The paper introduces a Mixture‑Gated Theory of Anisotropic Representation Dynamics that decomposes Transformer self‑attention into value transport, query gating, and key gating. It shows that the geometry of attended representations can cause a representation difference to contract or expand, a phenomenon termed gating‑induced regime switching. The authors derive a spectral criterion to predict switching, quantify its strength, and identify subspaces where switching occurs, validating these predictions experimentally across four Transformer architectures.
By Nguyen Do, My T. Thai
arXiv:2607. 00434v1 Announce Type: cross Abstract: Vision-language models (VLMs) have become a paradigm for multimodal learning, yet remain unstable due to object hallucination, weak visual grounding, and catastrophic forgetting after full-parameter instruction tuning.
By Guohao Sun, Xiaofang Wang, Yash Patel, Mengchen Liu, Zhiqiang Tao, Praveen Krishnan
arXiv:2601.11618v4 Announce Type: replace-cross
Abstract: An operation's input-output function does not, by itself, determine its computational role within a represented process. That role also depen...
By Luis F. Rosario Freytes
arXiv:2607. 11990v1 Announce Type: cross Abstract: Feedforward network (FFN) blocks account for a large fraction of the parameters and computation in Transformer architectures, yet their internal structure remains difficult to interpret due to the additive superposition induced by the residual stream.
By Johannes Knittel, Hanspeter Pfister
The paper investigates how diffusion transformers (DiTs) denoise images by framing them as aggregator–predictor models that use context aggregation and patch prediction. It shows that for Gaussian Markov random field priors, a global Bayes denoiser can be approximated with a limited context, and that patchwise linear denoisers recover empirical local denoisers when aggregation is informative. Experiments confirm that DiTs trained on real images exhibit noise‑dependent denoising contexts and that replacing DiT MLPs with shared‑memory patch predictors yields competitive performance, while cross‑dataset component transplantation supports the proposed functional roles of attention and MLPs.
By Gyeonghun Kang, William Xingxu Chen, Xiang Cheng
arXiv:2501. 18322v2 Announce Type: replace Abstract: Transformers, which are state-of-the-art in most machine learning tasks, represent the data as sequences of vectors called tokens.
By Val\'erie Castin, Pierre Ablin, Jos\'e Antonio Carrillo, Gabriel Peyr\'e
arXiv:2606. 10324v1 Announce Type: new Abstract: The analogy between deep neural network forward passes and renormalization group (RG) flows has been repeatedly noted in the literature, but existing treatments remain qualitative: depth is described as a coarse-graining scale, attention is likened to a partition function, and representations are said to flow toward fixed points.
By Parviz Haggi-Mani, Irina Rish
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
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
The paper investigates why Diffusion Transformers perform well when predicting clean data but poorly when predicting noise or velocity. It introduces the concept of *residual-stream burden*, explaining that noisy targets force the residual stream to carry noise-dependent variation through the network, limiting representation flexibility. Experiments show that spectral concentration of clean targets reduces this burden, and the authors propose Spatially Indexed Hyper-Connections (SiHC) to expand residual bandwidth, achieving state‑of‑the‑art FID on ImageNet.
By Tongtong Liang, Siqi Kou, Ziqiao Xi, Esha Singh, Kun Zhou, Zhijie Deng, Alexander Cloninger, Yu-Xiang Wang, Rahul Parhi
arXiv:2607.01630v2 Announce Type: replace
Abstract: Dynamic expansion methods for class-incremental learning (CIL) protect task-specific knowledge by growing dedicated tokens or subnetworks, yet our...
By Bingchen Huang, Yifu Chen, Zhiling Wang, Yuanchao Du
arXiv:2607. 08946v1 Announce Type: new Abstract: A transformer can be built from operators that are legible by construction -- bounded, named units that read as fuzzy set operations rather than dense activations -- but legibility must be pressed for during training, and the pressure has a failure mode.
By Mark Oskin