paper-with-me

Papers

Prefix-Tree Decoding for Predicting Mass Spectra from Molecules

2023-03-11 · NeurIPS 2023 11 · Samuel Goldman, John Bradshaw, Jiayi Xin, Connor W. Coley

Computational predictions of mass spectra from molecules have enabled the discovery of clinically relevant metabolites. However, such predictive tools are still limited as they occupy one of two extremes, either operating (a) by fragmenting molecules combinatorially with overly rigid constraints on potential rearrangements and poor time complexity or (b) by decoding lossy and nonphysical discretized spectra vectors. In this work, we use a new intermediate strategy for predicting mass spectra from molecules by treating mass spectra as sets of molecular formulae, which are themselves multisets of atoms. After first encoding an input molecular graph, we decode a set of molecular subformulae, each of which specify a predicted peak in the mass spectrum, the intensities of which are predicted by a second model. Our key insight is to overcome the combinatorial possibilities for molecular subformulae by decoding the formula set using a prefix tree structure, atom-type by atom-type, representing a general method for ordered multiset decoding. We show promising empirical results on mass spectra prediction tasks.

📄 PDF Abstract BibTeX arXiv:2303.06470

Code (1)

samgoldman97/ms-pred 공식 구현 pytorch

Similar Papers 제목 키워드 기반

TAPS: Target-Aware Prefix Tree Selection for Diffusion-Drafted Speculative Decoding

2026-05-30 · Zhuoyu Wang, Junnan Huang, Xinyu Chen arxiv

Using a diffusion model for parallel drafting is a promising approach for speculative decoding. By predicting tokens at multiple future positions in a single forward pass, diffusion drafters substantially reduce drafting…

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators

2026-02-26 · Zhengyang Su, Isay Katsman, Yueqi Wang, Ruining He 외 arxiv

Generative retrieval has emerged as a powerful paradigm for LLM-based recommendation. However, industrial recommender systems often benefit from restricting the output space to a constrained subset of items based on busi…

DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference

2024-03-30 · Jinwei Yao, Kaiqi Chen, Kexun Zhang, Jiaxuan You 외

Large language models (LLMs) are increasingly employed for complex tasks that process multiple generation calls in a tree structure with shared prefixes of tokens, including few-shot prompting, multi-step reasoning, spec…

GPU

Efficient Beam Search for Large Language Models Using Trie-Based Decoding

2025-01-31 · Brian J Chan, Jui-Hung Cheng, Mao Xun Huang, Chao-Ting Chen 외

In Transformer-based sequence-to-sequence generation, beam search has proven effective in enhancing the quality of generated sequences compared to greedy decoding. Conventional beam search methods typically adopt either …

SpecBlock: Block-Iterative Speculative Decoding with Dynamic Tree Drafting

2026-05-08 · Weijie Shi, Qiang Xu, Fan Deng, Yaguang Wu 외 arxiv

Speculative decoding accelerates LLM inference by drafting a tree of candidate continuations and verifying it in one target forward. Existing drafters fall into two camps with opposite weaknesses. Autoregressive drafters…