Song Gao

5 papers · 2013–2025 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

+3 more ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Half 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (16) 🧭 Keyword Pioneer

👥 Mega-Team · Squad 📈 Trend Setter 🚀 Conference Pioneer

Venues

NeurIPS (2) CVPR (1) EMNLP (1) ICLR (1)

Top co-authors

Yu Su (3) Cheng-Hao Tu (2) Qianheng Zhang (2) Yifei Li (2) Vishal Dey (2) Zheda Mai (2) Vardaan Pahuja (2) Charles Stewart (2) Shijie Chen (2) Tanya Berger-Wolf (2)

Research topics

Artificial Intelligence (3) Machine Learning (3) Application Areas (3) Deep Learning (2) Natural Language Processing (2) Core AI (2) Resources & Methods (2) Computer Vision (1) Analysis (1) Core Methods (1) Domain-Specific (1) Learning Paradigms (1) Learning Types (1) Models (1) Techniques (1)

Keywords

scientific discovery (2) large language model (2) data-driven discovery (2) domain adaptation (2) benchmark evaluation (2) code generation (1) word recognition (1) classification accuracy (1) pre-trained model (1) conditional random field (1) scene text recognition (1) tree-structured model (1) language agent (1) logit calibration (1) automated dataset (1) character detection (1) automatic dataset creation (1) agent benchmarking (1) part-based character detection (1) partial label space (1)

Papers

AutoSDT: Scaling Data-Driven Discovery Tasks Toward Open Co-Scientists EMNLP 2025 ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery ICLR 2025 Fine-Tuning is Fine, if Calibrated NeurIPS 2024 Holistic Transfer: Towards Non-Disruptive Fine-Tuning with Partial Target Data NeurIPS 2023 Scene Text Recognition Using Part-Based Tree-Structured Character Detection CVPR 2013