Related papers: Archon: An Architecture Search Framework for Infer…

Despite rapid advancements in large language models (LLMs), the token-level autoregressive nature constrains their complex reasoning capabilities. To enhance LLM reasoning, inference-time techniques, including…

Retrieving answers in a quick and low cost manner without hallucinations from a combination of structured and unstructured data using Language models is a major hurdle. This is what prevents employment of Language models in knowledge…

Harness engineering has emerged as an important inference-time technique for large language model (LLM) agents, aiming to improve long-term performance through task decomposition and guided execution. However, more elaborate harnesses are…

Large language models (LLMs) have shown remarkable performance across a wide range of applications, often outperforming human experts. However, deploying these gigantic models efficiently for diverse inference use cases requires carefully…

Large Language Models (LLMs) have become an integral part of many real-world workflows. However, LLMs consume a lot of energy, which becomes a large concern in the scale of the demand for these tools. As LLMs become integrated into…

Resource-management tasks in modern operating and distributed systems continue to rely primarily on hand-designed heuristics for tasks such as scheduling, caching, or active queue management. Designing performant heuristics is an expensive,…

Large language models (LLMs) have achieved remarkable progress in solving various natural language processing tasks due to emergent reasoning abilities. However, LLMs have inherent limitations as they are incapable of accessing up-to-date…

The inference of deep neural networks (DNNs) on resource-constrained embedded systems introduces non-trivial trade-offs among model accuracy, computational latency, and hardware limitations, particularly when real-time constraints must be…

Although Large Vision-Language Models (LVLMs) have achieved impressive results, their high computational costs pose a significant barrier to wide application. To enhance inference efficiency, most existing approaches can be categorized as…

Aligning Large Language Models (LLM) to address subjectivity and nuanced preference levels requires adequate flexibility and control, which can be a resource-intensive and time-consuming procedure. Existing training-time alignment methods…

Retrieval-Augmented Generation (RAG) has been shown to enhance the factual accuracy of Large Language Models (LLMs), but existing methods often suffer from limited reasoning capabilities in effectively using the retrieved evidence,…

On the path to exascale the landscape of computer device architectures and corresponding programming models has become much more diverse. While various low-level performance portable programming models are available, support at the…

Optimizing Large Language Model (LLM) inference in production systems is increasingly difficult due to dynamic workloads, stringent latency/throughput targets, and a rapidly expanding configuration space. This complexity spans not only…

Alignment has greatly improved large language models (LLMs)' output quality at the cost of diversity, yielding highly similar outputs across generations. We propose Base-Aligned Model Collaboration (BACo), an inference-time token-level…

AI inference scaling is often tuned through 1D heuristics (a fixed reasoning pass) or 2D bivariate trade-offs (e.g., accuracy vs. compute), which fail to consider cost and latency constraints. We introduce a 3D optimization framework that…

Multi-agent LLM frameworks are widely used to accelerate the development of agent systems powered by large language models (LLMs). These frameworks impose distinct architectural structures that govern how agents interact, store information,…

Large language models (LLMs) have demonstrated powerful decision-making and planning capabilities in solving complicated real-world problems. LLM-based autonomous agents can interact with diverse tools (e.g., functional APIs) and generate…

Large language models (LLMs) are increasingly used to assist ideation in research, but evaluating the quality of LLM-generated research proposals remains difficult: novelty and soundness are hard to measure automatically, and large-scale…

Designing feasible and effective architectures under diverse computation budgets incurred by different applications/devices is essential for deploying deep models in practice. Existing methods often perform an independent architecture…

Recent advances in large language models have led to strong performance on reasoning and environment-interaction tasks, yet their ability for creative problem-solving remains underexplored. We study this capability through the lens of…