{"total":15,"rows":[{"id":"2411.02038","title":"Addressing Representation Collapse in Vector Quantized Models with One Linear Layer","created":"2024-11-04","cited_by_count":80,"area":null},{"id":"2410.13782","title":"DPLM-2: A Multimodal Diffusion Protein Language Model","created":"2024-10-17","cited_by_count":64,"area":null},{"id":"2403.01528","title":"Leveraging Biomolecule and Natural Language through Multi-Modal Learning: A Survey","created":"2024-03-03","cited_by_count":17,"area":null},{"id":"2410.18403","title":"Structure Language Models for Protein Conformation Generation","created":"2024-10-24","cited_by_count":17,"area":null},{"id":"2405.15840","title":"Learning the Language of Protein Structure","created":"2024-05-24","cited_by_count":10,"area":null},{"id":"2602.06418","title":"Adaptive Protein Tokenization","created":"2026-02-06","cited_by_count":2,"area":null},{"id":"2407.00050","title":"FoldToken2: Learning compact, invariant and generative protein structure language","created":"2024-06-11","cited_by_count":1,"area":null},{"id":"2412.01564","title":"Tokenizing 3D Molecule Structure with Quantized Spherical Coordinates","created":"2024-12-02","cited_by_count":1,"area":null},{"id":"2602.19622","title":"VecFormer: Towards Efficient and Generalizable Graph Transformer with Graph Token Attention","created":"2026-02-23","cited_by_count":1,"area":null},{"id":"2605.09981","title":"Yeti: A compact protein structure tokenizer for reconstruction and multi-modal generation","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2605.10341","title":"PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2506.08365","title":"AlphaFold Database Debiasing for Robust Inverse Folding","created":"2025-06-10","cited_by_count":0,"area":null},{"id":"2603.19636","title":"RiboSphere: Learning Unified and Efficient Representations of RNA Structures","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2610.03978","title":"Learning Latent Protein Languages for Autoregressive Generation","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.18481","title":"ProTok: Unified Protein Tokenization via Modular Multi-Codebook Quantization","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}