English
Related papers

Related papers: Adaptive Cost-Efficient Evaluation for Reliable Pa…

200 papers

Current patent claim generation systems face three fundamental limitations: poor cross-jurisdictional generalization, inadequate semantic relationship modeling between claims and prior art, and unreliable quality assessment. We introduce a…

Computation and Language · Computer Science 2026-01-15 Chen-Wei Liang , Bin Guo , Zhen-Yuan Wei , Mu-Jiang-Shan Wang

Adaptive inference schemes reduce the cost of machine learning inference by assigning smaller models to easier examples, attempting to avoid invocation of larger models when possible. In this work we explore a simple, effective adaptive…

Machine Learning · Computer Science 2025-10-13 Steven Kolawole , Don Dennis , Ameet Talwalkar , Virginia Smith

Deploying machine learning models requires high model quality and needs to comply with application constraints. That motivates hyperparameter optimization (HPO) to tune model configurations under deployment constraints. The constraints…

Machine Learning · Computer Science 2022-08-08 Yi-Wei Chen , Chi Wang , Amin Saied , Rui Zhuang

This paper addresses the problem of providing runtime assurance for systems operating online under unknown and potentially time-varying data distributions. We propose Cost-Aware Adaptive Conformal Inference (ACI), a novel framework that…

Systems and Control · Electrical Eng. & Systems 2026-05-26 Taoran Wu , Jingduo Pan , Luke Ong , Bai Xue

LLMs' overconfidence, particularly when hallucinating, poses a significant challenge for the deployment of the models in safety-critical settings and makes a reliable estimation of uncertainty necessary. Existing approaches for uncertainty…

Machine Learning · Computer Science 2026-05-26 Hamed Karimi , Vaishali Meyappan , Reza Samavi

While Chain-of-Thought (CoT) prompting empowers Large Language Models (LLMs), ensuring reasoning reliability remains an open challenge. Contrary to the prevailing cascading failure hypothesis which posits that early errors are most…

Computation and Language · Computer Science 2026-03-04 Dongxu Zhang , Yujun Wu , Yiding Sun , Jinnan Yang , Ning Yang , Jihua Zhu , Miao Xin , Baoliang Tian

LLM cascades and model routing promise lower inference cost by sending easy queries to a small model and escalating hard ones to a large model, but most deployed routers use uncalibrated confidence scores and require per-workload threshold…

Machine Learning · Computer Science 2026-05-20 Varun Kotte

Large Language Models (LLMs) face significant inference latency challenges stemming from their autoregressive design and large size. To address this, speculative decoding emerges as a solution, enabling the simultaneous generation and…

Computation and Language · Computer Science 2026-02-27 Yinrong Hong , Zhiquan Tan , Kai Hu

Cross Entropy (CE) has an important role in machine learning and, in particular, in neural networks. It is commonly used in neural networks as the cost between the known distribution of the label and the Softmax/Sigmoid output. In this…

Machine Learning · Computer Science 2020-07-17 Ron Shoham , Haim Permuter

LLM agents that store knowledge as natural language suffer steep retrieval degradation as condition count grows, often struggle to compose learned rules reliably, and typically lack explicit mechanisms to detect stale or adversarial…

Artificial Intelligence · Computer Science 2026-03-11 Arash Shahmansoori

Large Language Models (LLMs) have recently advanced the field of Automated Theorem Proving (ATP), attaining substantial performance gains through widely adopted test-time scaling strategies, notably reflective Chain-of-Thought (CoT)…

Computation and Language · Computer Science 2025-09-17 Mukai Li , Linfeng Song , Zhenwen Liang , Jiahao Xu , Shansan Gong , Qi Liu , Haitao Mi , Dong Yu

Large language models excel at reasoning but lack key aspects of introspection, including anticipating their own success and the computation required to achieve it. Humans use real-time introspection to decide how much effort to invest,…

Machine Learning · Computer Science 2025-12-24 Rohin Manvi , Joey Hong , Tim Seyde , Maxime Labonne , Mathias Lechner , Sergey Levine

Test time adaptation (TTA) equips deep learning models to handle unseen test data that deviates from the training distribution, even when source data is inaccessible. While traditional TTA methods often rely on entropy as a confidence…

Machine Learning · Computer Science 2024-09-17 Afshar Shamsi , Rejisa Becirovic , Ahmadreza Argha , Ehsan Abbasnejad , Hamid Alinejad-Rokny , Arash Mohammadi

Reinforcement Learning with Verifiable Rewards (RLVR) has become the leading paradigm for enhancing reasoning in Large Language Models (LLMs). However, standard RLVR algorithms suffer from a well-documented pathology: while they improve…

Machine Learning · Computer Science 2026-02-26 Yuanda Xu , Hejian Sang , Zhengze Zhou , Ran He , Zhipeng Wang

Vision-language models (VLMs) exhibit remarkable zero-shot generalization but suffer performance degradation under distribution shifts in downstream tasks, particularly in the absence of labeled data. Test-Time Adaptation (TTA) addresses…

Computer Vision and Pattern Recognition · Computer Science 2025-11-17 Khanh-Binh Nguyen , Phuoc-Nguyen Bui , Hyunseung Choo , Duc Thanh Nguyen

The surge in generative AI workloads has created a need for scalable inference systems that can flexibly harness both GPUs and specialized accelerators while containing operational costs. This paper proposes a hardware-agnostic control loop…

Performance · Computer Science 2025-03-28 Yahav Biran , Imry Kissos

Agents built on large language models (LLMs) rely on a range of reliability techniques, including retry, majority voting, and self-consistency, that have been developed in parallel rather than within a common analytical framework. We…

Machine Learning · Computer Science 2026-05-12 Hamed Omidvar , Vahideh Akhlaghi

Increasing the thinking budget of AI models can significantly improve accuracy, but not all questions warrant the same amount of reasoning. Users may prefer to allocate different amounts of reasoning effort depending on how they value…

Artificial Intelligence · Computer Science 2025-11-13 Michael Kleinman , Matthew Trager , Alessandro Achille , Wei Xia , Stefano Soatto

In the era of Model-as-a-Service, organizations increasingly rely on third-party AI models for rapid deployment. However, the dynamic nature of emerging AI applications, the continual introduction of new datasets, and the growing number of…

Machine Learning · Computer Science 2026-02-10 Zihan Zhu , Yanqiu Wu , Qiongkai Xu

While Large Language Models (LLMs) have demonstrated exceptional proficiency in code completion, they typically adhere to a Hard Completion (HC) paradigm, compelling the generation of fully concrete code even amidst insufficient context.…

Computation and Language · Computer Science 2026-04-03 Liang Zhu , Haolin Chen , Lidong Zhao , Xian Wu
‹ Prev 1 2 3 10 Next ›