arXiv AI

Incremental Sheaf Cohomology on Cellular Complexes: O(1)-in-n Lazy Edit Processing under Bounded Local Geometry

arXiv:2606. 04227v1 Announce Type: cross Abstract: We present an algorithmic framework for incremental maintenance of first sheaf cohomology $H^1(X; \mathcal{F})$ on dynamically evolving 1-dimensional cellular complexes equipped with finite-dimensional cellular sheaves.

arXiv Machine Learning
Sep 25

Spectral-Guided Diffusion: Accelerating Inference via Static Spectral Layer Scheduling

Spectral-Guided Diffusion introduces a method to accelerate diffusion inference by identifying and reusing residual branches that need not be recomputed during the trajectory. The approach uses a Spectral Concentration Ratio (SCR) combined with Frobenius magnitude to create an offline sensitivity proxy and deterministic lifetime for each scheduled unit, eliminating the need for routers or input-dependent searches. Experiments on models such as LLaDA-8B, DiT-XL/2, U-ViT-L, and SDXL show that this scheduling preserves quality better than several baselines and achieves up to a 3.0× wall‑clock speedup over eager inference.

By Ibne Farabi Shihab, Abu Sa-Adat Mohamed Moon-Im Al Ahsan, Anuj Sharma
arXiv Computation and Language
Nov 4

Pacing Branch Parallelism in LLM Serving

The paper introduces PACE, a per‑step admission controller that manages intra‑request parallelism in large language model serving. By admitting extra decoding branches only when the predicted branch externality fits within the batch’s current slack, PACE avoids the pitfalls of eager or fixed‑cap branch admission. Experiments on Qwen3‑32B and other large models show that PACE boosts goodput by up to 2.15× while maintaining 99% SLO attainment.

By Swapnil Gandhi, Siva Kumar Sastry Hari, William J. Dally, Christos Kozyrakis
arXiv AI
Jul 22

Cost Accounting for Reactive Computational Graphs: Exhaustive Sweeps, Sequential Mutation, and the Backward-Locality Gap

arXiv:2607. 18323v1 Announce Type: cross Abstract: Exhaustive site-by-site interventions on a neural network's computational graph -- activation-patching sweeps, circuit-discovery searches, systematic ablation studies -- mutate the graph at every candidate site, and their cost is dominated by recomputation after each mutation.

By Abdallah Khemais (ISITCOM, University of Sousse)
arXiv Machine Learning
Jul 3

Incremental (k, z)-Clustering on Graphs

arXiv:2602. 08542v3 Announce Type: replace-cross Abstract: Given a weighted undirected graph, a number of clusters $k$, and an exponent $z$, the goal in the $(k, z)$-clustering problem on graphs is to select $k$ vertices as centers that minimize the sum of the distances raised to the power $z$ of each vertex to its closest center.

By Emilio Cruciani, Sebastian Forster, Antonis Skarlatos
arXiv AI
Jun 24

Repeated Shared Access Enables Grokking, but Edit Propagation Depends on an Addressable Memory

arXiv:2606. 20737v2 Announce Type: replace Abstract: We study factual edit propagation in a controlled synthetic knowledge-graph QA setting using a 2x2 grid that crosses loop recurrence with shared-memory access: a dense transformer (Dense), a looped transformer (Loop), a dense backbone with shared memory (Dense+Mem), and a looped backbone with shared memory (loop-memory coupling, LMC).

By Yanan Niu