Search Results - Timofte, Radu
-
1
MuDreamer: Learning Predictive World Models without Reconstruction
Published 2024Fuente: arXivTipo de material: PreprintAcceso al recurso -
2
Learning Transformer-based World Models with Contrastive Predictive Coding
Published 2025Fuente: arXivTipo de material: PreprintAcceso al recurso -
3
Learned Lightweight Smartphone ISP with Unpaired Data
Published 2025Fuente: arXivTipo de material: PreprintAcceso al recurso -
4
Higher fidelity perceptual image and video compression with a latent conditioned residual denoising diffusion model
Published 2025Fuente: arXivTipo de material: PreprintAcceso al recurso -
5
Practical Manipulation Model for Robust Deepfake Detection
Published 2025Fuente: arXivTipo de material: PreprintAcceso al recurso -
6
Accurate and Efficient World Modeling with Masked Latent Transformers
Published 2025Fuente: arXivTipo de material: PreprintAcceso al recurso -
7
Babel-ImageNet: Massively Multilingual Evaluation of Vision-and-Language Representations
Published 2023Fuente: arXivTipo de material: PreprintAcceso al recurso -
8
Virtually Enriched NYU Depth V2 Dataset for Monocular Depth Estimation: Do We Need Artificial Augmentation?
Published 2024Fuente: arXivTipo de material: PreprintAcceso al recurso -
9
Does Object Grounding Really Reduce Hallucination of Large Vision-Language Models?
Published 2024Fuente: arXivTipo de material: PreprintAcceso al recurso -
10
African or European Swallow? Benchmarking Large Vision-Language Models for Fine-Grained Object Classification
Published 2024Fuente: arXivTipo de material: PreprintAcceso al recurso -
11
Enhanced Super-Resolution Training via Mimicked Alignment for Real-World Scenes
Published 2024Fuente: arXivTipo de material: PreprintAcceso al recurso -
12
AdaptSR: Low-Rank Adaptation for Efficient and Scalable Real-World Super-Resolution
Published 2025Fuente: arXivTipo de material: PreprintAcceso al recurso -
13
AugmentGest: Can Random Data Cropping Augmentation Boost Gesture Recognition Performance?
Published 2025Fuente: arXivTipo de material: PreprintAcceso al recurso -
14
The Return of Structural Handwritten Mathematical Expression Recognition
Published 2025Fuente: arXivTipo de material: PreprintAcceso al recurso -
15
Cat: Post-Training Quantization Error Reduction via Cluster-based Affine Transformation
Published 2025Fuente: arXivTipo de material: PreprintAcceso al recurso -
16
UAIC_Twin_Width: An Exact yet Efficient Twin-Width Algorithm
Published 2025Fuente: arXivTipo de material: PreprintAcceso al recurso -
17
Preparation of Fractal-Inspired Computational Architectures for Advanced Large Language Model Analysis
Published 2025Fuente: arXivTipo de material: PreprintAcceso al recurso -
18
A Retrieval-Augmented Generation Approach to Extracting Algorithmic Logic from Neural Networks
Published 2025Fuente: arXivTipo de material: PreprintAcceso al recurso -
19
LLM as a Neural Architect: Controlled Generation of Image Captioning Models Under Strict API Contracts
Published 2025Fuente: arXivTipo de material: PreprintAcceso al recurso -
20
From Memorization to Creativity: LLM as a Designer of Novel Neural Architectures
Published 2026Fuente: arXivTipo de material: PreprintAcceso al recurso