BudgetDraft introduces an acceptance-aware multi-view training method that trains a sparse-KV speculative decoder to maintain high acceptance rates across varying context lengths and sparsity levels,…

The paper proposes Cross-Layer Sparse Attention (CLSA) to significantly improve the efficiency and accuracy of long-context LLMs by jointly optimizing KV-cache sharing and the routing index across dec…

PrunePath introduces a budget-adaptive structured sparsification framework that efficiently prunes Feed-forward networks in large language models, achieving hardware-friendly sparsity and measurable s…

This paper proposes a sparse cache with a novel allocation rule based on DP-means clustering for deep recurrent models, achieving full associative recall with only distinct items, outperforming other…

This paper introduces Stale Synchronous Parallel mode of execution for parallel sparse triangular linear system solve and presents a scheduler that achieves geometric-mean speed-ups of 7-30% over Grow…

This paper proves that for any finite abelian group, there exists a spectral sparsifier for its Cayley graph with log(|G|) generators. This result improves upon previous work for constructing code spa…

This paper introduces a new scaling law for sparse language models trained with limited data, demonstrating that sparsity can significantly improve performance and delay data saturation during multi-e…

This paper presents a method for compressing matrices using a RePair straight-line program (SLP), allowing matrix-vector products with time and space proportional to the compressed size, and demonstra…

This paper introduces CW-Ghost, a method for estimating cache line fill volume and determining helper-thread prefetching granularity based on cache capacity constraints.

The paper refutes Steurer's conjecture regarding the existence of large constant-separated sets within families of unit-norm vectors with low average correlation, using high-dimensional expanders to s…

The paper introduces Sparse Memory-Efficient Training (SMET), a method that stabilizes and optimizes Dynamic Sparse Training (DST) for large language models, enabling stable and memory-efficient spars…

This paper compares three neuromorphic core designs for handling weight sparsity in event-driven neural networks and quantifies the performance and energy costs.

This paper proposes a compression scheme for transmitting sparse local updates in distributed learning systems, and provides a converse based on f-divergence to characterize the communication-accuracy…

This paper proposes TileLens, a system to mitigate read amplification in Large-Granularity Memory Systems (LGMS) for Large Language Model (LLM) inference by adopting a tile-major layout.

The paper proposes GroundedCache, an evidence-validated cache router that significantly improves the safety of reusing cached semantic answers in RAG systems by requiring multiple gates to validate th…

This paper proposes a non-greedy insertion strategy for linear probing hash tables, improving worst-case expected insertion time from Θ(x^2) to O(x log x).

This paper presents the 2026 Algorithmic Information Theory Data Compression Challenge, evaluating lossless compressors under realistic constraints and revealing performance dependencies.

The paper introduces PATH, an in-situ indexing architecture for Processing-in-Memory systems that achieves higher throughput, lower tail latency, and fewer memory accesses than state-of-the-art scheme…