Imagen de Portada

Direct Ascent Synthesis: Revealing Hidden Generative Capabilities in Discriminative Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Fort, Stanislav, Whitaker, Jonathan
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

A Note on Implementation Errors in Recent Adaptive Attacks Against Multi-Resolution Self-Ensembles
por: Fort, Stanislav
Publicado: (2025)

Ensemble everything everywhere: Multi-scale aggregation for adversarial robustness
por: Fort, Stanislav, et al.
Publicado: (2024)

A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localization
por: Chen, Qiyu, et al.
Publicado: (2024)

Representations of Text and Images Align From Layer One
por: Wybitul, Evžen, et al.
Publicado: (2026)

Maximizing Discrimination Capability of Knowledge Distillation with Energy Function
por: Kim, Seonghak, et al.
Publicado: (2023)

Spatial-Frequency Discriminability for Revealing Adversarial Perturbations
por: Wang, Chao, et al.
Publicado: (2023)

Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator
por: Zheng, Kaiwen, et al.
Publicado: (2025)

Unlocking the Capabilities of Masked Generative Models for Image Synthesis via Self-Guidance
por: Hur, Jiwan, et al.
Publicado: (2024)

Generative Adversarial Synthesis and Deep Feature Discrimination of Brain Tumor MRI Images
por: Ali, Md Sumon, et al.
Publicado: (2025)

Map the Flow: Revealing Hidden Pathways of Information in VideoLLMs
por: Kim, Minji, et al.
Publicado: (2025)

Discriminator-Free Direct Preference Optimization for Video Diffusion
por: Cheng, Haoran, et al.
Publicado: (2025)

Leveraging Vision-Language Foundation Models to Reveal Hidden Image-Attribute Relationships in Medical Imaging
por: Kumar, Amar, et al.
Publicado: (2025)

Conservative Generator, Progressive Discriminator: Coordination of Adversaries in Few-shot Incremental Image Synthesis
por: Kong, Chaerin, et al.
Publicado: (2022)

Rethinking Fine-Tuning: Unlocking Hidden Capabilities in Vision-Language Models
por: Zhang, Mingyuan, et al.
Publicado: (2025)

Gait Recognition via Collaborating Discriminative and Generative Diffusion Models
por: Xiong, Haijun, et al.
Publicado: (2025)

Discriminative Image Generation with Diffusion Models for Zero-Shot Learning
por: Fu, Dingjie, et al.
Publicado: (2024)

Batch Transformer Architecture: Case of Synthetic Image Generation for Emotion Expression Facial Recognition
por: Selitskiy, Stanislav
Publicado: (2025)

Can Generative Geospatial Diffusion Models Excel as Discriminative Geospatial Foundation Models?
por: Jia, Yuru, et al.
Publicado: (2025)

The First to Know: How Token Distributions Reveal Hidden Knowledge in Large Vision-Language Models?
por: Zhao, Qinyu, et al.
Publicado: (2024)

Rethinking Domain Generalization: Discriminability and Generalizability
por: Long, Shaocong, et al.
Publicado: (2023)

DDAE++: Enhancing Diffusion Models Towards Unified Generative and Discriminative Learning
por: Xiang, Weilai, et al.
Publicado: (2025)

Bridging Generative and Discriminative Models for Unified Visual Perception with Diffusion Priors
por: Dong, Shiyin, et al.
Publicado: (2024)

RevealLayer: Disentangling Hidden and Visible Layers via Occlusion-Aware Image Decomposition
por: Wang, Binhao, et al.
Publicado: (2026)

Dynamically Masked Discriminator for Generative Adversarial Networks
por: Zhang, Wentian, et al.
Publicado: (2023)

Understanding-in-Generation: Reinforcing Generative Capability of Unified Model via Infusing Understanding into Generation
por: Lyu, Yuanhuiyi, et al.
Publicado: (2025)

Bridging Generative and Discriminative Noisy-Label Learning via Direction-Agnostic EM Formulation
por: Liu, Fengbei, et al.
Publicado: (2023)

Visual Anagrams Reveal Hidden Differences in Holistic Shape Processing Across Vision Models
por: Doshi, Fenil R., et al.
Publicado: (2025)

Direction-Flipped Influence Audits Reveal Hidden Structure in Moral Choices of LLMs
por: Blandfort, Phil, et al.
Publicado: (2026)

Spherical Dense Text-to-Image Synthesis
por: Winter, Timon, et al.
Publicado: (2025)

Revealing the Implicit Noise-based Imprint of Generative Models
por: Li, Xinghan, et al.
Publicado: (2025)

Exploiting Discriminative Codebook Prior for Autoregressive Image Generation
por: Tang, Longxiang, et al.
Publicado: (2025)

Few-shot Image Generation via Masked Discrimination
por: Zhu, Jingyuan, et al.
Publicado: (2022)

Bridging Degradation Discrimination and Generation for Universal Image Restoration
por: Hu, JiaKui, et al.
Publicado: (2026)

EgoInteract: Synthetic Egocentric Videos Generation for Interaction Understanding and Anticipation
por: Leonardi, Rosario, et al.
Publicado: (2026)

Revealing Directions for Text-guided 3D Face Editing
por: Chen, Zhuo, et al.
Publicado: (2024)

Unified Generative and Discriminative Training for Multi-modal Large Language Models
por: Chow, Wei, et al.
Publicado: (2024)

PurifyGen: A Risk-Discrimination and Semantic-Purification Model for Safe Text-to-Image Generation
por: Cao, Zongsheng, et al.
Publicado: (2025)

On Discriminative vs. Generative classifiers: Rethinking MLLMs for Action Understanding
por: Pang, Zhanzhong, et al.
Publicado: (2026)

Normalizing Flows are Capable Generative Models
por: Zhai, Shuangfei, et al.
Publicado: (2024)

Assessing the Geolocation Capabilities, Limitations and Societal Risks of Generative Vision-Language Models
por: Grainge, Oliver, et al.
Publicado: (2025)