Related papers: LLM as an Execution Estimator: Recovering Missing …

We study the problem of optimizing Large Language Model (LLM) inference scheduling to minimize total latency. LLM inference is an online and multi-task service process and also heavily energy consuming by which a pre-trained LLM processes…

LLMs are commonly used in retrieval-augmented applications to execute user instructions based on data from external sources. For example, modern search engines use LLMs to answer queries based on relevant search results; email plugins…

Vision-Language-Action (VLA) policies are typically deployed with asynchronous inference: the robot executes a previously predicted action chunk while the model computes the next one. This creates a prediction-execution misalignment: the…

Although Key-Value (KV) Cache is essential for efficient large language models (LLMs) inference, its growing memory footprint in long-context scenarios poses a significant bottleneck, making KVCache compression crucial. Current compression…

In analyzing and assessing the condition of dynamical systems, it is necessary to account for nonlinearity. Recent advances in computation have rendered previously computationally infeasible analyses readily executable on common computer…

Advection-dominated dynamical systems, characterized by partial differential equations, are found in applications ranging from weather forecasting to engineering design where accuracy and robustness are crucial. There has been significant…

Large Language Model (LLM) inference, where a trained model generates text one word at a time in response to user prompts, is a computationally intensive process requiring efficient scheduling to optimize latency and resource utilization. A…

We study the problem of learning robust discriminative representations of causally related latent variables given the underlying causal graph and a training set comprising passively collected observational data and interventional data…

This paper presents the tracking approach for deriving detectably recoverable (and thus also durable) implementations of many widely-used concurrent data structures. Such data structures, satisfying detectable recovery, are appealing for…

Large Language Models (LLMs) offer new potential for automating documentation-to-code traceability, yet their capabilities remain underexplored. We present a comprehensive evaluation of LLMs (Claude 3.5 Sonnet, GPT-4o, and o3-mini) in…

In LLM inference, the same prompt may yield different outputs across different runs. At the system level, this non-determinism arises from floating-point non-associativity combined with dynamic batching and GPU kernels whose reduction…

LLMs can solve program synthesis tasks but remain inefficient and unreliable on hard instances requiring large combinatorial search. Given a small set of reasoning traces, we use coding agents to compile them into reusable symbolic program…

Backtracking (i.e., reverse execution) helps the user of a debugger to naturally think backwards along the execution path of a program, and thinking backwards makes it easy to locate the origin of a bug. So far backtracking has been…

Sensing is one of the most fundamental tasks for the monitoring, forecasting and control of complex, spatio-temporal systems. In many applications, a limited number of sensors are mobile and move with the dynamics, with examples including…

The extent of parallelization of a loop is largely determined by the dependences between its statements. While dependence free loops are fully parallelizable, those with loop carried dependences are not. Dependence distance is a measure of…

Detecting vulnerabilities in source code remains critical yet challenging, as conventional static analysis tools construct inaccurate program representations, while existing LLM-based approaches often miss essential vulnerability context…

Released Large Language Models (LLMs) are often paired with a claimed knowledge cutoff date, or the dates at which training data was gathered. Such information is crucial for applications where the LLM must provide up to date information.…

Vision-and-Language Navigation (VLN) requires an agent to follow natural-language instructions and navigate through previously unseen environments. Recent approaches increasingly employ large language models (LLMs) as high-level navigators…

Recent literature has shown how linear time-invariant (LTI) systems can be represented by trajectories features, that is relying on a single input-output (IO) data dictionary to span all possible system trajectories, as long as the input is…

With the growing popularity of LLM agents and RAG, it has become increasingly important to retrieve documents that are essential for solving a task, even when their connection to the task is indirect or implicit. Addressing this problem…