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.
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
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
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.
The paper introduces NAIMA, a guided depth super‑resolution framework that leverages global contextual semantic priors from pretrained vision transformer token embeddings. Its Guided Token Attention (GTA) module uses depth encodings as queries to attend over semantic tokens, with a zero‑initialized gate controlling the influence of semantic evidence. NAIMA achieves competitive in‑distribution performance while delivering superior cross‑dataset generalization without relying on decoded priors or auxiliary objectives.
By Tayyab Nasir, Daochang Liu, Ajmal Mian
The paper introduces DARTS, a method for tuning decoder representations during model merging. It addresses representation bias in autoregressive decoders by using an entropy‑weighted L1 loss and a per‑position additive bias to correct errors that accumulate across token positions. Experiments on code generation, mathematical reasoning, and instruction following with Llama‑2‑7B show that DARTS improves performance over standard surgery while adding only 0.1% extra parameters.
By Aaryan Ajay Sharma, Sai Nishanth Padala, Seganrasan Subramanian
arXiv:2605. 18848v3 Announce Type: replace Abstract: This paper introduces Exact Linear Attention (ELA), a mechanism that achieves linear computational complexity for Transformer attention by exploiting the exact decomposition property of kernel functions, thereby eliminating approximation error.
By Weinuo Ou
arXiv:2607. 16012v1 Announce Type: cross Abstract: Multi-Task Learning (MTL) in robotics perception systems supports comprehensive 3D spatial scene understanding by integrating semantic segmentation and depth estimation.
By Jehun Kang, Jungha Wang, Youngjun Hwang, David Hyunchul Shim
The paper introduces Action-Contrastive Masked Transition Modeling (AC‑MTM), a method that stabilizes Joint‑Embedding Predictive Architectures (JEPAs) without relying on Gaussian regularization. AC‑MTM adds a training‑only inverse‑dynamics head that uses Action‑NCE to force each latent transition to identify its generating action, thereby preventing encoder collapse. Experiments on pixel‑control and multi‑object visual tasks show that AC‑MTM trains stably from scratch and matches or surpasses the performance of SIGReg, achieving up to a 24‑point improvement on the OGBench Visual Scene benchmark.
arXiv:2606. 11576v1 Announce Type: cross Abstract: Modern Vision-Language Models (VLMs) benefit from chain-of-thought prompting and test-time scaling, but these gains often come with prohibitive inference cost due to large visual contexts and long decoding chains.
By Ahmadreza Jeddi, Minh Ngoc Le, Amirhossein Kazerouni, Hakki Can Karaimer, Hue Nguyen, Iqbal Mohomed, Michael Brudno, Alex Levinshtein, Konstantinos G. Derpanis, Babak Taati, Radek Grzeszczuk
arXiv:2606. 09936v1 Announce Type: cross Abstract: World models are now built on substantially different computational substrates.
By Bhavith Chandra Challagundla, Sanskar Pandey, Param Thakkar, Rishikesh Mallagundla, Yugandhar Reddy Gogireddy, Wenhao Lu, Hindol Roy Choudhury, Shravani Challagundla, Mohamed Deraz Nasr, Spursh Deshpande
arXiv:2606. 27449v1 Announce Type: new Abstract: Multi-head attention conventionally partitions the hidden dimension equally across all heads at every layer, enforcing an identical representational subspace dimension (dh = dmodel/h) throughout the models depth.
By Shubham Aggarwal