Jianyang Gu
Computer Science · The Ohio State University
Publications
77
Citations
487
Est. group size
—
Recurring co-author estimate
Active years
8
Publishing since 2019
Jianyang Gu works in computer vision and machine learning, with a focus on dataset distillation (methods for compressing large training datasets into smaller, more efficient ones), fine-grained image recognition, and multimodal models that combine vision and language. Recent work also explores biological and ecological applications, such as species recognition from images and hierarchical classification across the tree of life. This research is well suited for students interested in efficient training methods, generative models, and applying vision-language AI to scientific domains like biodiversity monitoring.
Publication output has grown substantially over the last decade, rising from a handful of papers in 2019-2021 to double-digit annual counts since 2022, with the highest activity in 2025-2026.
Generated by claude-sonnet-5 from public bibliographic data · Jul 20, 2026
- HIERAMP: Coarse-to-Fine Autoregressive Amplification for Generative Dataset Distillation
Open MIND · 2026
- HIERAMP: Coarse-to-Fine Autoregressive Amplification for Generative Dataset Distillation
arXiv (Cornell University) · 2026
- AVION: Aerial Vision-Language Instruction from Offline Teacher to Prompt-Tuned Network
arXiv (Cornell University) · 2026
- AVION: Aerial Vision-Language Instruction from Offline Teacher to Prompt-Tuned Network
arXiv (Cornell University) · 2026
- Lessons and Open Questions from a Unified Study of Camera-Trap Species Recognition Over Time
arXiv (Cornell University) · 2026
- BioCLIP 2: Emergent Properties from Scaling Hierarchical Contrastive Learning
Zenodo (CERN European Organization for Nuclear Research) · 2026
- TaxaAdapter: Vision Taxonomy Models are Key to Fine-grained Image Generation over the Tree of Life
arXiv (Cornell University) · 2026
- BioCLIP 2: Emergent Properties from Scaling Hierarchical Contrastive Learning
Zenodo (CERN European Organization for Nuclear Research) · 2026
- TaxaAdapter: Vision Taxonomy Models are Key to Fine-grained Image Generation over the Tree of Life
arXiv (Cornell University) · 2026
- Concord: Concept-Informed Diffusion for Dataset Distillation
2026
- Leveraging Latent Visual Reasoning in Silence
arXiv (Cornell University) · 2026
- Leveraging Latent Visual Reasoning in Silence
arXiv (Cornell University) · 2026
- Better with Experience: Self-Evolving LLM Agents for Evidence-Grounded Health Community Notes
arXiv (Cornell University) · 2026
- Better with Experience: Self-Evolving LLM Agents for Evidence-Grounded Health Community Notes
arXiv (Cornell University) · 2026
- Lost at the End: Primacy Bias in Multimodal Retrieval-Augmented Question Answering
arXiv (Cornell University) · 2026
- arXiv (Cornell University)×46
- Lecture notes in computer science×2
- Zenodo (CERN European Organization for Nuclear Research)×2
- IEEE Transactions on Intelligent Transportation Systems×1
- IEEE Transactions on Information Forensics and Security×1
- Zijian He
Computer Science · Purdue University West Lafayette
- Xiangyu Zhang
Computer Science · Purdue University West Lafayette
- Peter Jin
Computer Science · Purdue University West Lafayette
- Tai-Yu Pan
Computer Science · The Ohio State University
- Shujon Naha
Computer Science · Indiana University
This profile was generated automatically from public scholarly data (OpenAlex). Group size and activity levels are estimates derived from co-authorship patterns.
Last updated Jul 19, 2026.
Claim or correct this profile