arXiv AI August 28, 2026 By Frederik Berenz

Successive Capacity Growth: Task-Complexity-Driven Width and Depth Expansion for Vision Transformer Encoders in JEPA World Models

The paper introduces Successive Capacity Growth (SCG), a method for adaptively expanding Vision Transformer encoders in Joint-Embedding Predictive Architectures (JEPAs). SCG starts with a minimal encoder and incrementally increases width or depth based on a task‑agnostic test‑and‑verify mechanism, while a Sketched Isotropic Gaussian Regularizer (SIGReg) keeps learned semantic dimensions independent. Experiments on multi‑object dynamics and 2D navigation tasks show that SCG achieves up to 20.3% better prediction loss than fixed small baselines and 23% better than fixed large models, with far greater parameter efficiency and no false‑positive expansions.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Hugging Face Trending Papers

Aug 27

Successive Capacity Growth: Task-Complexity-Driven Width and Depth Expansion for Vision Transformer Encoders in JEPA World Models

The paper introduces Successive Capacity Growth (SCG), a method that starts with a minimal Vision Transformer encoder and incrementally expands its width or depth based on a task‑agnostic test‑and‑verify mechanism. SCG uses function‑preserving expansion and a Sketched Isotropic Gaussian Regularizer (SIGReg) to ensure independent semantic dimensions and prevent collapse. Experiments on multi‑object dynamics and 2D navigation tasks show that SCG achieves significant prediction loss reductions while being far more parameter‑efficient than fixed large models, with no false‑positive expansions and exact function preservation.

llms rag computer-vision

arXiv Machine Learning

Jul 21

Depth-Regularized JEPA World Models Learn More Transferable Representations from Real Outdoor Robot Data

arXiv:2607. 16314v1 Announce Type: cross Abstract: World models, especially based on JEPA architectures, have been shown to learn robust dynamics of various environments.

By Usman M. Khan

robotics benchmarks

arXiv Computer Vision

Oct 2

Do Vision Transformers Need All-to-All Attention? Global Communication Through Elastic Learned Cores

arXiv:2605.12491v2 Announce Type: replace Abstract: Vision Transformers (ViTs) learn rich visual-semantic representations through all-to-all self-attention among patch tokens. However, this design im...

By Alan Z. Song, Yinjie Chen, Mu Nan, Deva Ramanan, Michael J. Tarr, Andrew F. Luo

llms computer-vision benchmarks

arXiv AI

Jun 16

Scaling Adaptive Depth with Norm-Agnostic Residual Networks

arXiv:2606. 16112v1 Announce Type: cross Abstract: Residual architectures are ubiquitous in deep learning, but they suffer from a subtle structural limitation: the norm of the residual stream can grow rapidly with depth.

By Tom\'as Figliolia, Beren Millidge

llms efficiency

Hugging Face Trending Papers

Jul 27

MAViE: A Multi-scale Adaptive Vision Encoder for Fine-grained Visual Perception and Efficient Multimodal Reasoning

Vision-language models commonly project all tokens produced by a pretrained vision encoder into a large language model. However, final-layer features can discard text, local attributes, and spatial relationships, while high-resolution inputs substantially increase context length and inference latency.

llms computer-vision efficiency multimodal benchmarks

arXiv Computer Vision

Sep 22

VGGT-Prime: Compute-Adaptive Mixture-of-Heads for Efficient Visual Geometry Transformers

arXiv:2609.23733v1 Announce Type: new Abstract: Feed-forward visual geometry models such as the Visual Geometry Grounded Transformer (VGGT) have recently enabled direct 3D reconstruction from multi-v...

By Abteen Arab, Guile Wu, Chengjie Huang, Dongfeng Bai

llms efficiency

One email a morning, machine-written

Related stories

Successive Capacity Growth: Task-Complexity-Driven Width and Depth Expansion for Vision Transformer Encoders in JEPA World Models

Depth-Regularized JEPA World Models Learn More Transferable Representations from Real Outdoor Robot Data

Do Vision Transformers Need All-to-All Attention? Global Communication Through Elastic Learned Cores

Scaling Adaptive Depth with Norm-Agnostic Residual Networks

MAViE: A Multi-scale Adaptive Vision Encoder for Fine-grained Visual Perception and Efficient Multimodal Reasoning

VGGT-Prime: Compute-Adaptive Mixture-of-Heads for Efficient Visual Geometry Transformers