English
Related papers

Related papers: Scalable Power Sampling: Unlocking Efficient, Trai…

200 papers

While recent work has shown that scores from models trained by the ubiquitous masked language modeling (MLM) objective effectively discriminate probable from improbable sequences, it is still an open question if these MLMs specify a…

Machine Learning · Computer Science 2022-03-16 Kartik Goyal , Chris Dyer , Taylor Berg-Kirkpatrick

Recent papers have demonstrated the possibility of energy-based text generation by adapting gradient-based sampling algorithms, a paradigm of MCMC algorithms that promises fast convergence. However, as we show in this paper, previous…

Computation and Language · Computer Science 2024-01-01 Li Du , Afra Amini , Lucas Torroba Hennigen , Xinyan Velocity Yu , Jason Eisner , Holden Lee , Ryan Cotterell

This study investigates the effects of Markov chain Monte Carlo (MCMC) sampling in unsupervised Maximum Likelihood (ML) learning. Our attention is restricted to the family of unnormalized probability densities for which the negative log…

Machine Learning · Statistics 2019-12-02 Erik Nijkamp , Mitch Hill , Tian Han , Song-Chun Zhu , Ying Nian Wu

Reinforcement Learning (RL) post-training has emerged as the dominant paradigm for eliciting mathematical reasoning in Large Language Models (LLMs), yet prevailing techniques such as GRPO and DAPO distribute rollout and gradient budgets…

Machine Learning · Computer Science 2026-05-20 Peng Cui , Boyao Yang , Jun Zhu

Improving Multi-modal Large Language Models (MLLMs) in the post-training stage typically relies on supervised fine-tuning (SFT) or reinforcement learning (RL), which require expensive and manually annotated multi-modal data--an ultimately…

Computation and Language · Computer Science 2025-10-28 Lai Wei , Yuting Li , Chen Wang , Yue Wang , Linghe Kong , Weiran Huang , Lichao Sun

Reinforcement learning (RL) has enabled machine learning models to achieve significant advances in many fields. Most recently, RL has empowered frontier language models to solve challenging math, science, and coding problems. However,…

Machine Learning · Computer Science 2025-06-30 Mihir Prabhudesai , Lili Chen , Alex Ippoliti , Katerina Fragkiadaki , Hao Liu , Deepak Pathak

Training energy-based probabilistic models is confronted with apparently intractable sums, whose Monte Carlo estimation requires sampling from the estimated probability distribution in the inner loop of training. This can be approximately…

Machine Learning · Computer Science 2016-06-13 Taesup Kim , Yoshua Bengio

Autoregressive language models are next-token predictors and have been criticized for only optimizing surface plausibility (i.e., local coherence) rather than maintaining correct latent-state representations (i.e., global coherence).…

Computation and Language · Computer Science 2026-01-21 Xucong Hu , Jian-Qiao Zhu

Multimodal Large Language Models (MLLMs) perform well in single-image visual grounding but struggle with real-world tasks that demand cross-image reasoning and multi-modal instructions. To address this, we adopt a reinforcement learning…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Bob Zhang , Haoran Li , Tao Zhang , Jianan Li , Cilin Yan , Xikai Liu , Jiayin Cai , Yanbin Hao

Reward models have been increasingly critical for improving the reasoning capability of LLMs. Existing research has shown that a well-trained reward model can substantially improve model performances at inference time via search. However,…

Machine Learning · Computer Science 2024-11-28 Jiaxuan Gao , Shusheng Xu , Wenjie Ye , Weilin Liu , Chuyi He , Wei Fu , Zhiyu Mei , Guangju Wang , Yi Wu

Large Language Models (LLMs) have exhibited an impressive capability to perform reasoning tasks, especially if they are encouraged to generate a sequence of intermediate steps. Reasoning performance can be improved by suitably combining…

Computation and Language · Computer Science 2025-04-11 Soumyasundar Pal , Didier Chételat , Yingxue Zhang , Mark Coates

Recent AI advancements, such as OpenAI's new models, are transforming LLMs into LRMs (Large Reasoning Models) that perform reasoning during inference, taking extra time and compute for higher-quality outputs. We aim to uncover the…

Artificial Intelligence · Computer Science 2025-02-11 Guanghao Ye , Khiem Duc Pham , Xinzhi Zhang , Sivakanth Gopi , Baolin Peng , Beibin Li , Janardhan Kulkarni , Huseyin A. Inan

Outcome-reward reinforcement learning (RL) is a common and increasingly significant way to refine the step-by-step reasoning of multimodal large language models (MLLMs). In the multiple-choice setting - a dominant format for multimodal…

Computer Vision and Pattern Recognition · Computer Science 2025-11-14 Jiahao Wang , Weiye Xu , Aijun Yang , Wengang Zhou , Lewei Lu , Houqiang Li , Xiaohua Wang , Jinguo Zhu

Markov Chain Monte Carlo (MCMC) methods sample from unnormalized probability distributions and offer guarantees of exact sampling. However, in the continuous case, unfavorable geometry of the target distribution can greatly limit the…

Machine Learning · Statistics 2020-10-09 Zengyi Li , Yubei Chen , Friedrich T. Sommer

Integrating large language models (LLMs) as priors in reinforcement learning (RL) offers significant advantages but comes with substantial computational costs. We present a principled cache-efficient framework for posterior sampling with…

Machine Learning · Computer Science 2025-09-30 Ibne Farabi Shihab , Sanjeda Akter , Anuj Sharma

Previous study suggest that powerful Large Language Models (LLMs) trained with Reinforcement Learning with Verifiable Rewards (RLVR) only refines reasoning path without improving the reasoning capacity in math tasks while…

Computation and Language · Computer Science 2025-05-29 Ran Li , Shimin Di , Yuchen Liu , Chen Jing , Yu Qiu , Lei Chen

Scaling model size and training data has led to great advances in the performance of Large Language Models (LLMs). However, the diminishing returns of this approach necessitate alternative methods to improve model capabilities, particularly…

Machine Learning · Computer Science 2025-11-05 Daman Arora , Andrea Zanette

Multimodal LLMs often produce fluent yet unreliable reasoning, exhibiting weak step-to-step coherence and insufficient visual grounding, largely because existing alignment approaches supervise only the final answer while ignoring the…

Computer Vision and Pattern Recognition · Computer Science 2025-12-30 Jesen Zhang , Ningyuan Liu , Kaitong Cai , Sidi Liu , Jing Yang , Ziliang Chen , Xiaofei Sun , Keze Wang

Recent advances in large language models (LLMs) have increasingly relied on reinforcement learning (RL) to improve their reasoning capabilities. Three types of approaches have been widely adopted: The first relies on a deep neural network…

Machine Learning · Computer Science 2026-05-19 Shijin Gong , Kai Ye , Jin Zhu , Xinyu Zhang , Hongyi Zhou , Chengchun Shi

This work presents an efficient approach for accelerating multilevel Markov Chain Monte Carlo (MCMC) sampling for large-scale problems using low-fidelity machine learning models. While conventional techniques for large-scale Bayesian…

Machine Learning · Statistics 2024-05-21 Sohail Reddy , Hillary Fairbanks