paper-with-me

홈 › Papers

UIPress: Bringing Optical Token Compression to UI-to-Code Generation

2026-04-10 · Dasen Dai, Shuoqi Li, Ronghao Chen, Huacan Wang, Biao Wu, Qizhen Lan arxiv

UI-to-Code generation requires vision-language models (VLMs) to produce thousands of tokens of structured HTML/CSS from a single screenshot, making visual token efficiency critical. Existing compression methods either select tokens at inference time using task-agnostic heuristics, or zero out low-attention features without actually shortening the sequence -- neither truly reduces prefill latency or adapts to the non-uniform information density of UI screenshots. Meanwhile, optical (encoder-side learned) compression has shown strong results for document OCR, yet no prior work has adapted this paradigm to UI-to-Code generation. We propose UIPress, a lightweight learned compression module inserted between the frozen ViT encoder and the LLM decoder of Qwen3-VL-8B. UIPress combines depthwise-separable convolutions, element-guided spatial reweighting, and Transformer refinement to compress ${\sim}$6{,}700 visual tokens to a fixed budget of 256. Together with Low-Rank Adaptation (LoRA) on the decoder to bridge the representation gap, the entire system adds only ${\sim}$21.7M trainable parameters (0.26\% of the 8B base model). Under a fair comparison on the same base model against four baselines on Design2Code, UIPress at 256 tokens achieves a CLIP score of 0.8127, outperforming the uncompressed baseline by +7.5\% and the strongest inference-time method by +4.6\%, while delivering 9.1$\times$ time-to-first-token speedup. To the best of our knowledge, UIPress is the first encoder-side learned compression method for the UI-to-Code task.

📄 PDF Abstract BibTeX arXiv:2604.09442

Code (0)

등록된 구현이 없습니다.

Tasks

Code Generation

Similar Papers 제목 키워드 기반

Context Cascade Compression: Exploring the Upper Limits of Text Compression

2025-11-19 · Fanfan Liu, Haibo Qiu arxiv

Million-level token inputs in long-context tasks pose significant computational and memory challenges for Large Language Models (LLMs). Recently, DeepSeek-OCR conducted research into the feasibility of Contexts Optical C…

DeepSeek-OCR: Contexts Optical Compression

2025-10-21 · Haoran Wei, Yaofeng Sun, Yukun Li arxiv

We present DeepSeek-OCR as an initial investigation into the feasibility of compressing long contexts via optical 2D mapping. DeepSeek-OCR consists of two components: DeepEncoder and DeepSeek3B-MoE-A570M as the decoder. …

AgentOCR: Reimagining Agent History via Optical Self-Compression

2026-01-08 · Lang Feng, Fuchao Yang, Feng Chen, Xin Cheng 외 arxiv

Recent advances in large language models (LLMs) enable agentic systems trained with reinforcement learning (RL) over multi-turn interaction, but practical deployment is bottlenecked by rapidly growing textual histories t…

Reinforcement Learning

Optical Context Compression Is Just (Bad) Autoencoding

2025-12-03 · Ivan Yee Lee, Cheng Yang, Taylor Berg-Kirkpatrick arxiv

DeepSeek-OCR shows that rendered text can be reconstructed from a small number of vision tokens, sparking excitement about using vision as a compression medium for long textual contexts. But this pipeline requires render…

Rethinking Genomic Modeling Through Optical Character Recognition

2026-02-02 · Hongxin Xiang, Pengsen Ma, Yunkang Cao, Di Yu 외 arxiv

Recent genomic foundation models largely adopt large language model architectures that treat DNA as a one-dimensional token sequence. However, exhaustive sequential reading is structurally misaligned with sparse and disc…