English
Related papers

Related papers: A Backward/Forward Recovery Approach for the Preco…

200 papers

Backward error analysis allows finding a modified loss function, which the parameter updates really follow under the influence of an optimization method. The additional loss terms included in this modified function is called implicit…

Machine Learning · Computer Science 2025-03-06 Jinwoo Lim , Suhyun Kim , Soo-Mook Moon

We present an SMT-based symbolic model checking algorithm for safety verification of recursive programs. The algorithm is modular and analyzes procedures individually. Unlike other SMT-based approaches, it maintains both "over-" and…

Logic in Computer Science · Computer Science 2014-05-27 Anvesh Komuravelli , Arie Gurfinkel , Sagar Chaki

We propose a conversion scheme that turns regret minimizing algorithms into fixed point iterations, with convergence guarantees following from regret bounds. The resulting iterations can be seen as a grand extension of the classical…

Optimization and Control · Mathematics 2025-09-29 Joon Kwon

Asynchronous iterative methods tolerate straggling processors by allowing workers to proceed with stale data, but at a cost: the iterates become inconsistent, potentially degrading convergence. We investigate whether convergence…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-28 Evan Coleman , Masha Sosonkina

In this paper, we present a domain specific process to assist the verification of observer-based fault detection software. Observer-based fault detection systems, like control systems, yield invariant properties of quadratic types. These…

Systems and Control · Computer Science 2013-11-11 Timothy Wang , Alireza Esna Ashari , Romain Jobredeaux , Eric M. Feron

Continual post-training (CPT) is a popular and effective technique for adapting foundation models like multimodal large language models to specific and ever-evolving downstream tasks. While existing research has primarily concentrated on…

Machine Learning · Computer Science 2026-01-22 Song Lai , Haohan Zhao , Rong Feng , Changyi Ma , Wenzhuo Liu , Hongbo Zhao , Xi Lin , Dong Yi , Qingfu Zhang , Hongbin Liu , Gaofeng Meng , Fei Zhu

When upgrading neural models to a newer version, new errors that were not encountered in the legacy version can be introduced, known as regression errors. This inconsistent behavior during model upgrade often outweighs the benefits of…

Computation and Language · Computer Science 2023-02-07 Yi-An Lai , Elman Mansimov , Yuqing Xie , Yi Zhang

A two-stage procedure for simultaneously detecting multiple thresholds and achieving model selection in the segmented accelerate failure time (AFT) model is developed in this paper. In the first stage, we formulate the threshold problem as…

Methodology · Statistics 2018-08-10 Jialiang Li , Baisuo Jin

Safety alignment is a key requirement for building reliable Artificial General Intelligence. Despite significant advances in safety alignment, we observe that minor latent shifts can still trigger unsafe responses in aligned models. We…

Machine Learning · Computer Science 2025-06-23 Tianle Gu , Kexin Huang , Zongqi Wang , Yixu Wang , Jie Li , Yuanqi Yao , Yang Yao , Yujiu Yang , Yan Teng , Yingchun Wang

In model-based reinforcement learning for safety-critical control systems, it is important to formally certify system properties (e.g., safety, stability) under the learned controller. However, as existing methods typically apply formal…

Machine Learning · Computer Science 2023-03-22 Yixuan Wang , Simon Zhan , Zhilu Wang , Chao Huang , Zhaoran Wang , Zhuoran Yang , Qi Zhu

Despite the remarkable capabilities of large language models, current training paradigms inadvertently foster \textit{sycophancy}, i.e., the tendency of a model to agree with or reinforce user-provided information even when it's factually…

Artificial Intelligence · Computer Science 2025-09-23 Mohammad Beigi , Ying Shen , Parshin Shojaee , Qifan Wang , Zichao Wang , Chandan Reddy , Ming Jin , Lifu Huang

Large language models (LLMs) are increasingly deployed in decision-making tasks, where not only accuracy but also reliable confidence estimates are essential. Well-calibrated confidence enables downstream systems to decide when to trust a…

Machine Learning · Computer Science 2026-01-21 Duygu Nur Yaldiz , Evangelia Spiliopoulou , Zheng Qi , Siddharth Varia , Srikanth Doss , Nikolaos Pappas

Automatic differentiation (AD) is conventionally understood as a family of distinct algorithms, rooted in two "modes" -- forward and reverse -- which are typically presented (and implemented) separately. Can there be only one? Following up…

Programming Languages · Computer Science 2022-12-07 Alexey Radul , Adam Paszke , Roy Frostig , Matthew Johnson , Dougal Maclaurin

State-of-the-art reasoning models utilize long chain-of-thought (CoT) to solve increasingly complex problems using more test-time computation. In this work, we explore a long CoT setting where the model makes up to K successive attempts at…

Machine Learning · Computer Science 2026-04-21 Muhammed Emrullah Ildiz , Halil Alperen Gozeten , Ege Onur Taga , Samet Oymak

Reinforcement fine-tuning (RFT) has become a core paradigm for post-training large language models, yet its training process remains highly fragile. Existing efforts mainly improve reliability at the system level or address specific issues…

Software Engineering · Computer Science 2026-05-07 Lingzhe Zhang , Tong Jia , Yunpeng Zhai , Liancheng Fang , Kening Zheng , Hongyi Liu , Xiaosong Huang , Philip S. Yu , Ying Li

We propose an abstraction-based model checking method which relies on refinement of an under-approximation of the feasible behaviors of the system under analysis. The method preserves errors to safety properties, since all analyzed…

Computer Science and Game Theory · Computer Science 2017-01-11 Corina S. Pasareanu , Radek Pelanek , Willem Visser

Fault detection is crucial for ensuring the safety and reliability of modern industrial systems. However, a significant scientific challenge is the lack of rigorous risk control and reliable uncertainty quantification in existing diagnostic…

Artificial Intelligence · Computer Science 2025-08-05 Mingchen Mei , Yi Li , YiYao Qian , Zijun Jia

Existing LLMs-post-training techniques are broadly categorized into supervised fine-tuning (SFT) and reinforcement fine-tuning (RFT). Each paradigm presents a distinct trade-off: (1) SFT excels at mimicking demonstration data, but can lead…

Machine Learning · Computer Science 2026-05-18 Zeyu Huang , Tianhao Cheng , Zihan Qiu , Zili Wang , Yinghui Xu , Edoardo M. Ponti , Ivan Titov

The numerical solution of an ordinary differential equation can be interpreted as the exact solution of a nearby modified equation. Investigating the behaviour of numerical solutions by analysing the modified equation is known as backward…

Numerical Analysis · Mathematics 2022-12-12 Robert I McLachlan , Christian Offen

Gradual verification, which supports explicitly partial specifications and verifies them with a combination of static and dynamic checks, makes verification more incremental and provides earlier feedback to developers. While an abstract,…

Programming Languages · Computer Science 2023-11-14 Conrad Zimmerman , Jenna DiVincenzo , Jonathan Aldrich