual Learning
Shengqin Jiang, Tianqi Kong, Yuankai Qi +5
Prompt-based continual learning methods fine-tune only a small set of additional learnable parameters while keeping the pre-trained model's parameters frozen. It enables efficient…
M: Dual-Memory Augmentation for Long-Horizon Web Agents via Trajectory Summarization and Insight Retrieval
Dawei Yan, Haokui Zhang, Guangda Huzhang +8
Multimodal Large Language Models (MLLMs) based agents have demonstrated remarkable potential in autonomous web navigation. However, handling long-horizon tasks remains a critical b…
ProgRoCC: A Progressive Approach to Rough Crowd Counting
Shengqin Jiang, Linfei Li, Haokui Zhang +6
As the number of individuals in a crowd grows, enumeration-based techniques become increasingly infeasible and their estimates increasingly unreliable. We propose instead an estima…
MMCR: Advancing Visual Language Model in Multimodal Multi-Turn Contextual Reasoning
Dawei Yan, Yang Li, Qing-Guo Chen +4
Compared to single-turn dialogue, multi-turn dialogue involving multiple images better aligns with the needs of real-world human-AI interactions. Additionally, as training data, it…