Oncel Tuzel

AMusE: Audio-Visual Benchmark and Alignment Framework for Agentic Multi-Speaker Understanding CVPR 2026 Beyond a Single Extractor: Re-thinking HTML-to-Text Extraction for LLM Pre-training EACL 2026 TrajTok: Learning Trajectory Tokens Enhances Video Understanding CVPR 2026 Velox: Learning Representations of 4D Geometry and Appearance CVPR 2026 FastVLM: Efficient Vision Encoding for Vision Language Models CVPR 2025 GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models ICLR 2025 Mutual Reinforcement of LLM Dialogue Synthesis and Summarization Capabilities for Few-Shot Dialogue Summarization NAACL 2025 Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting ICML 2025 TiC-LM: A Web-Scale Benchmark for Time-Continual LLM Pretraining ACL 2025 Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum NeurIPS 2024 HUGS: Human Gaussian Splats CVPR 2024 Knowledge Transfer from Vision Foundation Models for Efficient Training of Small Task-specific Models ICML 2024 MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training CVPR 2024 MUSCLE: A Model Update Strategy for Compatible LLM Evolution EMNLP 2024 Novel-view Acoustic Synthesis From 3D Reconstructed Rooms Interspeech 2024 Probabilistic Speech-Driven 3D Facial Motion Synthesis: New Benchmarks Methods and Applications CVPR 2024 ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models ICLR 2024 TiC-CLIP: Continual Training of CLIP Models ICLR 2024 FaceLit: Neural 3D Relightable Faces CVPR 2023 FastFill: Efficient Compatible Model Update ICLR 2023 FastViT: A Fast Hybrid Vision Transformer Using Structural Reparameterization ICCV 2023 MobileOne: An Improved One Millisecond Mobile Backbone CVPR 2023 Pointersect: Neural Rendering With Cloud-Ray Intersection CVPR 2023 Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Reinforcement ICCV 2023 Token Pooling in Vision Transformers for Image Classification WACV 2023 Forward Compatible Training for Large-Scale Embedding Retrieval Systems CVPR 2022 NeuMan: Neural Human Radiance Field from a Single Video ECCV 2022 Style Equalization: Unsupervised Learning of Controllable Generative Sequence Models ICML 2022 Data Parameters: A New Family of Parameters for Learning a Differentiable Curriculum NeurIPS 2019 VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection CVPR 2018 Learning From Simulated and Unsupervised Images Through Adversarial Training CVPR 2017 A Multi-Stream Bi-Directional Recurrent Neural Network for Fine-Grained Action Detection CVPR 2016 Coupled Generative Adversarial Networks NeurIPS 2016 Deep Gaussian Conditional Random Field Network: A Model-Based Deep Network for Discriminative Denoising CVPR 2016 Gaussian Conditional Random Field Network for Semantic Segmentation CVPR 2016 Deep Hierarchical Parsing for Semantic Segmentation CVPR 2015 Layered Interpretation of Street View Images RSS 2015 Recursive Context Propagation Network for Semantic Scene Labeling NeurIPS 2014 Joint Geodesic Upsampling of Depth Images CVPR 2013