Cover Image

Discrete JEPA: Learning Discrete Token Representations without Reconstruction

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Baek, Junyeob, Lee, Hosung, Hoang, Christopher, Ren, Mengye, Ahn, Sungjin
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Midway Network: Learning Representations for Recognition and Motion from Latent Dynamics
by: Hoang, Christopher, et al.
Published: (2025)

Dreamweaver: Learning Compositional World Models from Pixels
by: Baek, Junyeob, et al.
Published: (2025)

Slot-MLLM: Object-Centric Visual Tokenization for Multimodal LLM
by: Chi, Donghwan, et al.
Published: (2025)

Cubic Discrete Diffusion: Discrete Visual Generation on High-Dimensional Representation Tokens
by: Wang, Yuqing, et al.
Published: (2026)

On the Role of Discrete Tokenization in Visual Representation Learning
by: Du, Tianqi, et al.
Published: (2024)

Seeking the Unfamiliar but Memorable: Conceptual Creativity as Meta-Learning
by: Ren, Mengye
Published: (2026)

WeTok: Powerful Discrete Tokenization for High-Fidelity Visual Reconstruction
by: Zhuang, Shaobin, et al.
Published: (2025)

Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation
by: Wang, Yuqing, et al.
Published: (2025)

Le MuMo JEPA: Multi-Modal Self-Supervised Representation Learning with Learnable Fusion Tokens
by: Cornelissen, Ciem, et al.
Published: (2026)

Discretized Gaussian Representation for Tomographic Reconstruction
by: Wu, Shaokai, et al.
Published: (2024)

Learning to Theorize the World from Observation
by: Baek, Doojin, et al.
Published: (2026)

Memory Storyboard: Leveraging Temporal Segmentation for Streaming Self-Supervised Learning from Egocentric Videos
by: Yang, Yanlai, et al.
Published: (2025)

Organized Grouped Discrete Representation for Object-Centric Learning
by: Zhao, Rongzhen, et al.
Published: (2024)

Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning
by: Wang, Bohan, et al.
Published: (2025)

Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens
by: Pan, Kaihang, et al.
Published: (2025)

MergeTok: Unified Continuous and Discrete Visual Tokenization via Token Merging
by: Zhang, Luyuan, et al.
Published: (2026)

Beyond Single Tokens: Distilling Discrete Diffusion Models via Discrete MMD
by: Hoogeboom, Emiel, et al.
Published: (2026)

On the Adversarial Robustness of Discrete Image Tokenizers
by: Bhagwatkar, Rishika, et al.
Published: (2026)

An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learning
by: Yoon, Jaesik, et al.
Published: (2023)

Neural Discrete Representation Learning for Sparse-View CBCT Reconstruction: From Algorithm Design to Prospective Multicenter Clinical Evaluation
by: Wang, Haoshen, et al.
Published: (2025)

LongCat-Next: Lexicalizing Modalities as Discrete Tokens
by: Meituan LongCat Team, et al.
Published: (2026)

MambaVideo for Discrete Video Tokenization with Channel-Split Quantization
by: Argaw, Dawit Mureja, et al.
Published: (2025)

VAEVQ: Enhancing Discrete Visual Tokenization through Variational Modeling
by: Yang, Sicheng, et al.
Published: (2025)

Guidance Contrastive Token Credit Assignment for Discrete Policy Optimization
by: Li, Shufan, et al.
Published: (2026)

Neural Language of Thought Models
by: Wu, Yi-Fu, et al.
Published: (2024)

Grouped Discrete Representation for Object-Centric Learning
by: Zhao, Rongzhen, et al.
Published: (2024)

LGQ: Learning Discretization Geometry for Scalable and Stable Image Tokenization
by: Altun, Idil Bilge, et al.
Published: (2026)

PooDLe: Pooled and dense self-supervised learning from naturalistic videos
by: Wang, Alex N., et al.
Published: (2024)

Autoregressive Sign Language Production: A Gloss-Free Approach with Discrete Representations
by: Hwang, Eui Jun, et al.
Published: (2023)

Planning in 8 Tokens: A Compact Discrete Tokenizer for Latent World Model
by: Kim, Dongwon, et al.
Published: (2026)

ProCreate, Don't Reproduce! Propulsive Energy Diffusion for Creative Generation
by: Lu, Jack, et al.
Published: (2024)

SFTok: Bridging the Performance Gap in Discrete Tokenizers
by: Rao, Qihang, et al.
Published: (2025)

CODA: Repurposing Continuous VAEs for Discrete Tokenization
by: Liu, Zeyu, et al.
Published: (2025)

Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization
by: Jin, Yang, et al.
Published: (2023)

Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer
by: Gu, Chenyang, et al.
Published: (2026)

Learning to Compose: Improving Object Centric Learning by Injecting Compositionality
by: Jung, Whie, et al.
Published: (2024)

Information-Maximized Soft Variable Discretization for Self-Supervised Image Representation Learning
by: Niu, Chuang, et al.
Published: (2025)

Text-Conditional JEPA for Learning Semantically Rich Visual Representations
by: Huang, Chen, et al.
Published: (2026)

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis
by: Zheng, Peng, et al.
Published: (2025)

Wave-Particle (Continuous-Discrete) Dualistic Visual Tokenization for Unified Understanding and Generation
by: Chen, Yizhu, et al.
Published: (2025)