English
Related papers

Related papers: Reward-Weighted Sampling: Enhancing Non-Autoregres…

200 papers

Diffusion language models have emerged as a promising approach for text generation. One would naturally expect this method to be an efficient replacement for autoregressive models since multiple tokens can be sampled in parallel during each…

Machine Learning · Computer Science 2025-06-10 Guhao Feng , Yihan Geng , Jian Guan , Wei Wu , Liwei Wang , Di He

Controlled text generation allows for enforcing user-defined constraints on large language model outputs, an increasingly important field as LLMs become more prevalent in everyday life. One common approach uses energy-based decoding, which…

Computation and Language · Computer Science 2025-02-07 Patrick Pynadath , Ruqi Zhang

Diffusion models that are based on iterative denoising have been recently proposed and leveraged in various generation tasks like image generation. Whereas, as a way inherently built for continuous data, existing diffusion models still have…

Computation and Language · Computer Science 2023-04-11 Jiaao Chen , Aston Zhang , Mu Li , Alex Smola , Diyi Yang

We present significant extensions to diffusion-based sequence generation models, blurring the line with autoregressive language models. We introduce hyperschedules, which assign distinct noise schedules to individual token positions,…

Machine Learning · Computer Science 2025-10-08 Nima Fathi , Torsten Scholak , Pierre-André Noël

Reinforcement Learning (RL) has emerged as a powerful paradigm for advancing Large Language Models (LLMs), achieving remarkable performance in complex reasoning domains such as mathematics and code generation. However, current RL methods…

Machine Learning · Computer Science 2025-12-10 Jingyu Xing , Chenwei Tang , Xinyu Liu , Deng Xiong , Shudong Huang , Wei Ju , Jiancheng Lv , Ziyue Qiao

Retrieval-Augmented Generation (RAG) improves factual grounding by incorporating external knowledge into language model generation. However, when retrieved context is noisy, unreliable, or inconsistent with the model's parametric knowledge,…

Computation and Language · Computer Science 2026-04-06 Jaemin Kim , Jong Chul Ye

Masked diffusion language models (MDMs) uniquely support any-order generation, with confidence-based decoding currently serving as the de facto standard inference policy. To optimize for this, recent training schemes attempt to align…

Artificial Intelligence · Computer Science 2026-05-29 Dueun Kim , Albert No

Reasoning with large language models often benefits from generating multiple chains-of-thought, but existing aggregation strategies are typically trajectory-level (e.g., selecting the best trace or voting on the final answer), discarding…

Computation and Language · Computer Science 2026-02-27 Roy Miles , Aysim Toker , Andreea-Maria Oncescu , Songcen Xu , Jiankang Deng , Ismail Elezi

The iterative and stochastic nature of diffusion models enables test-time scaling, whereby spending additional compute during denoising generates higher-fidelity samples. Increasing the number of denoising steps is the primary scaling axis,…

Machine Learning · Computer Science 2025-09-09 Vignav Ramesh , Morteza Mardani

Reward Feedback Learning (ReFL) has recently shown great potential in aligning model outputs with human preferences across various generative tasks. In this work, we introduce a ReFL framework, named DiffusionReward, to the Blind Face…

Computer Vision and Pattern Recognition · Computer Science 2025-05-26 Bin Wu , Wei Wang , Yahui Liu , Zixiang Li , Yao Zhao

Diffusion models have gained attention for their success in modeling complex distributions, achieving impressive perceptual quality in SR tasks. However, existing diffusion-based SR methods often suffer from high computational costs,…

Computer Vision and Pattern Recognition · Computer Science 2025-05-22 Rui Qin , Qijie Wang , Ming Sun , Haowei Zhu , Chao Zhou , Bin Wang

In sequence-to-sequence Transformer ASR, autoregressive (AR) models achieve strong accuracy but suffer from slow decoding, while non-autoregressive (NAR) models enable parallel decoding at the cost of degraded performance. We propose a…

Audio and Speech Processing · Electrical Eng. & Systems 2026-02-26 Hao Yen , Pin-Jui Ku , Ante Jukić , Sabato Marco Siniscalchi

Autoregressive language models (ARMs) have been shown to memorize and occasionally reproduce training data verbatim, raising concerns about privacy and copyright liability. Diffusion language models (DLMs) have recently emerged as a…

Computation and Language · Computer Science 2026-03-04 Xiaoyu Luo , Wenrui Yu , Qiongxiu Li , Johannes Bjerva

Masked diffusion models (MDMs), which leverage bidirectional attention and a denoising process, are narrowing the performance gap with autoregressive models (ARMs). However, their internal attention mechanisms remain under-explored. This…

Artificial Intelligence · Computer Science 2026-01-13 Pengcheng Huang , Tianming Liu , Zhenghao Liu , Yukun Yan , Shuo Wang , Tong Xiao , Zulong Chen , Maosong Sun

We introduce a novel approach to large language model (LLM) distillation by formulating it as a constrained reinforcement learning problem. While recent work has begun exploring the integration of task-specific rewards into distillation…

Machine Learning · Computer Science 2025-09-30 Matthieu Zimmer , Xiaotong Ji , Tu Nguyen , Haitham Bou Ammar

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an indispensable paradigm for enhancing reasoning in Large Language Models (LLMs). However, standard policy optimization methods, such as Group Relative Policy…

Machine Learning · Computer Science 2026-02-09 Pengyi Li , Elizaveta Goncharova , Andrey Kuznetsov , Ivan Oseledets

We introduce Autoregressive Diffusion Models (ARDMs), a model class encompassing and generalizing order-agnostic autoregressive models (Uria et al., 2014) and absorbing discrete diffusion (Austin et al., 2021), which we show are special…

Machine Learning · Computer Science 2022-02-03 Emiel Hoogeboom , Alexey A. Gritsenko , Jasmijn Bastings , Ben Poole , Rianne van den Berg , Tim Salimans

Publicly available, large pretrained LanguageModels (LMs) generate text with remarkable quality, but only sequentially from left to right. As a result, they are not immediately applicable to generation tasks that break the unidirectional…

Computation and Language · Computer Science 2021-12-28 Peter West , Ximing Lu , Ari Holtzman , Chandra Bhagavatula , Jena Hwang , Yejin Choi

Improving the reasoning capabilities of diffusion-based large language models (dLLMs) through reinforcement learning (RL) remains an open problem. The intractability of dLLMs likelihood function necessitates approximating the current, old,…

Machine Learning · Computer Science 2026-02-17 Xiaohang Tang , Rares Dolga , Sangwoong Yoon , Ilija Bogunovic

Reward models (RMs) play a critical role in enhancing the reasoning performance of LLMs. For example, they can provide training signals to finetune LLMs during reinforcement learning (RL) and help select the best answer from multiple…

Computation and Language · Computer Science 2025-10-06 Qiyuan Liu , Hao Xu , Xuhong Chen , Wei Chen , Yee Whye Teh , Ning Miao