{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/code/add-gumbel-noise","entry":"add_gumbel_noise","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-10-05T00:36:11+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample = n_papers_ran_no_instrument_failure (papers with a run with no instrument failure) + n_papers_ran_instrument_only (papers where every run was a failure of Syntology's instrument); n_samples_ran = n_samples_ran_checked (honoured, violated, no contract) + n_samples_instrument (failures of Syntology's instrument, not of the code).","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":32,"n_papers_ran":30,"n_papers_ran_no_instrument_failure":4,"n_papers_ran_instrument_only":26,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":23,"n_samples_ran":21,"n_samples_constructed":0,"n_samples_ran_checked":5,"n_samples_instrument":16,"n_samples_unverified":2,"n_samples_fingerprinted":18,"n_places":40,"n_places_pointer_only":25,"n_places_pointer_only_link_open":5,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_places_pointer_only_link_open counts the places where this paper's link allows the text and the stored copy does not","by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":14,"ran":4,"unverified":2},"key_notes":{"n_samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2608.08086","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2608-08086","title":"Archer: Adaptive Reuse of Cached Hidden States for Efficient Rollback in Diffusion Language Models","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"Hxnng/Archer","path":"src/archer/state_distance/sampler.py","file_url":"https://github.com/Hxnng/Archer/blob/HEAD/src/archer/state_distance/sampler.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Hxnng/Archer when it was checked","code_sha256":"10e530678395c16a","code_sha256_prefix":"10e530678395c16a","mcp_get_code":{"code_sha256":"10e530678395c16a"}},{"arxiv_id":"2607.28166","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2607-28166","title":"Commit Locally, Exit Globally: Coordinating Adaptive Sampling and Early Exit in Diffusion Language Models","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"ming053l/C4-dLLM","path":"c4/decode.py","file_url":"https://github.com/ming053l/C4-dLLM/blob/HEAD/c4/decode.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"027b7c000eacca21","code_sha256_prefix":"027b7c000eacca21","mcp_get_code":{"code_sha256":"027b7c000eacca21"}},{"arxiv_id":"2607.04206","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2607-04206","title":"Sangam: Efficiently Serving Diffusion LLMs with the AR Stack","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"UT-InfraAI/sangam","path":"src/sangam/sampler.py","file_url":"https://github.com/UT-InfraAI/sangam/blob/HEAD/src/sangam/sampler.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"c551a291fca9e38d","code_sha256_prefix":"c551a291fca9e38d","mcp_get_code":{"code_sha256":"c551a291fca9e38d"}},{"arxiv_id":"2606.18195","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2606-18195","title":"Learning from the Self-future: On-policy Self-distillation for dLLMs","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"xingzhejun/d-OPSD","path":"d-opsd/utils.py","file_url":"https://github.com/xingzhejun/d-OPSD/blob/HEAD/d-opsd/utils.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, xingzhejun/d-OPSD when it was checked","code_sha256":"746963c6a9e9b2b0","code_sha256_prefix":"746963c6a9e9b2b0","mcp_get_code":{"code_sha256":"746963c6a9e9b2b0"}},{"arxiv_id":"2606.18195","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2606-18195","title":"Learning from the Self-future: On-policy Self-distillation for dLLMs","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"xingzhejun/d-OPSD","path":"eval/generate.py","file_url":"https://github.com/xingzhejun/d-OPSD/blob/HEAD/eval/generate.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, xingzhejun/d-OPSD when it was checked","code_sha256":"f3233aab1c6c6543","code_sha256_prefix":"f3233aab1c6c6543","mcp_get_code":{"code_sha256":"f3233aab1c6c6543"}},{"arxiv_id":"2606.10537","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2606-10537","title":"Prefilling-dLLM: Predictive Prefilling for Long-Context Inference in Diffusion Language Models","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"menik1126/Prefilling-dLLM","path":"prefilling_dllm_eval/llada_native_model.py","file_url":"https://github.com/menik1126/Prefilling-dLLM/blob/HEAD/prefilling_dllm_eval/llada_native_model.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"027b7c000eacca21","code_sha256_prefix":"027b7c000eacca21","mcp_get_code":{"code_sha256":"027b7c000eacca21"}},{"arxiv_id":"2606.04974","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2606-04974","title":"SAID: Accelerating Diffusion-Based Language Models via Scaffold-Aware Iterative Decoding","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"TH-AI-Lab-PKU/SAID","path":"SAID-block/generate_said.py","file_url":"https://github.com/TH-AI-Lab-PKU/SAID/blob/HEAD/SAID-block/generate_said.