The ability of Language Models (LMs) to understand natural language makes them a powerful tool for parsing human instructions into task plans for autonomous robots. Unlike traditional planning methods that rely on domain-specific knowledge and handcrafted rules, LMs generalize from diverse data and adapt to various tasks with minimal tuning, acting as a compressed knowledge base. However, LMs in their standard form face challenges with long-horizon tasks, particularly in partially observable multi-agent settings. We propose an LM-based Long-Horizon Planner for Multi-Agent Robotics (LLaMAR), a cognitive architecture for planning that achieves state-of-the-art results in long-horizon tasks within partially observable environments. LLaMAR employs a plan-act-correct-verify framework, allowing self-correction from action execution feedback without relying on oracles or simulators. Additionally, we present MAP-THOR, a comprehensive test suite encompassing household tasks of varying complexity within the AI2-THOR environment. Experiments show that LLaMAR achieves a 30\% higher success rate than other state-of-the-art LM-based multi-agent planners in MAP-THOR and Search \& Rescue tasks. Code can be found at [https://github.com/nsidn98/LLaMAR](https://github.com/nsidn98/LLaMAR)

As the size and complexity of analytic data processing systems continue to grow, the effort required to mitigate faults and performance skew has also risen. However, in some environments we have encountered, users prefer to continue query execution even in the presence of failures (e.g., the unavailability of certain data sources), and receive a "partial" answer to their query. We explore ways to characterize and classify these partial results, and describe an analytical framework that allows the system to perform coarse to fine-grained analysis to determine the semantics of a partial result. We propose that if the system is equipped with such a framework, in some cases it is better to return and explain partial results than to attempt to avoid them.

Communication in multi- and many-core processors has long been a bottleneck to performance due to the high cost of long-distance electrical transmission. This difficulty has been partially remedied by architectural constructs such as caches and novel interconnect topologies, albeit at a steep cost in terms of complexity. Unfortunately, even these measures are rendered ineffective by certain kinds of communication, most notably scatter and gather operations that exhibit highly nonlocal data access patterns. Much work has gone into examining how the increased bandwidth density afforded by chip-scale silicon photonic interconnect technologies affects computing, but photonics have additional properties that can be leveraged to greatly accelerate performance and energy efficiency under such difficult loads. This paper describes a novel synchronized global photonic bus and system architecture called P-sync that uses photonics' distance independence to greatly improve performance on many important applications previously limited by electronic interconnect. The architecture is evaluated in the context of a non-local yet common application: the distributed Fast Fourier Transform. We show that it is possible to achieve high efficiency by tightly balancing computation and communication latency in P-sync and achieve upwards of a 6× performance increase on gather patterns, even when bandwidth is equalized.

In recent years, Massively Parallel Processors have increasingly been used to manage and query vast amounts of data. Dramatic performance improvements are achieved through distributed execution of queries across many nodes. Query optimization for such system is a challenging and important problem.

As advancements in CMOS technology trend toward ever increasing core counts in chip multiprocessors for high-performance embedded computing, the discrepancy between on- and off-chip communication bandwidth continues to widen due to the power and spatial constraints of electronic off-chip signaling. Silicon photonics-based communication offers many advantages over electronics for network-on-chip design, namely power consumption that is effectively agnostic to distance traveled at the chip- and board-scale, even across chip boundaries. In this work we develop a design for a photonic network-on-chip with integrated DRAM I/O interfaces and compare its performance to similar electronic solutions using a detailed network-on-chip simulation. When used in a circuit-switched network, silicon nanophotonic switches offer higher bandwidth density and low power transmission, adding up to over 10x better performance and 3-5x lower power over the baseline for projective transform, matrix multiply, and Fast Fourier Transform (FFT), all key algorithms in embedded real-time signal and image processing.

This paper introduces Clustera, an integrated computation and data management system. In contrast to traditional cluster-management systems that target specific types of workloads, Clustera is designed for extensibility, enabling the system to be easily extended to handle a wide variety of job types ranging from computationally-intensive, long-running jobs with minimal I/O requirements to complex SQL queries over massive relational tables. Another unique feature of Clustera is the way in which the system architecture exploits modern software building blocks including application servers and relational database systems in order to realize important performance, scalability, portability and usability benefits. Finally, experimental evaluation suggests that Clustera has good scale-up properties for SQL processing, that Clustera delivers performance comparable to Hadoop for MapReduce processing and that Clustera can support higher job throughput rates than previously published results for the Condor and CondorJ2 batch computing systems.

Through the use of a new disk-based method for enumerating very large orbits, condensation for orbits with tens of billions of elements can be performed. The algorithm is novel in that it offers efficient access to data using distributed disk-based data structures. This provides fast access to hundreds of gigabytes of data,which allows for computing without worrying about memory limitations.

We outline a distributed, disk-based technique for computing over very large matrix groups. This technique is used to compute a permutation representation for the Baby Monster, a sporadic simple group that acts on 13,571,955,000 points. Its group order is approximately 4 × 1033. This is a landmark because it is 100 times larger than any previous construction of a permutation representation. By using the computed on-disk data structures, computation over the Baby Monster is now feasible using the distributed disks of a cluster. Our work allows researchers to use either a matrix, a permutation, or a word representation for computing over the Baby Monster where previously only a matrix representation was available. The methodology is demonstrated by using as a signature the image of a vector that is stabilized by the maximal subgroup. The technique extends to finite simple groups and to other groups, through other signatures.

Group membership is a fundamental algorithm, upon which most other algorithms of computational group theory depend. Until now, group membership for permutation groups has been limited to ten million points or less. We extend the applicability of group membership algorithms to permutation groups acting on more than 100,000,000 points. As an example, we experimentally construct a group membership data structure for Thompson's group, acting on 143,127,000 points, in 36 minutes. More significantly, we require approximately 10 GB of RAM for the computation --- even though a single permutation of Thompson's group already requires half a gigabyte of storage.In addition, we propose a disk-based group membership algorithm with the promise of extending group membership to well over one billion (1,000,000,000) points. Such a disk-based algorithm has formerly been impossible, due in part to the lack of a practical disk-based algorithm for multiplying and taking inverses of such large permutations. Random access to disk is prohibitively expensive. We demonstrate the first practical disk-based implementation of the basic permutation operations. We also propose a disk-based architecture for group membership data structures.