{"task":"Language Modelling","dataset":"OpenWebText","metric_names":["eval_perplexity","eval_loss","parameters"],"rows":[{"id":33741,"task":"Language Modelling","parent_task":null,"dataset":"OpenWebText","model_name":"MDLM-Prime","metrics":{"eval_perplexity":"15.36","parameters":"131M"},"paper_url":"https://arxiv.org/abs/2505.18495v1","paper_title":"Beyond Masked and Unmasked: Discrete Diffusion Models via Partial Masking","paper_date":"2025-05-24","code_links":[],"metrics_order":"[\"eval_perplexity\", \"eval_loss\", \"parameters\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33742,"task":"Language Modelling","parent_task":null,"dataset":"OpenWebText","model_name":"ARM","metrics":{"eval_perplexity":"17.54","parameters":"131M"},"paper_url":"https://arxiv.org/abs/2406.07524v2","paper_title":"Simple and Effective Masked Diffusion Language Models","paper_date":"2024-06-11","code_links":[{"title":"kuleshov-group/mdlm","url":"https://github.com/kuleshov-group/mdlm"},{"title":"masa-ue/svdd","url":"https://github.com/masa-ue/svdd"}],"metrics_order":"[\"eval_perplexity\", \"eval_loss\", \"parameters\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33743,"task":"Language Modelling","parent_task":null,"dataset":"OpenWebText","model_name":"EDLM-coAR","metrics":{"eval_perplexity":"17.58","parameters":"131M"},"paper_url":"https://arxiv.org/abs/2410.21357v1","paper_title":"Energy-Based Diffusion Language Models for Text Generation","paper_date":"2024-10-28","code_links":[],"metrics_order":"[\"eval_perplexity\", \"eval_loss\", \"parameters\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33744,"task":"Language Modelling","parent_task":null,"dataset":"OpenWebText","model_name":"GPT2-Hermite","metrics":{"eval_loss":"2.91","eval_perplexity":"18.39","parameters":"124M"},"paper_url":"https://arxiv.org/abs/2502.01247v2","paper_title":"Polynomial, trigonometric, and tropical activations","paper_date":"2025-02-03","code_links":[{"title":"K-H-Ismail/torchortho","url":"https://github.com/K-H-Ismail/torchortho"}],"metrics_order":"[\"eval_perplexity\", \"eval_loss\", \"parameters\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33745,"task":"Language Modelling","parent_task":null,"dataset":"OpenWebText","model_name":"GPT2-Tropical","metrics":{"eval_loss":"2.92","eval_perplexity":"18.64","parameters":"124M"},"paper_url":"https://arxiv.org/abs/2502.01247v2","paper_title":"Polynomial, trigonometric, and tropical activations","paper_date":"2025-02-03","code_links":[{"title":"K-H-Ismail/torchortho","url":"https://github.com/K-H-Ismail/torchortho"}],"metrics_order":"[\"eval_perplexity\", \"eval_loss\", \"parameters\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33746,"task":"Language Modelling","parent_task":null,"dataset":"OpenWebText","model_name":"GPT2-Fourier","metrics":{"eval_loss":"2.93","eval_perplexity":"18.72","parameters":"124M"},"paper_url":"https://arxiv.org/abs/2502.01247v2","paper_title":"Polynomial, trigonometric, and tropical activations","paper_date":"2025-02-03","code_links":[{"title":"K-H-Ismail/torchortho","url":"https://github.com/K-H-Ismail/torchortho"}],"metrics_order":"[\"eval_perplexity\", \"eval_loss\", \"parameters\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33747,"task":"Language Modelling","parent_task":null,"dataset":"OpenWebText","model_name":"GPT2-GELU","metrics":{"eval_loss":"2.95","eval_perplexity":"19.24","parameters":"124M"},"paper_url":"https://arxiv.org/abs/2502.01247v2","paper_title":"Polynomial, trigonometric, and tropical activations","paper_date":"2025-02-03","code_links":[{"title":"K-H-Ismail/torchortho","url":"https://github.com/K-H-Ismail/torchortho"}],"metrics_order":"[\"eval_perplexity\", \"eval_loss\", \"parameters\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33748,"task":"Language Modelling","parent_task":null,"dataset":"OpenWebText","model_name":"BD3-LMs","metrics":{"eval_perplexity":"20.73","parameters":"131M"},"paper_url":"https://arxiv.org/abs/2503.09573v3","paper_title":"Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models","paper_date":"2025-03-12","code_links":[{"title":"kuleshov-group/bd3lms","url":"https://github.com/kuleshov-group/bd3lms"},{"title":"MindSpore-scientific/code-12","url":"https://github.com/MindSpore-scientific/code-12/tree/main/Block_Model"}],"metrics_order":"[\"eval_perplexity\", \"eval_loss\", \"parameters\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33749,"task":"Language Modelling","parent_task":null,"dataset":"OpenWebText","model_name":"EDLM-NCE","metrics":{"eval_perplexity":"21.52","parameters":"131M"},"paper_url":"https://arxiv.org/abs/2410.21357v1","paper_title":"Energy-Based Diffusion Language Models for Text Generation","paper_date":"2024-10-28","code_links":[],"metrics_order":"[\"eval_perplexity\", \"eval_loss\", \"parameters\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33750,"task":"Language Modelling","parent_task":null,"dataset":"OpenWebText","model_name":"GenMD4","metrics":{"eval_perplexity":"21.80","parameters":"131M"},"paper_url":"https://arxiv.org/abs/2406.04329v4","paper_title":"Simplified and Generalized Masked Diffusion for Discrete Data","paper_date":"2024-06-06","code_links":[{"title":"google-deepmind/md4","url":"https://github.com/google-deepmind/md4"}],"metrics_order":"[\"eval_perplexity\", \"eval_loss\", \"parameters\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33751,"task":"Language Modelling","parent_task":null,"dataset":"OpenWebText","model_name":"MDLM","metrics":{"eval_perplexity":"22.98","parameters":"131M"},"paper_url":"https://arxiv.org/abs/2406.07524v2","paper_title":"Simple and Effective Masked Diffusion Language Models","paper_date":"2024-06-11","code_links":[{"title":"kuleshov-group/mdlm","url":"https://github.com/kuleshov-group/mdlm"},{"title":"masa-ue/svdd","url":"https://github.com/masa-ue/svdd"}],"metrics_order":"[\"eval_perplexity\", \"eval_loss\", \"parameters\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33752,"task":"Language Modelling","parent_task":null,"dataset":"OpenWebText","model_name":"SEDD","metrics":{"eval_perplexity":"24.10","parameters":"131M"},"paper_url":"https://arxiv.org/abs/2310.16834v3","paper_title":"Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution","paper_date":"2023-10-25","code_links":[{"title":"louaaron/score-entropy-discrete-diffusion","url":"https://github.com/louaaron/score-entropy-discrete-diffusion"},{"title":"ozekri/SEPO","url":"https://github.com/ozekri/SEPO"},{"title":"lingxiaoshawn/usd3","url":"https://github.com/lingxiaoshawn/usd3"},{"title":"gabeguo/any-order-speculative-decoding","url":"https://github.com/gabeguo/any-order-speculative-decoding"}],"metrics_order":"[\"eval_perplexity\", \"eval_loss\", \"parameters\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]}]}