English
Related papers

Related papers: Efficient Test-Time Inference via Deterministic Ex…

200 papers

Diffusion Language Models (DLMs) have recently achieved significant success due to their any-order generation capabilities. However, existing inference methods typically rely on local, immediate-step metrics such as confidence or entropy…

Computation and Language · Computer Science 2025-12-03 Kecheng Chen , Ziru Liu , Xijia Tao , Hui Liu , Xinyu Fu , Suiyun Zhang , Dandan Tu , Lingpeng Kong , Rui Liu , Haoliang Li

Reinforcement learning (RL) with tree search has demonstrated superior performance in traditional reasoning tasks. Compared to conventional independent chain sampling strategies with outcome supervision, tree search enables better…

Machine Learning · Computer Science 2025-06-16 Zhenyu Hou , Ziniu Hu , Yujiang Li , Rui Lu , Jie Tang , Yuxiao Dong

Speculative decoding accelerates large language model (LLM) inference by using a lightweight draft model to propose tokens that are later verified by a stronger target model. While effective in centralized systems, its behavior in…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-18 Jingwei Song , Wanyi Chen , Xinyuan Song , Max , Chris Tong , Gufeng Chen , Tianyi Zhao , Eric Yang , Bill Shi , Lynn Ai

Large language models (LLMs) have shown outstanding performance across numerous real-world tasks. However, the autoregressive nature of these models makes the inference process slow and costly. Speculative decoding has emerged as a…

Artificial Intelligence · Computer Science 2025-03-17 Zongyue Qin , Zifan He , Neha Prakriya , Jason Cong , Yizhou Sun

While Large Language Models (LLMs) have advanced complex reasoning, prominent methods like the Tree of Thoughts (ToT) framework face a critical trade-off between exploration depth and computational efficiency. Existing ToT implementations…

Artificial Intelligence · Computer Science 2026-03-24 Xuanqi Gao , Haoyu Wang , Jun Sun , Shiqing Ma , Chao Shen

Self-ensembling techniques with diverse reasoning paths such as Self-Consistency have demonstrated remarkable performance gains in text generation with Large Language Models (LLMs). However, such techniques depend on the availability of an…

Computation and Language · Computer Science 2024-08-20 Sumanth Prabhu

Speculative decoding is an effective technique for accelerating large language model inference by drafting multiple tokens in parallel. In practice, its speedup is often bottlenecked by a rigid verification step that strictly enforces the…

Computation and Language · Computer Science 2026-04-10 Ziyi Wang , Siva Rajesh Kasa , Ankith M S , Santhosh Kumar Kasa , Jiaru Zou , Sumit Negi , Ruqi Zhang , Nan Jiang , Qifan Song

Sampling-based decoding strategies have been widely adopted for Large Language Models (LLMs) in numerous applications, targeting a balance between diversity and quality via temperature tuning and tail truncation. Considering the strong…

Computation and Language · Computer Science 2025-01-09 Yuxuan Zhou , Margret Keuper , Mario Fritz

Speculative decoding (SD) has emerged as an effective technique to accelerate large language model (LLM) inference without compromising output quality. However, the achievable speedup largely depends on the effectiveness of the drafting…

Computation and Language · Computer Science 2025-11-04 Min Fang , Zhihui Fu , Qibin Zhao , Jun Wang

Deliberative tree search is a cornerstone of modern Large Language Model (LLM) research, driving the pivot from brute-force scaling toward algorithmic efficiency. This single paradigm unifies two critical frontiers: \textbf{Test-Time…

This work presents a novel trie (prefix-tree)-based parallel decoding method that addresses the memory inefficiency of batch-based beam search. By sharing a single KV cache across beams with common prefixes, our approach dramatically…

Computation and Language · Computer Science 2025-09-23 Brian J Chan , MaoXun Huang , Jui-Hung Cheng , Chao-Ting Chen , Hen-Hsen Huang

While speculative decoding has recently appeared as a promising direction for accelerating the inference of large language models (LLMs), the speedup and scalability are strongly bounded by the token acceptance rate. Prevalent methods…

Machine Learning · Computer Science 2024-10-16 Yunfan Xiong , Ruoyu Zhang , Yanzeng Li , Tianhao Wu , Lei Zou

Large language models (LLMs) demand considerable computational, energy, and financial resources during both training and deployment. While scaling laws for training have guided much of the field's recent progress, inference costs now…

Machine Learning · Computer Science 2025-07-11 Austin R. Ellis-Mohr , Anuj K. Nayak , Lav R. Varshney

Speculative decoding accelerates large language model (LLM) inference by using a small draft model to generate candidate tokens for a larger target model to verify. The efficacy of this technique hinges on the trade-off between the time…

Computation and Language · Computer Science 2026-03-03 Jiebin Zhang , Zhenghan Yu , Liang Wang , Nan Yang , Eugene J. Yu , Zheng Li , Yifan Song , Dawei Zhu , Xingxing Zhang , Furu Wei , Sujian Li

Speculative decoding accelerates autoregressive language models by using a lightweight drafter to propose multiple future tokens, which the target model then verifies in parallel. DFlash shows that a block diffusion drafter can generate an…

Computation and Language · Computer Science 2026-04-15 Liran Ringel , Yaniv Romano

The acceleration of Large Language Models (LLMs) with speculative decoding provides a significant runtime improvement without any loss of accuracy. Currently, EAGLE-2 is the state-of-the-art speculative decoding method, improving on EAGLE…

Computation and Language · Computer Science 2024-09-04 Oscar Brown , Zhengjie Wang , Andrea Do , Nikhil Mathew , Cheng Yu

Diffusion Large Language Models (DLLMs) have emerged as a new paradigm of language modeling beyond autoregressive next-token prediction. Taking advantage of their inherent modeling foundations, DLLMs have the great potential of efficient…

Machine Learning · Computer Science 2026-02-04 Shutong Wu , Jiawei Zhang

Plant phenotyping tasks such as leaf segmentation and counting are fundamental to the study of phenotypic traits. Since it is well-suited for these tasks, deep supervised learning has been prevalent in recent works proposing better…

Computer Vision and Pattern Recognition · Computer Science 2020-12-22 Douglas Pinto Sampaio Gomes , Lihong Zheng

We revisit test-time scaling for language model reasoning and ask a fundamental question: at equal token budget and compute, is it better to run multiple independent chains in parallel, or to run fewer chains that iteratively refine through…

Machine Learning · Computer Science 2025-11-05 Aman Sharma , Paras Chopra

Multi-path speculative decoding accelerates lossless sampling from a target model by using a cheaper draft model to generate a draft tree of tokens, and then applies a verification algorithm that accepts a subset of these. While prior work…

Machine Learning · Computer Science 2026-02-20 Rahul Thomas , Teo Kitanovski , Micah Goldblum , Arka Pal