arXiv:2606. 16730v2 Announce Type: replace-cross Abstract: We re-interpret Transformer pretraining as a fast-slow, singularly perturbed flow along depth, with untied weights as its non-autonomous feature.
arXiv:2606. 16730v1 Announce Type: cross Abstract: Causal self-attention is a coupling mechanism: each token's hidden state is updated by a learned mixture of preceding tokens at the same timescale.
arXiv:2607. 18363v1 Announce Type: cross Abstract: Feed-forward networks hold two thirds of a transformer's non-embedding parameters, yet the architecture has not received a necessity test that controls parameters, compute, and depth at once.
arXiv:2607. 15449v1 Announce Type: new Abstract: Using the language of Wilsonian renormalization group theory (RG), we treat the Transformer's attention mechanism as a perturbation of the trained MLP residual-stack fixed point and ask whether it constitutes a relevant, marginal, or irrelevant operator.
arXiv:2608. 15022v1 Announce Type: new Abstract: Language models hold latent quantities in a form they can report on, and more of a quantity is present in that form when the task requires reusing it flexibly.
The paper investigates how block‑diffusion language models can use a constant‑size cache to enable efficient parallel decoding. By employing sequence mixers that summarize completed blocks into a reusable state and a block‑causal training objective, the authors pretrain three 3B block‑diffusion denoisers (attention, Mamba, and hybrid) on 300 B tokens. The resulting state‑space cache remains O(1) in memory and latency regardless of context length, yielding significant speed‑up and memory savings compared to traditional attention‑based caches, especially at very long sequences.
Selective state space models (SSMs) use a recurrence to mix token information, a process analogous to attention in transformers. By modeling token evolution as an ordinary differential equation and applying input‑to‑state stability, the study proves that SSMs exhibit local exponential stability of consensus equilibria and delineates their domain of attraction for time‑varying weight matrices. Experiments on a pretrained Mamba‑2 model reveal that the output gate controls the degree of consensus, preventing tokens from fully converging.
arXiv:2608.12149v2 Announce Type: replace Abstract: We present the first systematic study of Massive activations (MAs) in layer-interleaved HLA LLMs and uncover two architecture-aligned morphologies:...
arXiv:2606. 00091v1 Announce Type: cross Abstract: Joint Embedding Predictive Architectures (JEPAs) have reshaped self-supervised representation learning in vision.
arXiv:2606. 24396v1 Announce Type: new Abstract: Large Transformer models function as Dense Associative Memories (DAMs), retrieving knowledge via high-dimensional attractor dynamics driven by the self-attention mechanism \citep{ramsauer2020hopfield, wu2024attention}.
arXiv:2607. 20484v1 Announce Type: new Abstract: Large Language Models (LLMs) are fundamentally limited by representation collapse, a bottleneck that severely degrades long-context performance.
arXiv:2601. 11618v2 Announce Type: replace-cross Abstract: Geometric Attention (GA) specifies an attention layer by four independent inputs: a finite carrier (what indices are addressable), an evidence-kernel rule (how masked proto-scores and a link induce nonnegative weights), a probe family (which observables are treated as admissible), and an anchor/update rule (which representative kernel is selected and how it is applied).
We present the first systematic study of Massive activations (MAs) in layer-interleaved HLA LLMs and uncover two architecture-aligned morphologies: MAs consistently spike immediately before full attention layers, forming pre-attention spikes (PAS), and can persist through intervening linear attention layers, giving rise to inter-spike plateaus (ISP). As full attention becomes denser, successive PAS become increasingly connected through ISP, ultimately recovering the stable MA morphology of full attention LLMs.