We propose a novel conditioned text generation model. It draws inspiration from traditional template-based text generation techniques, where the source provides the content (i.e., what to say), and the template influences how to say it. Building on the successful encoder-decoder paradigm, it first encodes the content representation from the given input text; to produce the output, it retrieves exemplar text from the training data as "soft templates," which are then used to construct an exemplar-specific decoder. We evaluate the proposed model on abstractive text summarization and data-to-text generation. Empirical results show that this model achieves strong performance and outperforms comparable baselines.
AdaSD: Adaptive Speculative Decoding for Efficient Language Model Inference
Institute of Information Science, Academia Sinica（学术院信息研究所）；Department of Computer Science and Information Engineering, National Taiwan University（台湾大学计算机科学与信息工程系）
Adaptive Contrastive Decoding in Retrieval-Augmented Generation for Handling Noisy Contexts
Seoul National University（首尔大学）；Ewha Womans University（梨花女子大学）；NAVER Cloud（NAVER云）；KAIST AI（韩国科学技术院AI学院）；NAVER AI LAB（NAVER AI实验室）；Hanyang University（汉阳大学）
AdaPLD: Adaptive Retrieval and Reuse for Efficient Model-Free Speculative Decoding
School of Computer Science and Technology, Beijing Institute of Technology（北京理工大学计算机科学与技术学院）；Department of Mathematical Sciences, Tsinghua University（清华大学数学科学部）；JDT AI Infra（京东AI基础设施）
DREAM: Drafting with Refined Target Features and Entropy-Adaptive Cross-Attention Fusion for Multimodal Speculative Decoding
Courant Institute of Mathematical Sciences, New York University（纽约大学数学科学学院）；Tandon School of Engineering, New York University（纽约大学工程学院）；Cerebras Systems Inc.（Cerebras Systems公司）；University of Pennsylvania（宾夕法尼亚大学）
University of Southern California（南加州大学）；University of Oklahoma（俄克拉荷马大学）
Automatic extraction of product attribute values is an important enabling technology in e-Commerce platforms. This task is usually modeled using sequence labeling architectures, with several extensions to handle multi-attribute extraction. One line of previous work constructs attribute-specific models, through separate decoders or entirely separate models. However, this approach constrains knowledge sharing across different attributes. Other contributions use a single multi-attribute model, with different techniques to embed attribute information. But sharing the entire network parameters acro…
Learning to Draft: Adaptive Speculative Decoding with Reinforcement Learning
National Key Laboratory for Multimedia Information Processing, Peking University（多媒体信息处理国家级重点实验室，北京大学）；School of Computer Science, Peking University（计算机科学学院，北京大学）；Microsoft Research Asia（微软亚洲研究院）
Please refuse to answer me! Mitigating Over-Refusal in Large Language Models via Adaptive Contrastive Decoding
School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University（中山大学信息科学与技术学院深圳校区）；School of Information, Central University of Finance and Economics（中央财经大学信息学院）；School of Artificial Intelligence, Beijing Normal University（北京师范大学人工智能学院）；School of Computing Technologies, RMIT University（皇家墨尔本理工大学计算技术学院）
AdaEAGLE: Optimizing Speculative Decoding via Explicit Modeling of Adaptive Draft Structures
X-LANCE Lab（X-LANCE实验室）；Department of Computer Science and Engineering（计算机科学与工程系）；MoE Key Lab of Artificial Intelligence（教育部人工智能重点实验室）；SJTU AI Institute（上海交通大学人工智能研究院）；Shanghai Jiao Tong University（上海交通大学）
PACER: Blockwise Pre-verification for Speculative Decoding with Adaptive Length
X-LANCE Lab, School of Computer Science MoE Key Lab of Artificial Intelligence, SJTU AI Institute Shanghai Jiao Tong University（X-LANCE实验室，计算机科学学院，人工智能关键实验室，上海交通大学人工智能研究院）
$ϕ$-Decoding: Adaptive Foresight Sampling for Balanced Inference-Time Exploration and Exploitation
Shanghai AI Lab（上海人工智能实验室）；Xi’an Jiaotong University（西安交通大学）；The University of Hong Kong（香港大学）；Peking University（北京大学）；National University of Singapore（新加坡国立大学）
Mixture of Decoding: An Attention-Inspired Adaptive Decoding Strategy to Mitigate Hallucinations in Large Vision-Language Models
New Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA)（模式识别新技术实验室，自动化研究所，中国科学院）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Kuaishou Technology（快手科技）；Nanjing University（南京大学）
本文提出 Mixture of Decoding（MoD），通过比较原始与被注意图像 token 的输出一致性，自适应采用互补或对比解码策略，从而在多个基准上有效缓解 LVLMs 幻觉。
