arXiv:2608. 03962v1 Announce Type: cross Abstract: Modern large language models - transformers and diffusion language models - are built around two canonical algorithmic tasks: prediction and generation.
Modern large language models - transformers and diffusion language models - are built around two canonical algorithmic tasks: prediction and generation. We prove unconditional separations between low-depth quantum computation and the corresponding bounded-resource classical language-model architectures in both regimes.
arXiv:2608. 05110v1 Announce Type: cross Abstract: Near-term quantum hardware limits circuit depth and often imposes geometrically local connectivity for quantum generative models, restricting the output distributions accessible to shallow unitary Born models.
arXiv:2608. 11066v1 Announce Type: cross Abstract: We prove inference-time quantum coordination advantages for specified AI state-tracking tasks.
arXiv:2606. 11673v1 Announce Type: cross Abstract: Standard dot-product self-attention computes, in a single layer, only pairwise (order-2) interactions between tokens; representing a generic order-$k$ interaction is known to require either super-quadratic resources in one layer or composition across depth.
arXiv:2606. 19697v1 Announce Type: cross Abstract: The increasing popularity of \emph{reasoning} models -- language models that output a series of reasoning or thought tokens before producing an answer -- is justified, in part, by theoretical results showing that chain-of-thought (CoT) transformers can simulate Turing machines, and thus perform arbitrary computation.
arXiv:2607. 24686v1 Announce Type: cross Abstract: Variational quantum circuits have been central to many proposed near-term applications of quantum computing, but a growing body of evidence suggests that trainability and quantum advantage are fundamentally at odds: ans\"atze expressive enough to resist efficient classical simulation tend to exhibit barren plateaus, while structures that provably rule out barren plateaus typically render them classically simulable.
arXiv:2603. 03612v3 Announce Type: replace Abstract: The community is increasingly exploring linear RNNs (LRNNs) as language models, motivated by their expressive power and parallelizability.
arXiv:2606. 12211v1 Announce Type: cross Abstract: A central principle in quantum machine learning is that an ansatz should be expressive enough to represent the quantum data of interest.
arXiv:2607. 12780v1 Announce Type: cross Abstract: Quantum circuit optimization for fault-tolerant computing requires exact functional equivalence while minimizing expensive non-Clifford resources such as T gates.
Quantum circuit optimization for fault-tolerant computing requires exact functional equivalence while minimizing expensive non-Clifford resources such as T gates. We study this problem using a compact 44.
arXiv:2607. 17872v1 Announce Type: cross Abstract: Circuit cutting promises to scale quantum computations beyond current hardware, but variational quantum advantage also requires low cutting overhead, classical hardness, and trainability.
arXiv:2608. 11716v1 Announce Type: new Abstract: Chain of Thought (CoT) lifts the expressive ceiling of bounded-depth Transformers, with characterizations tying the number of CoT steps to circuit complexity classes.