Oncel Tuzel

Computer Science · Physical Sciences

42h-index14.0kcitations149works7.92yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Neural Network Applications(32), Advanced Image and Video Retrieval Techniques(30), Advanced Vision and Imaging(24), Domain Adaptation and Few-Shot Learning(22), Multimodal Machine Learning Applications(18)

Publications149 total

The Design Space of Tri-Modal Masked Diffusion Models
arXiv (Cornell University)·2026Open Access
The Design Space of Tri-Modal Masked Diffusion Models
ArXiv.org·2026Open Access
AMUSE: Audio-Visual Benchmark and Alignment Framework for Agentic Multi-Speaker Understanding
arXiv (Cornell University)·2025Open Access
Learning from Self Critique and Refinement for Faithful LLM Summarization
arXiv (Cornell University)·2025Open Access
Learning to Reason for Hallucination Span Detection
arXiv (Cornell University)·2025Open Access
Pretraining with hierarchical memories: separating long-tail and common knowledge
arXiv (Cornell University)·2025Open Access
MobileCLIP2: Improving Multi-Modal Reinforced Training
arXiv (Cornell University)·2025Open Access
FastVLM: Efficient Vision Encoding for Vision Language Models
2025· 8 cited
Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting
arXiv (Cornell University)·2025Open Access
FocalLens: Instruction Tuning Enables Zero-Shot Conditional Image Representations
arXiv (Cornell University)·2025Open Access
TiC-LM: A Web-Scale Benchmark for Time-Continual LLM Pretraining
arXiv (Cornell University)·2025Open Access
Mutual Reinforcement of LLM Dialogue Synthesis and Summarization Capabilities for Few-Shot Dialogue Summarization
arXiv (Cornell University)·2025Open Access
Synth4Seg—Learning Defect Data Synthesis for Defect Segmentation Using Bi-Level Optimization
IEEE Transactions on Automation Science and Engineering·2025· 1 cited
Mutual Reinforcement of LLM Dialogue Synthesis and Summarization Capabilities for Few-Shot Dialogue Summarization
2025Open Access
TiC-LM: A Web-Scale Benchmark for Time-Continual LLM Pretraining
2025Open Access
3D Shape Tokenization via Latent Flow Matching
arXiv (Cornell University)·2024Open Access
FastVLM: Efficient Vision Encoding for Vision Language Models
arXiv (Cornell University)·2024· 1 citedOpen Access
Synth4Seg -- Learning Defect Data Synthesis for Defect Segmentation using Bi-level Optimization
arXiv (Cornell University)·2024Open Access
GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models
arXiv (Cornell University)·2024· 48 citedOpen Access
Novel-view Acoustic Synthesis From 3D Reconstructed Rooms
2024· 3 cited
page 1 of 8Next →

Frequent Co-authors

Fatih Porikli(12), Peter Meer(12), Ming-Yu Liu(10), Rama Chellappa(6), Anurag Ranjan(6), Tim K. Marks(4), Pavan Kumar Anasosalu Vasu(4), James Gabriel(4), Yuichi Taguchi(4), Ashok Veeraraghavan(4), Jeff Zhu(3), Mingyu Liu(3), Raviteja Vemulapalli(3), Lin Yang(3), David J. Foran(3), Yin Zhou(2), Srikumar Ramalingam(2), Abhishek Sharma(2), Jen-Hao Rick Chang(2), Mehrdad Farajtabar(2)