paper-with-me

Papers

LongProLIP: A Probabilistic Vision-Language Model with Long Context Text

2025-03-11 · Sanghyuk Chun, Sangdoo Yun

Recently, Probabilistic Language-Image Pre-Training (ProLIP) has been proposed to tackle the multiplicity issue of vision-language (VL) tasks. Despite their success in probabilistic representation learning at a scale, the ProLIP models cannot handle long context texts longer than 64 context length, which limits their ability to capture rich contextual information from longer text sequences. To address this issue, this paper proposes a fine-tuning strategy for ProLIP to accept longer texts, e.g., 256 text tokens. Experimental results on Urban-1k and the DataComp evaluation suite show that the proposed LongProLIP recipe can improve understanding of long contexts while minimizing the negative effect of fine-tuning.We also observe a trade-off between the long context understanding (measured by Urban-1k) and general zero-shot capability (measured by evaluation datasets by DataComp). Code is available at https://github.com/naver-ai/prolip

📄 PDF Abstract BibTeX arXiv:2503.08048

Code (1)

naver-ai/prolip 공식 구현 pytorch

Tasks

Language ModelingLanguage ModellingLong-Context UnderstandingRepresentation Learning

Similar Papers 제목 키워드 기반

PreSIST: Vision-Language-Informed Object Persistence Prediction in Open-World Scenes

2026-07-04 · Amanda Adkins, Tarunvidyut Ravisankar, Joydeep Biswas arxiv

Robots deployed over long periods must reason about environments that change over time. Existing long-term perception systems often address object change reactively, updating their maps only after revisiting a scene and …

MMLongBench: Benchmarking Long-Context Vision-Language Models Effectively and Thoroughly

2025-05-15 · Zhaowei Wang, Wenhao Yu, Xiyu Ren, Jipeng Zhang 외

The rapid extension of context windows in large vision-language models has given rise to long-context vision-language models (LCVLMs), which are capable of handling hundreds of images with interleaved text tokens in a si…

8kBenchmarkingRAG

Bayesian Attention Mechanism: A Probabilistic Framework for Positional Encoding and Context Length Extrapolation

2025-05-28 · Arthur S. Bianchessi, Rodrigo C. Barros, Lucas S. Kupssinskü

Transformer-based language models rely on positional encoding (PE) to handle token order and support context length extrapolation. However, existing PE methods lack theoretical clarity and rely on limited evaluation metr…

Information RetrievalRetrieval

How Much Information Can a Vision Token Hold? A Scaling Law for Recognition Limits in VLMs

2026-01-28 · Shuxin Zhuang, Zi Liang, Runsheng Yu, Hongzong Li 외 arxiv

Recent vision-centric approaches have made significant strides in long-context modeling. Represented by DeepSeek-OCR, these models encode rendered text into continuous vision tokens, achieving high compression rates with…

AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agents

2026-03-29 · Zhaopeng Feng, Liangcai Su, Zhen Zhang, Xinyu Wang 외 arxiv

As large language models (LLMs) evolve into autonomous agents for long-horizon information-seeking, managing finite context capacity has become a critical bottleneck. Existing context management methods typically commit …