中文
相关论文

相关论文: Self-Distilled Trajectory-Aware Boltzmann Modeling…

200 篇论文

Diffusion large language models (DLLMs) have emerged as powerful generative models with the promise of fast text generation through parallel decoding. However, realizing this potential in practice remains challenging: reducing the number of…

Diffusion large language models (dLLMs) offer a promising paradigm for parallel text generation, but in practice they face an accuracy-parallelism trade-off, where increasing tokens per forward (TPF) often degrades generation quality.…

计算与语言 · 计算机科学 2026-05-12 Haoyang Zhou , Li Kong , Shijie Ren , Xiting Wang , Shuang Liang , Guowei Wang , Zhenxuan Pan

Diffusion language models (DLMs) offer a promising path toward low-latency generation through parallel decoding, but their practical efficiency depends heavily on the decoding trajectory. In practice, this advantage often fails to fully…

计算与语言 · 计算机科学 2026-04-02 Lingjie Chen , Ruizhong Qiu , Yuyu Fan , Yanjun Zhao , Hanghang Tong

Diffusion Language Models (DLMs) have recently achieved strong results in text generation. However, their multi-step sampling leads to slow inference, limiting practical use. To address this, we extend Inverse Distillation, a technique…

Diffusion language models, as a promising alternative to traditional autoregressive (AR) models, enable faster generation and richer conditioning on bidirectional context. However, they suffer from a key discrepancy between training and…

机器学习 · 计算机科学 2025-09-26 Haoyu He , Katrin Renz , Yong Cao , Andreas Geiger

Diffusion Language Models (DLMs) are rapidly emerging as a powerful and promising alternative to the dominant autoregressive (AR) paradigm. By generating tokens in parallel through an iterative denoising process, DLMs possess inherent…

计算与语言 · 计算机科学 2025-12-08 Tianyi Li , Mingda Chen , Bowei Guo , Zhiqiang Shen

Diffusion large language models (dLLMs) offer capabilities beyond those of autoregressive (AR) LLMs, such as parallel decoding and random-order generation. However, realizing these benefits in practice is non-trivial, as dLLMs inherently…

机器学习 · 计算机科学 2026-01-30 Yu-Yang Qian , Junda Su , Lanxiang Hu , Peiyuan Zhang , Zhijie Deng , Peng Zhao , Hao Zhang

Diffusion Large Language Models (dLLMs) are rapidly emerging alongside autoregressive models as a powerful paradigm for complex reasoning, with reinforcement learning increasingly used for downstream alignment. Existing trajectory-based RL…

机器学习 · 计算机科学 2025-11-20 Ranfei Chen , Ming Chen , Kaifei Wang

Diffusion Large Language Models (dLLMs) introduce a new paradigm for language generation, which in turn presents new challenges for aligning them with human preferences. In this work, we aim to improve the policy optimization for dLLMs by…

Trajectory prediction is a fundamental task in Autonomous Vehicles (AVs) and Intelligent Transportation Systems (ITS), supporting efficient motion planning and real-time traffic safety management. Diffusion models have recently demonstrated…

人工智能 · 计算机科学 2025-10-02 Bingzhang Wang , Kehua Chen , Yinhai Wang

The landscape of high-performance image generation models is currently shifting from the inefficient multi-step ones to the efficient few-step counterparts (e.g, Z-Image-Turbo and FLUX.2-klein). However, these models present significant…

计算机视觉与模式识别 · 计算机科学 2026-05-27 Dengyang Jiang , Xin Jin , Dongyang Liu , Zanyi Wang , Mingzhe Zheng , Ruoyi Du , Xiangpeng Yang , Qilong Wu , Zhen Li , Peng Gao , Harry Yang , Steven Hoi

Diffusion-based language models (dLLMs) have emerged as a promising alternative to autoregressive language models, offering the potential for parallel token generation and bidirectional context modeling. However, harnessing this flexibility…

计算与语言 · 计算机科学 2026-05-28 Jiyeon Kim , Sungik Choi , Yongrae Jo , Moontae Lee , Minjoon Seo

Reinforcement learning (RL) can be used to improve the policy (denoiser) of diffusion large language models (dLLMs), while being hindered by the intractability of the policy likelihood. A dominant and efficient family of methods replaces…

机器学习 · 计算机科学 2026-05-29 Xiaohang Tang , Keyue Jiang , Che Liu , Qifang Zhao , Xiaoxiao Xu , Sangwoong Yoon , Ilija Bogunovic

We propose TraceRL, a trajectory-aware reinforcement learning framework for diffusion language models (DLMs) that incorporates preferred inference trajectory into post-training, and is applicable across different architectures. Equipped…

计算与语言 · 计算机科学 2025-09-09 Yinjie Wang , Ling Yang , Bowen Li , Ye Tian , Ke Shen , Mengdi Wang

In this work, we propose Dimple, the first Discrete Diffusion Multimodal Large Language Model (DMLLM). We observe that training with a purely discrete diffusion approach leads to significant training instability, suboptimal performance, and…

计算机视觉与模式识别 · 计算机科学 2025-05-27 Runpeng Yu , Xinyin Ma , Xinchao Wang

Diffusion Language Models (dLLMs) have emerged as promising alternatives to Auto-Regressive (AR) models. While recent efforts have validated their pre-training potential and accelerated inference speeds, the post-training landscape for…

机器学习 · 计算机科学 2026-01-07 Ying Zhu , Jiaxin Wan , Xiaoran Liu , Siyang He , Qiqi Wang , Xu Guo , Tianyi Liang , Zengfeng Huang , Ziwei He , Xipeng Qiu

Discrete diffusion models have recently emerged as strong alternatives to autoregressive language models, matching their performance through large-scale training. However, inference-time control remains relatively underexplored. In this…

机器学习 · 计算机科学 2026-04-09 Meihua Dang , Jiaqi Han , Minkai Xu , Kai Xu , Akash Srivastava , Stefano Ermon

Diffusion Large Language Models (DLLMs) promise fast parallel generation, yet open-source DLLMs still face a severe quality-speed trade-off: accelerating decoding by revealing multiple tokens often causes substantial quality degradation. We…

计算与语言 · 计算机科学 2026-05-19 Fanqin Zeng , Feng Hong , Geng Yu , Huangjie Zheng , Xiaofeng Cao , Ya Zhang , Bo Han , Yanfeng Wang , Jiangchao Yao

Diffusion language models intrinsically fail to capture correlations between decoded tokens, which leads to a harsh trade-off between sampling quality and throughput. To solve this issue, we propose DiLaDiff, a variant of masked diffusion…

机器学习 · 计算机科学 2026-05-25 Jean-Marie Lemercier , Tomas Geffner , Karsten Kreis , Morteza Mardani , Arash Vahdat , Ante Jukić

Diffusion language models (DLMs) are an attractive alternative to autoregressive models because they promise sublinear-time, parallel generation, yet practical gains remain elusive as high-quality samples still demand hundreds of refinement…

机器学习 · 计算机科学 2026-05-04 Hasan Amin , Yuan Gao , Yaser Souri , Subhojit Som , Ming Yin , Rajiv Khanna , Xia Song
‹ 上一页 1 2 3 10 下一页 ›