6 papers
Policy-based Tuning of Autoregressive Image Models with Instance- and Distribution-Level Rewards
Orhun Bugra Baran, Melih Kandemir, Ramazan Gokberk Cinbis
Autoregressive (AR) models are highly effective for image generation, yet their standard maximum-likelihood estimation training lacks direct optimization for sample quality and div…
Representation Recycling for Streaming Video Analysis
Can Ufuk Ertenli, Ramazan Gokberk Cinbis, Emre Akbas
We present StreamDEQ, a method that aims to infer frame-wise representations on videos with minimal per-frame computation. Conventional deep networks perform feature extraction fro…
LuMon: A Comprehensive Benchmark and Development Suite with Novel Datasets for Lunar Monocular Depth Estimation
Aytaç Sekmen, Fatih Emre Gunes, Furkan Horoz +9
Monocular Depth Estimation (MDE) is crucial for autonomous lunar rover navigation using electro-optical cameras. However, deploying terrestrial MDE networks to the Moon brings a se…
Meta-LoRA: Meta-Learning LoRA Components for Domain-Aware ID Personalization
BarıŠBatuhan Topal, Umut Ãzyurt, Zafer DoÄan Budak +1
Recent advancements in text-to-image generative models, particularly latent diffusion models (LDMs), have demonstrated remarkable capabilities in synthesizing high-quality images f…
Interchangeable Token Embeddings for Extendable Vocabulary and Alpha-Equivalence
Ä°lker IÅık, Ramazan Gokberk Cinbis, Ebru Aydin Gol
Language models lack the notion of interchangeable tokens: symbols that are semantically equivalent yet distinct, such as bound variables in formal logic. This limitation prevents…
Exploring Sparsity for Parameter Efficient Fine Tuning Using Wavelets for Vision
Ahmet Bilican, M. Akın Yılmaz, M. Akın Yılmaz +3
Efficiently adapting large pretrained models is critical under tight compute and memory budgets. While Parameter-Efficient Fine-Tuning (PEFT) methods like LoRA achieve efficiency t…