paper-with-me

Papers

Discrete JEPA: Learning Discrete Token Representations without Reconstruction

2025-06-17 · Junyeob Baek, Hosung Lee, Christopher Hoang, Mengye Ren, Sungjin Ahn

The cornerstone of cognitive intelligence lies in extracting hidden patterns from observations and leveraging these principles to systematically predict future outcomes. However, current image tokenization methods demonstrate significant limitations in tasks requiring symbolic abstraction and logical reasoning capabilities essential for systematic inference. To address this challenge, we propose Discrete-JEPA, extending the latent predictive coding framework with semantic tokenization and novel complementary objectives to create robust tokenization for symbolic reasoning tasks. Discrete-JEPA dramatically outperforms baselines on visual symbolic prediction tasks, while striking visual evidence reveals the spontaneous emergence of deliberate systematic patterns within the learned semantic token space. Though an initial model, our approach promises a significant impact for advancing Symbolic world modeling and planning capabilities in artificial intelligence systems.

📄 PDF Abstract BibTeX arXiv:2506.14373

Code (0)

등록된 구현이 없습니다.

Tasks

Logical Reasoning

Similar Papers 제목 키워드 기반

Probing the Latent World: Emergent Discrete Symbols and Physical Structure in Latent Representations

2026-03-20 · Liu hung ming arxiv

Video world models trained with Joint Embedding Predictive Architectures (JEPA) acquire rich spatiotemporal representations by predicting masked regions in latent space rather than reconstructing pixels. This removes the…

JEPA-T: Joint-Embedding Predictive Architecture with Text Fusion for Image Generation

2025-10-01 · Siheng Wan, Zhengtao Yao, Zhengdao Li, Junhao Dong 외 arxiv

Modern Text-to-Image (T2I) generation increasingly relies on token-centric architectures that are trained with self-supervision, yet effectively fusing text with visual tokens remains a challenge. We propose \textbf{JEPA…

Image Generation

JEPA-Reasoner: Decoupling Latent Reasoning from Token Generation

2025-12-22 · Bingyang Kelvin Liu, Ziyu Patrick Chen, David P. Woodruff arxiv

Current autoregressive language models couple high-level reasoning and low-level token generation into a single sequential process, making the reasoning trajectory vulnerable to compounding expression errors. We propose …

UniJEPA: Enhancing Robot Policy via Unified Continuous and Discrete Representation Learning

2025-10-12 · Jianke Zhang, Yucheng Hu, Yanjiang Guo, Xiaoyu Chen 외 arxiv

Building generalist robot policies that can handle diverse tasks in open-ended environments is a central challenge in robotics. To leverage knowledge from large-scale pretraining, prior work (VLA) has typically built gen…

Representation Learning

OneVAE: Joint Discrete and Continuous Optimization Helps Discrete Video VAE Train Better

2025-08-13 · Yupeng Zhou, Zhen Li, Ziheng Ouyang, Yuming Chen 외 arxiv

Encoding videos into discrete tokens could align with text tokens to facilitate concise and unified multi-modal LLMs, yet introducing significant spatiotemporal compression compared to continuous video representation. Pr…