A-CODE presents a fully atomic one-stage multimodal diffusion model for protein co-design that claims superior unconditional generation performance over prior one- and two-stage models plus a tenfold success-rate gain on hard binder-design tasks.
hub Canonical reference
Diffusion language models are versatile protein learners
Canonical reference. 100% of citing Pith papers cite this work as background.
11
Pith papers citing it
Background
100% of classified citations
hub tools
citation-role summary
background 5
citation-polarity summary
roles
background 5polarities
background 5representative citing papers
LLaDA is a scalable diffusion-based language model that matches autoregressive LLMs like LLaMA3 8B on tasks and surpasses GPT-4o on reversal poem completion.
Dual Triangle Attention achieves effective bidirectional attention with built-in positional inductive bias via dual triangular masks, outperforming standard bidirectional attention on position-sensitive tasks and showing strong masked language modeling results with or without positional embeddings.
Yeti is a compact tokenizer for protein structures that delivers strong codebook use, token diversity, and reconstruction while enabling from-scratch multimodal generation of plausible sequences and structures with 10x fewer parameters than ESM3.
Primal-dual guided decoding casts constrained discrete diffusion as a KL-regularized optimization solved online with adaptive Lagrangian multipliers to satisfy constraints while staying close to the unconstrained model distribution.
Coupling Models enable single-step discrete sequence generation via learned couplings to Gaussian latents and outperform prior one-step baselines on text perplexity, biological FBD, and image FID metrics.
MP2D is a framework that guides discrete diffusion denoising with constrained MCTS and Pareto rewards to optimize protein sequences for four to five simultaneous objectives, outperforming baselines on antimicrobial peptide and binder design tasks.
MIMIC is a split-track encoder-decoder foundation model that unifies sequence reconstruction, prediction, and constrained design across nucleic acids, proteins, and regulatory context using partially observed multimodal inputs.
Discrete, Gaussian, and simplicial diffusion models for sequences are unified as parameterizations of the Wright-Fisher population genetics model, allowing multi-domain training and stable simplicial diffusion.
CodeFP jointly generates protein sequences and structures using functional local structures and auxiliary supervision, yielding 6.1% better functional consistency and 3.2% better foldability than prior baselines.
citing papers explorer
-
A-CODE: Fully Atomic Protein Co-Design with Unified Multimodal Diffusion
A-CODE presents a fully atomic one-stage multimodal diffusion model for protein co-design that claims superior unconditional generation performance over prior one- and two-stage models plus a tenfold success-rate gain on hard binder-design tasks.
-
Large Language Diffusion Models
LLaDA is a scalable diffusion-based language model that matches autoregressive LLMs like LLaMA3 8B on tasks and surpasses GPT-4o on reversal poem completion.
-
Dual Triangle Attention: Effective Bidirectional Attention Without Positional Embeddings
Dual Triangle Attention achieves effective bidirectional attention with built-in positional inductive bias via dual triangular masks, outperforming standard bidirectional attention on position-sensitive tasks and showing strong masked language modeling results with or without positional embeddings.
-
Yeti: A compact protein structure tokenizer for reconstruction and multi-modal generation
Yeti is a compact tokenizer for protein structures that delivers strong codebook use, token diversity, and reconstruction while enabling from-scratch multimodal generation of plausible sequences and structures with 10x fewer parameters than ESM3.
-
Primal-Dual Guided Decoding for Constrained Discrete Diffusion
Primal-dual guided decoding casts constrained discrete diffusion as a KL-regularized optimization solved online with adaptive Lagrangian multipliers to satisfy constraints while staying close to the unconstrained model distribution.
-
Coupling Models for One-Step Discrete Generation
Coupling Models enable single-step discrete sequence generation via learned couplings to Gaussian latents and outperform prior one-step baselines on text perplexity, biological FBD, and image FID metrics.
-
MP2D: Constrained Monte Carlo Tree-Guided Diffusion for Multi-Objective Protein Sequence Design
MP2D is a framework that guides discrete diffusion denoising with constrained MCTS and Pareto rewards to optimize protein sequences for four to five simultaneous objectives, outperforming baselines on antimicrobial peptide and binder design tasks.
-
MIMIC: A Generative Multimodal Foundation Model for Biomolecules
MIMIC is a split-track encoder-decoder foundation model that unifies sequence reconstruction, prediction, and constrained design across nucleic acids, proteins, and regulatory context using partially observed multimodal inputs.
-
A Unification of Discrete, Gaussian, and Simplicial Diffusion
Discrete, Gaussian, and simplicial diffusion models for sequences are unified as parameterizations of the Wright-Fisher population genetics model, allowing multi-domain training and stable simplicial diffusion.
-
Co-Generative De Novo Functional Protein Design
CodeFP jointly generates protein sequences and structures using functional local structures and auxiliary supervision, yielding 6.1% better functional consistency and 3.2% better foldability than prior baselines.
- Towards A Generative Protein Evolution Machine with DPLM-Evo