English
Related papers

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

200 papers

Large language models (LLMs) now solve multi-step problems by emitting extended chains of thought. During the process, they often re-derive the same intermediate steps across problems, inflating token usage and latency. This saturation of…

Machine Learning · Computer Science 2025-09-17 Aniket Didolkar , Nicolas Ballas , Sanjeev Arora , Anirudh Goyal

Developing autonomous driving systems (ADSs) involves generating and storing extensive log data from test drives, which is essential for verification, research, and simulation. However, these high-frequency logs, recorded over varying…

Software Engineering · Computer Science 2025-06-16 Simin Sun , Yuchuan Jin , Miroslaw Staron

While test-time reasoning enables language models (LMs) to tackle complex tasks, searching or planning in natural language can be slow, costly, and error-prone. But even when LMs struggle to emulate the precise reasoning steps needed to…

Computation and Language · Computer Science 2025-08-11 Gabriel Grand , Joshua B. Tenenbaum , Vikash K. Mansinghka , Alexander K. Lew , Jacob Andreas

We propose SLIM (Stochastic Learning and Inference in overidentified Models), a scalable stochastic approximation framework for nonlinear GMM. SLIM forms iterative updates from independent mini-batches of moments and their derivatives,…

Econometrics · Economics 2025-11-03 Xiaohong Chen , Min Seong Kim , Sokbae Lee , Myung Hwan Seo , Myunghyun Song

Load instructions often limit instruction-level parallelism (ILP) in modern processors due to data and resource dependences they cause. Prior techniques like Load Value Prediction (LVP) and Memory Renaming (MRN) mitigate load data…

The RTS smoother is widely used for state estimation and it is utilized here to increase the data quality with respect to physical coherence and to increase resolution. The purpose of this paper is to enhance the performance of the RTS…

Applications · Statistics 2022-06-22 Lukas Höhndorf , Thomas Nagler , Phillip Koppitz , Claudia Czado , Florian Holzapfel

Speculative decoding accelerates LLM inference by letting a small drafter propose multiple tokens which a large target model verifies once per speculation step. As vocabularies scale past 10e5 tokens,verification cost in the target model is…

Computation and Language · Computer Science 2026-02-04 Jinbin Zhang , Nasib Ullah , Erik Schultheis , Rohit Babbar

Analysis of execution traces plays a fundamental role in many program analysis approaches, such as runtime verification, testing, monitoring, and specification mining. Execution traces are frequently parametric, i.e., they contain events…

Programming Languages · Computer Science 2015-07-01 Grigore Rosu , Feng Chen

In optimization problems, some variable subsets may have a joint non-linear or non-monotonical influence on the function value. Therefore, knowledge of variable dependencies may be crucial for effective optimization, and many…

Machine Learning · Statistics 2026-04-15 M. W. Przewozniczek , B. Frej , M. M. Komarnicki , M. Prusik , R. Tinós

This work addresses inverse linear optimization where the goal is to infer the unknown cost vector of a linear program. Specifically, we consider the data-driven setting in which the available data are noisy observations of optimal…

Optimization and Control · Mathematics 2021-12-07 Rishabh Gupta , Qi Zhang

Reinforcement learning (RL) policies are typically trained for fixed objectives, making reuse difficult when task requirements change. We study inference-time policy reuse: given a library of pre-trained policies and a new composite…

Machine Learning · Computer Science 2026-04-29 Ihor Vitenko , Noha Ibrahim , Sihem Amer-Yahia

As large language models (LLMs) become increasingly versatile, numerous large scale benchmarks have been developed to thoroughly assess their capabilities. These benchmarks typically consist of diverse datasets and prompts to evaluate…

Machine Learning · Computer Science 2024-10-10 Yang Li , Jie Ma , Miguel Ballesteros , Yassine Benajiba , Graham Horwood

Since the release of Deepseek-R1, reinforcement learning with verifiable rewards (RLVR) has become a central approach for training large language models (LLMs) on reasoning tasks. Recent work has largely focused on modifying loss functions…

Machine Learning · Computer Science 2025-10-03 Weizhe Chen , Sven Koenig , Bistra Dilkina

In the field of instruction-following large vision-language models (LVLMs), the efficient deployment of these models faces challenges, notably due to the high memory demands of their key-value (KV) caches. Conventional cache management…

Computer Vision and Pattern Recognition · Computer Science 2024-07-26 Zuyan Liu , Benlin Liu , Jiahui Wang , Yuhao Dong , Guangyi Chen , Yongming Rao , Ranjay Krishna , Jiwen Lu

In the trace reconstruction problem, one observes the output of passing a binary string $s \in \{0,1\}^n$ through a deletion channel $T$ times and wishes to recover $s$ from the resulting $T$ "traces." Most of the literature has focused on…

Information Theory · Computer Science 2024-11-05 Kayvon Mazooji , Ilan Shomorony

This paper considers the problem of learning, from samples, the dependency structure of a system of linear stochastic differential equations, when some of the variables are latent. In particular, we observe the time evolution of some…

Machine Learning · Computer Science 2012-05-02 Ali Jalali , Sujay Sanghavi

Policy loss estimation remains a fundamental and long-standing challenge in reinforcement learning (RL) for diffusion language models (dLLMs). We introduce Reinforcement Learning from Denoising Feedback (RLDF), a novel training paradigm…

Computation and Language · Computer Science 2026-05-26 Qi He , Huan Chen , Ya Guo , Huijia Zhu , Yi R. Fung , Baojian Zhou

Dynamic languages (such as Python and JavaScript) offer flexibility and simplified type handling for programming, but this can also lead to an increase in type-related errors and additional overhead for compile-time type inference. As a…

Software Engineering · Computer Science 2026-04-06 Teyu Lin , Minghao Fan , Huaxun Huang , Zhirong Shen , Rongxin Wu

Offline runtime verification involves the static analysis of executions of a system against a specification. For distributed systems, it is generally not possible to characterize executions in the form of global traces, given the absence of…

Software Engineering · Computer Science 2024-03-06 Erwan Mahe , Boutheina Bannour , Christophe Gaston , Arnault Lapitre , Pascale Le Gall

Selective prediction minimizes incorrect predictions from vision-language models (VLMs) by allowing them to abstain from answering when uncertain. However, when deploying a vision-language system with low tolerance for inaccurate…

Computation and Language · Computer Science 2024-06-14 Tejas Srinivasan , Jack Hessel , Tanmay Gupta , Bill Yuchen Lin , Yejin Choi , Jesse Thomason , Khyathi Raghavi Chandu