{"total":13,"items":[{"citing_arxiv_id":"2605.30963","ref_index":58,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"AMix-2: Establishing Protein as a Native Modality in Large Language Models","primary_cat":"q-bio.BM","submitted_at":"2026-05-29T07:58:08+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"AMix-2 unifies protein sequences and text in one LLM via shared tokens and block-wise diffusion modeling, introduces the ProteinArena benchmark, and reports competitive performance against task-specific protein models and frontier LLMs.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.21610","ref_index":191,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"AgForce Enables Antigen-conditioned Generative Antibody Design","primary_cat":"cs.LG","submitted_at":"2026-05-20T18:16:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"AgForce improves antigen-conditioned antibody design by using framework dropout, gated bottlenecks, hyperbolic cross attention, MDN sequence head with Potts-like coupling, annealed MCL, and antigen cycle consistency to achieve 8% better amino acid recovery and superior binding metrics on CHIMERA-BEN","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.21600","ref_index":191,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"ConTact: Contact-First Antibody CDR Design via Explicit Interface Reasoning","primary_cat":"cs.LG","submitted_at":"2026-05-20T18:04:32+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.21485","ref_index":191,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"EvoStruct: Bridging Evolutionary and Structural Priors for Antibody CDR Design via Protein Language Model Adaptation","primary_cat":"cs.LG","submitted_at":"2026-05-20T17:59:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"EvoStruct integrates evolutionary priors from a protein language model with structural priors from an E(3)-equivariant GNN to raise amino acid recovery by 16% and diversity by 2.3x on CHIMERA-Bench while cutting perplexity 43%.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09981","ref_index":4,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Yeti: A compact protein structure tokenizer for reconstruction and multi-modal generation","primary_cat":"q-bio.BM","submitted_at":"2026-05-11T04:49:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"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.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"expressive and compatible with large-scale learning. Recent generative models have addressed this by treating proteins as 3D objects, utilizing complex architectures operating in SE(3) and diffusion processes in continuous coordinate space. A complementary and increasingly compelling alternative is to encode 3D atomic structure as discrete tokens, as in ESM3[3], DPLM2[4], and SaProt[5], which frame protein modeling as masked or auto-regressive language modeling over structure vocabularies jointly with inherently discrete modalities such as sequence and functional annotations. An advantage of auto-regressive model is that it allows protein structure generation without predefined length which is desirable in a case where given an experimental cryo-EM density map we want to automatically"},{"citing_arxiv_id":"2605.09302","ref_index":42,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Discrete Langevin-Inspired Posterior Sampling","primary_cat":"cs.LG","submitted_at":"2026-05-10T03:59:40+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"ΔLPS is a gradient-guided discrete posterior sampler for inverse problems that works with masked or uniform discrete diffusion priors and outperforms prior discrete methods on image restoration tasks.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"samplers can provide a promising path toward practical and general posterior samplers over a wide class of inverse problems over discrete representations. 2 Preliminaries and Related Work Discrete diffusion modelshave recently emerged as a powerful class of generative models for discretedata, including text [ 23, 51, 22, 6], code [14, 10], vector-quantized images [44, 19], audio 2 [43], protein, and molecular generation [ 42, 38, 20, 46]. These models use a forward Markov corruption process over categorical states z0 ∈ {1, . . . , K}L and learn a reverse denoising model. In D3PM [ 1], the forward process is specified by transition matrices Qt ∈R K×K , where Qij t denotes the probability of transitioning from token i to token j at time t. For each coordinate ℓ, q(zt[ℓ] =j|z t−1[ℓ] =i) =Q ij"},{"citing_arxiv_id":"2605.07193","ref_index":66,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Coupling Models for One-Step Discrete Generation","primary_cat":"cs.LG","submitted_at":"2026-05-08T03:40:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.03360","ref_index":33,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A-CODE: Fully Atomic Protein Co-Design with Unified Multimodal Diffusion","primary_cat":"q-bio.QM","submitted_at":"2026-05-05T04:41:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":8.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.00948","ref_index":13,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Co-Generative De Novo Functional Protein Design","primary_cat":"q-bio.QM","submitted_at":"2026-05-01T10:39:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.00182","ref_index":53,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Towards A Generative Protein Evolution Machine with DPLM-Evo","primary_cat":"cs.LG","submitted_at":"2026-04-30T19:59:07+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2602.04883","ref_index":43,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Protein Autoregressive Modeling via Multiscale Structure Generation","primary_cat":"cs.LG","submitted_at":"2026-02-04T18:59:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"PAR is a multi-scale autoregressive transformer framework for protein backbone generation that uses coarse-to-fine prediction, noisy context learning, and flow-based decoding to achieve high-quality unconditional and zero-shot conditional outputs.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2511.18801","ref_index":34,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"PartDiffuser: Part-wise 3D Mesh Generation via Discrete Diffusion","primary_cat":"cs.CV","submitted_at":"2025-11-24T06:11:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"PartDiffuser is a semi-autoregressive discrete diffusion framework that generates high-fidelity 3D meshes from point clouds by combining inter-part autoregression with intra-part parallel diffusion using a part-aware DiT architecture.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2502.09992","ref_index":78,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Large Language Diffusion Models","primary_cat":"cs.CL","submitted_at":"2025-02-14T08:23:51+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":8.0,"formal_verification":"none","one_line_summary":"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.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"[76] Xinyou Wang, Zaixiang Zheng, Fei Ye, Dongyu Xue, Shujian Huang, and Quanquan Gu. Diffusion language models are versatile protein learners.arXiv preprint arXiv:2402.18567, 2024. [77] Xinyou Wang, Zaixiang Zheng, Fei Ye, Dongyu Xue, Shujian Huang, and Quanquan Gu. Dplm-2: A multimodal diffusion protein language model.arXiv preprint arXiv:2410.13782, 2024. [78] Siqi Kou, Lanxiang Hu, Zhezhi He, Zhijie Deng, and Hao Zhang. Cllms: Consistency large language models.arXiv preprint arXiv:2403.00835, 2024. [79] Chenkai Xu, Xu Wang, Zhenyi Liao, Yishun Li, Tianqi Hou, and Zhijie Deng. Show-o turbo: Towards accelerated unified multimodal understanding and generation.arXiv preprint arXiv:2502.05415, 2025. [80] Sulin Liu, Juno Nam, Andrew Campbell, Hannes Stärk, Yilun Xu, Tommi Jaakkola, and Rafael"}],"limit":50,"offset":0}