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…

The paper introduces SecRL-Prune, a structured reinforcement learning framework that effectively prunes CodeLLMs while preserving their critical ability to generate adversarial, functionality-preservi…

The paper proposes PALS, a method for adjusting per-layer sparsity based on activation magnitudes in transformer models, achieving better performance than uniform one-shot pruning methods.

MAESTRO is a structured pruning framework designed for MoE language models that models autoregressive expert activation trajectories as Ergodic Markov chains, yielding a globally aware importance heur…

This paper introduces Polynomial-Sensitivity-Aware Pruning (PSAP), a reliability-aware structured pruning method for neural networks under homomorphic encryption, reducing catastrophic layer vulnerabi…

The paper introduces STARFISH, a novel healing method that efficiently recovers significant accuracy in heavily pruned neural networks by optimizing the pruned model to match the original network's in…

VEDAL introduces a variational, error-driven asynchronous learning framework to efficiently prune 3D Gaussian Splatting, achieving high compression ratios with minimal loss in novel view synthesis qua…

The paper proposes Locality-Aware Redundancy Pruning (LoRP), a training-free method that prunes LLM layers by exploiting localized inter-layer redundancy, leading to improved efficiency while maintain…

The paper proposes an aggressive, parameter-efficient method to prune non-essential experts from Mixture-of-Experts (MoE) LLMs, significantly compressing the model while maintaining high machine trans…

This paper proposes a resource-oriented one-shot quantiser pruning method for high granularity quantisation (HGQ) to reduce search cost and achieve a competitive Pareto frontier in FPGA-based edge neu…

This paper investigates the use of spectral filtering for continuous subgraph matching over dynamic graphs and presents three key findings.

This paper proves a coarse tree decomposition of graphs with bounded adhesion sets and separators.

This paper introduces structured cut sets, a novel preprocessing technique for Maximum k-Cut, and extends existing techniques from Maximum Cut. The rules are optimality-preserving and yield significan…

The paper introduces PRAXIS, a novel algorithm that efficiently approximates the computation of 'Rashomon sets' for decision trees, significantly reducing memory and runtime complexity.

The paper introduces two library combinators, prune and defrel/bank, to bring observational deduplication and bottom-up enumeration into the relational setting using plain miniKanren.

This paper presents four novel parallel algorithms for maintaining a rooted spanning forest in dynamic graphs, achieving a throughput of 2 million insertions and 1.4 million deletions per second.

This paper improves the time complexity of exact algorithms for converting a connected graph into a cactus by reducing it from O*(3^n) to O*(2^n) for unweighted graphs, and provides faster algorithms…