18 papers
MM-Matryoshka: Towards Budget-Elastic Visual Document Retrieval via a 2D Multimodal Matryoshka Training Framework
Haowen Xiang, Yibo Yan, Jiahao Huo +4
Multi-vector visual document retrievers achieve strong fine-grained matching by representing each page with multiple vectors from deep Vision-Language Models (VLMs), but this desig…
StreamMeCo: Long-Term Agent Memory Compression for Efficient Streaming Video Understanding
Junxi Wang, Te Sun, Jiayi Zhu +6
Vision agent memory has shown remarkable effectiveness in streaming video understanding. However, storing such memory for videos incurs substantial memory overhead, leading to high…
AudioKV: KV Cache Eviction in Efficient Large Audio Language Models
Yuxuan Wang, Peize He, Xiyan Gui +6
Large Audio-Language Models (LALMs) have set new benchmarks in speech processing, yet their deployment is hindered by the memory footprint of the Key-Value (KV) cache during long-c…
Temporal Gains, Spatial Costs: Revisiting Video Fine-Tuning in Multimodal Large Language Models
Linghao Zhang, Jungang Li, Yonghua Hei +12
Multimodal large language models (MLLMs) are typically trained in multiple stages, with video-based supervised fine-tuning (Video-SFT) serving as a key step for improving visual un…
DRUPI: Dataset Reduction Using Privileged Information
Shaobo Wang, Youxin Jiang, Tianle Niu +9
Dataset Condensation (DC) seeks to select or distill samples from large datasets into smaller subsets while preserving performance on target tasks. Existing methods primarily focus…
StruVis: Enhancing Reasoning-based Text-to-Image Generation via Thinking with Structured Vision
Yuanhuiyi Lyu, Kaiyu Lei, Ziqiao Weng +7
Reasoning-based text-to-image (T2I) generation requires models to interpret complex prompts accurately. Existing reasoning frameworks can be broadly categorized into two types: (1)…