OptiSQL: Executable SQL Generation from Optical Tokens

2026-01-20 · Sifan Li, Hongkai Chen, Yujun Cai, Liyang Chen, Qingwen Ye, Yiwei Wang arxiv

Executable SQL generation is typically studied in text-to-SQL settings, where tables are provided as fully linearized textual schemas and contents. While effective, this formulation assumes access to structured text and incurs substantial token overhead, which is misaligned with many real-world scenarios where tables appear as visual artifacts in documents or webpages. We investigate whether compact optical representations can serve as an efficient interface for executable semantic parsing. We present OptiSQL, a vision-driven framework that generates executable SQL directly from table images and natural language questions using compact optical tokens. OptiSQL leverages an OCR-oriented visual encoder to compress table structure and content into a small set of optical tokens and fine-tunes a pretrained decoder for SQL generation while freezing the encoder to isolate representation sufficiency. Experiments on a visualized version of Spider 2.0-Snow show that OptiSQL retains strong execution accuracy while reducing table input tokens by an order of magnitude. Robustness analyses further demonstrate that optical tokens preserve essential structural information under visual perturbations.

📄 PDF Abstract BibTeX arXiv:2601.13695

Code (0)

등록된 구현이 없습니다.

Tasks

Semantic Parsing

Thinking with Drafting: Optical Decompression via Logical Reconstruction

2026-02-12 · Jingxuan Wei, Honghao He, Caijun Jia, Siyuan Li 외 arxiv

Existing multimodal large language models have achieved high-fidelity visual perception and exploratory visual generation. However, a precision paradox persists in complex reasoning tasks: optical perception systems tran…

Visual Reasoning

†DAGGER: Distractor-Aware Graph Generation for Executable Reasoning in Math Problems

2026-01-11 · Zabir Al Nazi, Shubhashis Roy Dipta, Sudipta Kar arxiv

Chain-of-Thought (CoT) prompting is widely adopted for mathematical problem solving, including in low-resource languages, yet its behavior under irrelevant context remains underexplored. To systematically study this chal…

Mathematical Reasoning Graph Generation

Hierarchical SVG Tokenization: Learning Compact Visual Programs for Scalable Vector Graphics Modeling

2026-04-06 · Ximing Xing, Ziteng Xue, Zhenxi Li, Weicong Liang 외 arxiv

Recent large language models have shifted SVG generation from differentiable rendering optimization to autoregressive program synthesis. However, existing approaches still rely on generic byte-level tokenization inherite…

Program Synthesis

From Resource Flow to Executable Tests: Petri-Net-Guided LLM Test Generation for Concurrent Stateful Rust APIs

2026-07-23 · Kaiwen Zhang, Guanjun Liu arxiv

Concurrent stateful library APIs expose behavior through evolving resource ownership, lifecycle states, and competing interleavings. Large language models can synthesize executable Rust tests, but their outputs often vio…

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

2026-04-10 · Dasen Dai, Shuoqi Li, Ronghao Chen, Huacan Wang 외 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 se…

Code Generation