Imagen de Portada

Does VLM Classification Benefit from LLM Description Semantics?

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ma, Pingchuan, Rietdorf, Lennart, Kotovenko, Dmytro, Hu, Vincent Tao, Ommer, Björn
Formato:	Preprint
Publicado:	2024
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

DepthFM: Fast Monocular Depth Estimation with Flow Matching
por: Gui, Ming, et al.
Publicado: (2024)

WaSt-3D: Wasserstein-2 Distance for Scene-to-Scene Stylization on 3D Gaussians
por: Kotovenko, Dmytro, et al.
Publicado: (2024)

Distillation of Diffusion Features for Semantic Correspondence
por: Fundel, Frank, et al.
Publicado: (2024)

[MASK] is All You Need
por: Hu, Vincent Tao, et al.
Publicado: (2024)

Diffusion Models and Representation Learning: A Survey
por: Fuest, Michael, et al.
Publicado: (2024)

MaskFlow: Discrete Flows For Flexible and Efficient Long Video Generation
por: Fuest, Michael, et al.
Publicado: (2025)

Boosting Latent Diffusion with Flow Matching
por: Schusterbauer, Johannes, et al.
Publicado: (2023)

Denoising, Fast and Slow: Difficulty-Aware Adaptive Sampling for Image Generation
por: Schusterbauer, Johannes, et al.
Publicado: (2026)

ActAlign: Zero-Shot Fine-Grained Video Classification via Language-Guided Sequence Alignment
por: Aghdam, Amir, et al.
Publicado: (2025)

ZigMa: A DiT-style Zigzag Mamba Diffusion Model
por: Hu, Vincent Tao, et al.
Publicado: (2024)

Unsupervised View-Invariant Human Posture Representation
por: Sardari, Faegheh, et al.
Publicado: (2021)

SCFlow: Implicitly Learning Style and Content Disentanglement with Flow Models
por: Ma, Pingchuan, et al.
Publicado: (2025)

Guiding Token-Sparse Diffusion Models
por: Krause, Felix, et al.
Publicado: (2026)

Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions
por: Baumann, Stefan Andreas, et al.
Publicado: (2024)

TREAD: Token Routing for Efficient Architecture-agnostic Diffusion Training
por: Krause, Felix, et al.
Publicado: (2025)

CAGE: Unsupervised Visual Composition and Animation for Controllable Video Generation
por: Davtyan, Aram, et al.
Publicado: (2024)

Scaling Image Tokenizers with Grouped Spherical Quantization
por: Wang, Jiangtao, et al.
Publicado: (2024)

What If : Understanding Motion Through Sparse Interactions
por: Baumann, Stefan Andreas, et al.
Publicado: (2025)

CoherentGS: Sparse Novel View Synthesis with Coherent 3D Gaussians
por: Paliwal, Avinash, et al.
Publicado: (2024)

TopoGaussian: Inferring Internal Topology Structures from Visual Clues
por: Xiong, Xiaoyu, et al.
Publicado: (2025)

Stable-Pose: Leveraging Transformers for Pose-Guided Text-to-Image Generation
por: Wang, Jiajun, et al.
Publicado: (2024)

Probabilistic Precipitation Nowcasting with Rectified Flow Transformers
por: Schusterbauer, Johannes, et al.
Publicado: (2026)

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment
por: Schusterbauer, Johannes, et al.
Publicado: (2025)

CleanDIFT: Diffusion Features without Noise
por: Stracke, Nick, et al.
Publicado: (2024)

EDGS: Eliminating Densification for Efficient Convergence of 3DGS
por: Kotovenko, Dmytro, et al.
Publicado: (2025)

TRANSPORTER: Transferring Visual Semantics from VLM Manifolds
por: Stergiou, Alexandros
Publicado: (2025)

PolarVLM: Bridging the Semantic-Physical Gap in Vision-Language Models
por: Li, Yuliang, et al.
Publicado: (2026)

CTRLorALTer: Conditional LoRAdapter for Efficient 0-Shot Control & Altering of T2I Models
por: Stracke, Nick, et al.
Publicado: (2024)

What Semantics Survive the Connector? Diagnosing VLM-to-DiT Alignment in Video Editing
por: Lin, Hangyu, et al.
Publicado: (2026)

When Does Pruning Benefit Vision Representations?
por: Cassano, Enrico, et al.
Publicado: (2025)

MGFFD-VLM: Multi-Granularity Prompt Learning for Face Forgery Detection with VLM
por: Chen, Tao, et al.
Publicado: (2025)

RayDer: Scalable Self-Supervised Novel View Synthesis from Real-World Video
por: Prestel, Ulrich, et al.
Publicado: (2026)

Analyzing VLM-Based Approaches for Anomaly Classification and Segmentation
por: Kakda, Mohit, et al.
Publicado: (2026)

Learning Long-term Motion Embeddings for Efficient Kinematics Generation
por: Stracke, Nick, et al.
Publicado: (2026)

Progressive Alignment with VLM-LLM Feature to Augment Defect Classification for the ASE Dataset
por: Hsu, Chih-Chung, et al.
Publicado: (2024)

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection
por: Bao, Wentao, et al.
Publicado: (2024)

Semantic Richness or Geometric Reasoning? The Fragility of VLM's Visual Invariance
por: Qiu, Jason, et al.
Publicado: (2026)

Adapting Self-Supervised Representations as a Latent Space for Efficient Generation
por: Gui, Ming, et al.
Publicado: (2025)

Can Better Text Semantics in Prompt Tuning Improve VLM Generalization?
por: Kuchibhotla, Hari Chandana, et al.
Publicado: (2024)

MUSE-VL: Modeling Unified VLM through Semantic Discrete Encoding
por: Xie, Rongchang, et al.
Publicado: (2024)