English
Related papers

Related papers: Learnable Chernoff Baselines for Inference-Time Al…

200 papers

In this paper we are concerned with the learnability of nonlocal interaction kernels for first order systems modeling certain social interactions, from observations of realizations of their dynamics. This paper is the first of a series on…

Dynamical Systems · Mathematics 2016-02-17 Mattia Bongini , Massimo Fornasier , Markus Hansen , Mauro Maggioni

Sequential neural posterior estimation (SNPE) techniques have been recently proposed for dealing with simulation-based models with intractable likelihoods. Unlike approximate Bayesian computation, SNPE techniques learn the posterior from…

Machine Learning · Statistics 2025-01-17 Yifei Xiong , Xiliang Yang , Sanguo Zhang , Zhijian He

By allowing models to predict without task-specific training, in-context learning (ICL) with pretrained LLMs has enormous potential in NLP. However, a number of problems persist in ICL. In particular, its performance is sensitive to the…

Computation and Language · Computer Science 2024-02-20 Zhichao Xu , Daniel Cohen , Bei Wang , Vivek Srikumar

Existing graph contrastive learning methods rely on augmentation techniques based on random perturbations (e.g., randomly adding or dropping edges and nodes). Nevertheless, altering certain edges or nodes can unexpectedly change the graph…

Machine Learning · Computer Science 2022-11-08 Huidong Liang , Xingjian Du , Bilei Zhu , Zejun Ma , Ke Chen , Junbin Gao

Reinforcement Learning with Verifiable Rewards (RLVR) has improved the reasoning abilities of Large Language Models (LLMs) by using rule-based binary feedback. However, current RLVR methods typically assign the same reward to every token.…

Machine Learning · Computer Science 2025-10-21 Guofu Xie , Yunsheng Shi , Hongtao Tian , Ting Yao , Xiao Zhang

Most recent machine learning research focuses on developing new classifiers for the sake of improving classification accuracy. With many well-performing state-of-the-art classifiers available, there is a growing need for understanding…

Machine Learning · Computer Science 2020-09-30 Jaehoon Koo , Diego Klabjan , Jean Utke

Reward models have become a staple in modern NLP, serving as not only a scalable text evaluator, but also an indispensable component in many alignment recipes and inference-time algorithms. However, while recent reward models increase…

Computation and Language · Computer Science 2025-09-22 Zhaofeng Wu , Michihiro Yasunaga , Andrew Cohen , Yoon Kim , Asli Celikyilmaz , Marjan Ghazvininejad

Appropriate credit assignment for delay rewards is a fundamental challenge for reinforcement learning. To tackle this problem, we introduce a delay reward calibration paradigm inspired from a classification perspective. We hypothesize that…

Machine Learning · Computer Science 2021-08-26 Yixuan Liu , Hu Wang , Xiaowei Wang , Xiaoyue Sun , Liuyue Jiang , Minhui Xue

Reinforcement Learning from Human Feedback (RLHF) enables powerful LLM alignment but can introduce reward hacking - models exploit spurious correlations in proxy rewards without genuine alignment. Compounding this, the objectives…

Artificial Intelligence · Computer Science 2026-02-24 Mohammad Beigi , Ming Jin , Junshan Zhang , Jiaxin Zhang , Qifan Wang , Lifu Huang

With the widespread deployment of deep learning models, they influence their environment in various ways. The induced distribution shifts can lead to unexpected performance degradation in deployed models. Existing methods to anticipate…

Actively inferring user preferences, for example by asking good questions, is important for any human-facing decision-making system. Active inference allows such systems to adapt and personalize themselves to nuanced individual preferences.…

Computation and Language · Computer Science 2024-06-27 Wasu Top Piriyakulkij , Volodymyr Kuleshov , Kevin Ellis

Concept bottleneck models (CBMs) are interpretable neural networks that first predict labels for human-interpretable concepts relevant to the prediction task, and then predict the final label based on the concept label predictions. We…

Machine Learning · Computer Science 2023-04-28 Kushal Chauhan , Rishabh Tiwari , Jan Freyberg , Pradeep Shenoy , Krishnamurthy Dvijotham

Reinforcement Learning with Verifiable Rewards (RLVR) is a central paradigm for turning large language models (LLMs) into reliable problem solvers, especially in logic-heavy domains. Despite its empirical success, it remains unclear whether…

Machine Learning · Computer Science 2026-01-27 Mingyuan Fan , Weiguang Han , Daixin Wang , Cen Chen , Zhiqiang Zhang , Jun Zhou

Diffusion language models (DLMs) have recently emerged as a promising alternative to autoregressive (AR) approaches, enabling parallel token generation beyond a rigid left-to-right order. Despite growing empirical success, the theoretical…

Machine Learning · Computer Science 2026-02-24 Yunxiao Zhao , Changxiao Cai

Scaling test-time computation with reinforcement learning (RL) has emerged as a reliable path to improve large language models (LLM) reasoning ability. Yet, outcome-based reward often incentivizes models to be overconfident, leading to…

Machine Learning · Computer Science 2026-04-28 Liaoyaqi Wang , Chunsheng Zuo , William Jurayj , Benjamin Van Durme , Anqi Liu

Restricted Boltzmann Machines (RBMs) are generative models which can learn useful representations from samples of a dataset in an unsupervised fashion. They have been widely employed as an unsupervised pre-training method in machine…

Machine Learning · Statistics 2013-09-13 Chris Häusler , Alex Susemihl , Martin P Nawrot , Manfred Opper

Inference after model selection presents computational challenges when dealing with intractable conditional distributions. Markov chain Monte Carlo (MCMC) is a common method for sampling from these distributions, but its slow convergence…

Methodology · Statistics 2023-08-22 Sifan Liu

Efficient sampling of complex high-dimensional probability distributions is a central task in computational science. Machine learning methods like autoregressive neural networks, used with Markov chain Monte Carlo sampling, provide good…

Statistical Mechanics · Physics 2021-11-11 Dian Wu , Riccardo Rossi , Giuseppe Carleo

The primary objective of methods in continual learning is to learn tasks in a sequential manner over time (sometimes from a stream of data), while mitigating the detrimental phenomenon of catastrophic forgetting. This paper proposes a…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Nisha L. Raichur , Lucas Heublein , Tobias Feigl , Alexander Rügamer , Christopher Mutschler , Felix Ott

Inference-time controllable generation is essential for real-world applications of unconditional diffusion models. However, most existing techniques focus on individual samples, struggling in applications that require the sample population…

Machine Learning · Computer Science 2026-05-11 Hao Luan , See-Kiong Ng , Chun Kai Ling
‹ Prev 1 8 9 10 Next ›