English
Related papers

Related papers: CAPS: Cascaded Adaptive Pairwise Selection for Eff…

200 papers

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

Industrial experimentation requires both factor screening to identify critical variables and response optimization to find optimal operating conditions. Traditional approaches treat these as separate phases, necessitating costly sequential…

Methodology · Statistics 2026-04-28 Kumarjit Pathak

Cascading multiple pre-trained models is an effective way to compose an end-to-end system. However, fine-tuning the full cascaded model is parameter and memory inefficient and our observations reveal that only applying adapter modules on…

Machine Learning · Computer Science 2023-10-30 Yingying Gao , Shilei Zhang , Zihao Cui , Chao Deng , Junlan Feng

Conformal prediction (CP) is widely presented as distribution-free predictive inference with finite-sample marginal coverage under exchangeability. We argue that CP is best understood as a rank-calibrated descendant of the…

Statistics Theory · Mathematics 2025-12-30 Jyotishka Datta , Nicholas G. Polson , Vadim Sokolov , Daniel Zantedeschi

This paper proposes a general adaptive procedure for budget-limited predictor design in high dimensions called two-stage Sampling, Prediction and Adaptive Regression via Correlation Screening (SPARCS). SPARCS can be applied to high…

Machine Learning · Statistics 2016-11-18 Hamed Firouzi , Alfred Hero , Bala Rajaratnam

Vision-Language Models (VLMs) have achieved strong performance on general multimodal reasoning, yet remain challenged in integrating nonlocal visual information to support semantically underdetermined visual reasoning. We describe this…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Tengda Guo , Jie Leng , Hanlei Li , Yaoyuan Liang , Qingyue Zhang , Dian Yang , Mingyu Zhang , Yuhua Fu , Shao-Lun Huang

Automated patent claim validation demands low error tolerance. However, existing approaches face a rigidity-resource dilemma: lightweight encoders cannot track long-range legal dependencies, while exhaustive LLM verification incurs 4-5X…

Computation and Language · Computer Science 2026-05-28 Yongmin Yoo , Qiongkai Xu , Longbing Cao

Chain-of-thought (CoT) reasoning with self-consistency improves performance by aggregating multiple sampled reasoning paths. In this setting, correctness is no longer tied to a single reasoning trace but to the aggregation rule over a pool…

Machine Learning · Statistics 2026-05-15 Yu Gu , Zijun Yu , Vahid Partovi Nia , Masoud Asgharian

Accuracy predictor is trained to predict the validation accuracy of an network from its architecture encoding. It can effectively assist in designing networks and improving Neural Architecture Search(NAS) efficiency. However, a…

Computer Vision and Pattern Recognition · Computer Science 2021-08-13 Ruyi Zhang , Ziwei Yang , Zhi Yang , Xubo Yang , Lei Wang , Zheyang Li

Recent advances in vision-language foundational models, such as CLIP, have demonstrated significant strides in zero-shot classification. However, the extensive parameterization of models like CLIP necessitates a resource-intensive…

Computer Vision and Pattern Recognition · Computer Science 2024-11-08 Qijie Wang , Guandu Liu , Bin Wang

Neural predictors are effective in boosting the time-consuming performance evaluation stage in neural architecture search (NAS), owing to their direct estimation of unseen architectures. Despite the effectiveness, training a powerful neural…

Machine Learning · Computer Science 2024-06-05 Han Ji , Yuqi Feng , Yanan Sun

Context-augmented generation (CAG) techniques, including RAG and ICL, require the efficient combination of multiple contexts to generate responses to user queries. Directly inputting these contexts as a sequence introduces a considerable…

Machine Learning · Computer Science 2025-02-13 Xinyu Yang , Tianqi Chen , Beidi Chen

This paper considers multiple binary hypothesis tests with adaptive allocation of sensing resources from a shared budget over a small number of stages. A Bayesian formulation is provided for the multistage allocation problem of minimizing…

Methodology · Statistics 2014-11-05 Dennis Wei

Vision-language models achieve strong performance across a wide range of multimodal understanding and reasoning tasks, yet their multi-step reasoning remains unstable. Repeated sampling over the same input often produces divergent reasoning…

Computer Vision and Pattern Recognition · Computer Science 2026-01-14 Chaoyu Li , Deeparghya Dutta Barua , Fei Tao , Pooyan Fazli

Machine-learning classifiers provide high quality of service in classification tasks. Research now targets cost reduction measured in terms of average processing time or energy per solution. Revisiting the concept of cascaded classifiers,…

Machine Learning · Computer Science 2022-03-10 Cecilia Latotzke , Johnson Loh , Tobias Gemmeke

Pairwise matching cost aggregation is a crucial step for modern learning-based Multi-view Stereo (MVS). Prior works adopt an early aggregation scheme, which adds up pairwise costs into an intermediate cost. However, we analyze that this…

Computer Vision and Pattern Recognition · Computer Science 2024-01-25 Jiang Wu , Rui Li , Yu Zhu , Wenxun Zhao , Jinqiu Sun , Yanning Zhang

Many recent successes in sentence representation learning have been achieved by simply fine-tuning on the Natural Language Inference (NLI) datasets with triplet loss or siamese loss. Nevertheless, they share a common weakness: sentences in…

Computation and Language · Computer Science 2022-02-01 Dejiao Zhang , Shang-Wen Li , Wei Xiao , Henghui Zhu , Ramesh Nallapati , Andrew O. Arnold , Bing Xiang

Scaling the size of language models to tens of billions of parameters has led to impressive performance on a wide range of tasks. At generation, these models are used auto-regressively, requiring a forward pass for each generated token, and…

Computation and Language · Computer Science 2023-11-23 Giovanni Monea , Armand Joulin , Edouard Grave

We develop a novel approach for confidently accelerating inference in the large and expensive multilayer Transformers that are now ubiquitous in natural language processing (NLP). Amortized or approximate computational methods increase…

Computation and Language · Computer Science 2021-09-10 Tal Schuster , Adam Fisch , Tommi Jaakkola , Regina Barzilay

Large language models (LLMs) have revolutionized natural language processing by solving a wide range of tasks simply guided by a prompt. Yet their performance is highly sensitive to prompt formulation. While automatic prompt optimization…

Computation and Language · Computer Science 2025-06-18 Tom Zehle , Moritz Schlager , Timo Heiß , Matthias Feurer