{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/tess-2-a-large-scale-generalist-diffusion","title":"TESS 2: A Large-Scale Generalist Diffusion Language Model","arxiv_id":"2502.13917","date":"2025-02-19","proceeding":null,"authors":["Jaesung Tae","Hamish Ivison","Sachin Kumar","Arman Cohan"],"abstract":"We introduce TESS 2, a general instruction-following diffusion language model that outperforms contemporary instruction-tuned diffusion models, as well as matches and sometimes exceeds strong autoregressive (AR) models. We train TESS 2 by first adapting a strong AR model via continued pretraining with the usual cross-entropy as diffusion loss, and then performing further instruction tuning. We find that adaptation training as well as the choice of the base model is crucial for training good instruction-following diffusion models. We further propose reward guidance, a novel and modular inference-time guidance procedure to align model outputs without needing to train the underlying model. Finally, we show that TESS 2 further improves with increased inference-time compute, highlighting the utility of diffusion LMs in having fine-grained controllability over the amount of compute used at inference time. Code and models are available at https://github.com/hamishivi/tess-2.","url_abs":"https://arxiv.org/abs/2502.13917v1","url_pdf":"https://arxiv.org/pdf/2502.13917v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"tess-2-a-large-scale-generalist-diffusion","repo_url":"https://github.com/hamishivi/tess-2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"instruction-following","task_name":"Instruction Following"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"base","method_name":"BASE"},{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2502.13917","atlas_url":"https://app.syntology.ai/?focus=2502.13917","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.13917"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/hamishivi/tess-2","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"unverified":4},"by_repo_kind":{"official":{"samples":7,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"e75c43251c9f2f57","entry":"filter_by_length","repo":"hamishivi/tess-2","repo_kind":"official","path":"sdlm/run_pretrain.py","file_url":"https://github.com/hamishivi/tess-2/blob/HEAD/sdlm/run_pretrain.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e75c43251c9f2f57"}},{"code_sha256_prefix":"adb7541f2edf078e","entry":"get_label_list","repo":"hamishivi/tess-2","repo_kind":"official","path":"sdlm/train_sentiment_model.py","file_url":"https://github.com/hamishivi/tess-2/blob/HEAD/sdlm/train_sentiment_model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"adb7541f2edf078e"}},{"code_sha256_prefix":"a95c8b8f5a6743bf","entry":"get_linear_schedule_with_warmup","repo":"hamishivi/tess-2","repo_kind":"official","path":"sdlm/train_reward_model.py","file_url":"https://github.com/hamishivi/tess-2/blob/HEAD/sdlm/train_reward_model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a95c8b8f5a6743bf"}},{"code_sha256_prefix":"59f032ff780a37ee","entry":"get_compute_metrics","repo":"hamishivi/tess-2","repo_kind":"official","path":"sdlm/run_pretrain.py","file_url":"https://github.com/hamishivi/tess-2/blob/HEAD/sdlm/run_pretrain.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"59f032ff780a37ee"}},{"code_sha256_prefix":"a62ff00e2085ee78","entry":"is_cdcd_check","repo":"hamishivi/tess-2","repo_kind":"official","path":"sdlm/models/utils.py","file_url":"https://github.com/hamishivi/tess-2/blob/HEAD/sdlm/models/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a62ff00e2085ee78"}},{"code_sha256_prefix":"000dd575fde96911","entry":"is_tokenwise_cdcd_check","repo":"hamishivi/tess-2","repo_kind":"official","path":"sdlm/models/utils.py","file_url":"https://github.com/hamishivi/tess-2/blob/HEAD/sdlm/models/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"000dd575fde96911"}},{"code_sha256_prefix":"8e2e5b02685daa31","entry":"model_config_helper","repo":"hamishivi/tess-2","repo_kind":"official","path":"sdlm/models/utils.py","file_url":"https://github.com/hamishivi/tess-2/blob/HEAD/sdlm/models/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8e2e5b02685daa31"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}