4 citations · 9 across the 9 of their papers we have counts for
10 papers
Efficient Text-to-Image Generation: An Adaptive Step Schedule Controller for Diffusion Models
Kuluhan Binici, Cihan Acar, Shivam Aggarwal +2
Text-to-image diffusion models often use a fixed number of denoising steps, balancing time costs and image quality. However, the optimal number of steps depends on the complexity o…
Visual Attention Faithfulness in Vision-Language Models is Heterogeneous
Xurui Song, Weishi Wang, Zhongqi Yue +5
Whether attention weights faithfully reflect model reasoning has been actively debated in NLP, yet this question remains largely unexplored for the visual modality in Vision-Langua…
MEDSAGE: Enhancing Robustness of Medical Dialogue Summarization to ASR Errors with LLM-generated Synthetic Dialogues
Kuluhan Binici, Abhinav Ramesh Kashyap, Viktor Schlegel +6
Automatic Speech Recognition (ASR) systems are pivotal in transcribing speech into text, yet the errors they introduce can significantly degrade the performance of downstream tasks…
Condensed Data Expansion Using Model Inversion for Knowledge Distillation
Kuluhan Binici, Shivam Aggarwal, Cihan Acar +4
Condensed datasets offer a compact representation of larger datasets, but training models directly on them or using them to enhance model performance through knowledge distillation…
LLMs are not Zero-Shot Reasoners for Biomedical Information Extraction
Aishik Nagar, Viktor Schlegel, Thanh-Tung Nguyen +4
Large Language Models (LLMs) are increasingly adopted for applications in healthcare, reaching the performance of domain experts on tasks such as question answering and document su…
Generalizing Teacher Networks for Effective Knowledge Distillation Across Student Architectures
Kuluhan Binici, Weiming Wu, Tulika Mitra
Knowledge distillation (KD) is a model compression method that entails training a compact student model to emulate the performance of a more complex teacher model. However, the arc…
CRISP: Hybrid Structured Sparsity for Class-aware Model Pruning
Shivam Aggarwal, Kuluhan Binici, Tulika Mitra
Machine learning pipelines for classification tasks often train a universal model to achieve accuracy across a broad range of classes. However, a typical user encounters only a lim…
Visual-Policy Learning through Multi-Camera View to Single-Camera View Knowledge Distillation for Robot Manipulation Tasks
Cihan Acar, Kuluhan Binici, Alp Tekirdağ +1
The use of multi-camera views simultaneously has been shown to improve the generalization capabilities and performance of visual policies. However, the hardware cost and design con…
Robust and Resource-Efficient Data-Free Knowledge Distillation by Generative Pseudo Replay
Kuluhan Binici, Shivam Aggarwal, Nam Trung Pham +2
Data-Free Knowledge Distillation (KD) allows knowledge transfer from a trained neural network (teacher) to a more compact one (student) in the absence of original training data. Ex…
Preventing Catastrophic Forgetting and Distribution Mismatch in Knowledge Distillation via Synthetic Data
Kuluhan Binici, Nam Trung Pham, Tulika Mitra +1
With the increasing popularity of deep learning on edge devices, compressing large neural networks to meet the hardware requirements of resource-constrained devices became a signif…