PAS encodes locations via relative anchors and bins to deliver roughly 370-400m adversarial error in spatial RAG while retaining over half the baseline retrieval performance and keeping generation quality robust.
Title resolution pending
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
verdicts
UNVERDICTED 8roles
method 1polarities
use method 1representative citing papers
ATRS uses a shared neural policy in a multi-agent MDP to adaptively re-split trajectory segments during parallel ADMM optimization, cutting iterations by up to 26% and time by 19.1% with zero-shot generalization.
GEN-Graph is a heterogeneous PIM accelerator with specialized Matrix-tile and traversal-tile that delivers exact computation for both matrix-centric and topology-centric graph DP workloads.
IcePick applies model checking to achieve guaranteed state coverage in API testing while Glacier provides executable semantic contracts for automated behavioral oracles.
A dynamic saturation rate extension to the multi-commodity store-and-forward model is reformulated as an efficient MILP that outperforms prior multi-commodity approaches in mixed CAV-HDV traffic simulations.
A resource-reusing FPGA architecture for GARI-structured message-passing decoding of quantum LDPC codes with correlated errors achieves 596 ns average latency and 6x lower resource use than prior GARI hardware on a VCU19P device.
The authors develop an error pattern tree representation that unifies SGRAND and ORBGRAND, enabling a parallel SGRAND design with ML optimality and an enhanced parallel ORBGRAND variant, with reported speedups of 3.96x and 4.21x respectively.
Precomputes rotation angles classically and adds a magnitude-then-phase procedure to enable complex-valued state preparation on BBQRAM at unchanged O(log²(MN)) query cost with no reversible arithmetic on the QPU.
citing papers explorer
-
Privacy Without Losing Place: A Paradigm for Private Retrieval in Spatial RAGs
PAS encodes locations via relative anchors and bins to deliver roughly 370-400m adversarial error in spatial RAG while retaining over half the baseline retrieval performance and keeping generation quality robust.
-
ATRS: Adaptive Trajectory Re-splitting via a Shared Neural Policy for Parallel Optimization
ATRS uses a shared neural policy in a multi-agent MDP to adaptively re-split trajectory segments during parallel ADMM optimization, cutting iterations by up to 26% and time by 19.1% with zero-shot generalization.
-
GEN-Graph: Heterogeneous PIM Accelerator for General Computational Patterns in Graph-based Dynamic Programming
GEN-Graph is a heterogeneous PIM accelerator with specialized Matrix-tile and traversal-tile that delivers exact computation for both matrix-centric and topology-centric graph DP workloads.
-
Systematic API Testing Through Model Checking and Executable Contracts
IcePick applies model checking to achieve guaranteed state coverage in API testing while Glacier provides executable semantic contracts for automated behavioral oracles.
-
Efficient MILP-based Urban Network Traffic Control in Mixed Autonomy with Dynamic Saturation Rates
A dynamic saturation rate extension to the multi-commodity store-and-forward model is reformulated as an efficient MILP that outperforms prior multi-commodity approaches in mixed CAV-HDV traffic simulations.
-
A Scalable FPGA Architecture for Real-Time Decoding of Quantum LDPC Codes Using GARI
A resource-reusing FPGA architecture for GARI-structured message-passing decoding of quantum LDPC codes with correlated errors achieves 596 ns average latency and 6x lower resource use than prior GARI hardware on a VCU19P device.
-
A Parallelization Strategy for GRAND with Optimality Guarantee by Exploiting Error Pattern Tree Representation
The authors develop an error pattern tree representation that unifies SGRAND and ORBGRAND, enabling a parallel SGRAND design with ML optimality and an enhanced parallel ORBGRAND variant, with reported speedups of 3.96x and 4.21x respectively.
-
Efficient Complex-Valued State Preparation on Bucket Brigade QRAM
Precomputes rotation angles classically and adds a magnitude-then-phase procedure to enable complex-valued state preparation on BBQRAM at unchanged O(log²(MN)) query cost with no reversible arithmetic on the QPU.