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, TH-AI-Lab-PKU/SAID when it was checked","code_sha256":"0f2bf418118186bc","code_sha256_prefix":"0f2bf418118186bc","mcp_get_code":{"code_sha256":"0f2bf418118186bc"}},{"arxiv_id":"2605.23215","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2605-23215","title":"FASTKERNELS: Benchmarking GPU Kernel Generation in Production","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"Snowflake-AI-Research/fastkernels","path":"fastkernels/infra/dllm_engine.py","file_url":"https://github.com/Snowflake-AI-Research/fastkernels/blob/HEAD/fastkernels/infra/dllm_engine.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"e5d55fd1b07cbbf3","code_sha256_prefix":"e5d55fd1b07cbbf3","mcp_get_code":{"code_sha256":"e5d55fd1b07cbbf3"}},{"arxiv_id":"2605.16941","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2605-16941","title":"Roll Out and Roll Back: Diffusion LLMs are Their Own Efficiency Teachers","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"Feng-Hong/WINO-DLLM","path":"LLaDA/decoding.py","file_url":"https://github.com/Feng-Hong/WINO-DLLM/blob/HEAD/LLaDA/decoding.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Feng-Hong/WINO-DLLM when it was checked","code_sha256":"a5334721ab55f48f","code_sha256_prefix":"a5334721ab55f48f","mcp_get_code":{"code_sha256":"a5334721ab55f48f"}},{"arxiv_id":"2605.09536","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2605-09536","title":"TAD: Temporal-Aware Trajectory Self-Distillation for Fast and Accurate Diffusion LLM","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"BHmingyang/TAD","path":"eval/eval_llada.py","file_url":"https://github.com/BHmingyang/TAD/blob/HEAD/eval/eval_llada.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, BHmingyang/TAD when it was checked","code_sha256":"027b7c000eacca21","code_sha256_prefix":"027b7c000eacca21","mcp_get_code":{"code_sha256":"027b7c000eacca21"}},{"arxiv_id":"2605.02263","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2605-02263","title":"Break the Block: Dynamic-size Reasoning Blocks for Diffusion Large Language Models via Monotonic Entropy Descent with Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"YanJiangJerry/Block-R1","path":"rl/trainers/dynamic_generate.py","file_url":"https://github.com/YanJiangJerry/Block-R1/blob/HEAD/rl/trainers/dynamic_generate.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"746963c6a9e9b2b0","code_sha256_prefix":"746963c6a9e9b2b0","mcp_get_code":{"code_sha256":"746963c6a9e9b2b0"}},{"arxiv_id":"2604.18995","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2604-18995","title":"R 2 -dLLM: Accelerating Diffusion Large Language Models via Spatio-Temporal Redundancy Reduction","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"GATECH-EIC/R2-dLLM","path":"llada/generate.py","file_url":"https://github.com/GATECH-EIC/R2-dLLM/blob/HEAD/llada/generate.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, GATECH-EIC/R2-dLLM when it was checked","code_sha256":"a5334721ab55f48f","code_sha256_prefix":"a5334721ab55f48f","mcp_get_code":{"code_sha256":"a5334721ab55f48f"}},{"arxiv_id":"2604.08302","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2604-08302","title":"DMax: Aggressive Parallel Decoding for dLLMs","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"czg1225/DMax","path":"dInfer/python/dinfer/decoding/parallel_strategy.py","file_url":"https://github.com/czg1225/DMax/blob/HEAD/dInfer/python/dinfer/decoding/parallel_strategy.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"990cdbb7b7b9c54c","code_sha256_prefix":"990cdbb7b7b9c54c","mcp_get_code":{"code_sha256":"990cdbb7b7b9c54c"}},{"arxiv_id":"2603.01331","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2603-01331","title":"MetaState: Persistent Working Memory Enhances Reasoning in Discrete Diffusion Language Models","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"Les1a/MetaState","path":"dllm/core/samplers/utils.py","file_url":"https://github.com/Les1a/MetaState/blob/HEAD/dllm/core/samplers/utils.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"c7fd61b6c723375b","code_sha256_prefix":"c7fd61b6c723375b","mcp_get_code":{"code_sha256":"c7fd61b6c723375b"}},{"arxiv_id":"2602.06462","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2602-06462","title":"Diffusion-State Policy Optimization for Masked Diffusion Language Models","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"dllm-reasoning/d1","path":"eval/generate.py","file_url":"https://github.com/dllm-reasoning/d1/blob/HEAD/eval/generate.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from xingzhejun/d-OPSD, and GitHub detected no licence in that repository when it was checked","code_sha256":"f3233aab1c6c6543","code_sha256_prefix":"f3233aab1c6c6543","mcp_get_code":{"code_sha256":"f3233aab1c6c6543"}},{"arxiv_id":"2602.02600","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2602-02600","title":"Step-Wise Refusal Dynamics in Autoregressive and Diffusion Language Models","date":"2026-02-01","month_inferred_from_arxiv_id":null,"title_source":"syntology","repo":"niez233/DiffuGuard","path":"utility/generate_function.py","file_url":"https://github.com/niez233/DiffuGuard/blob/HEAD/utility/generate_function.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, niez233/DiffuGuard when it was checked","code_sha256":"1495eea6ced11dfa","code_sha256_prefix":"1495eea6ced11dfa","mcp_get_code":{"code_sha256":"1495eea6ced11dfa"}},{"arxiv_id":"2602.02600","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2602-02600","title":"Step-Wise Refusal Dynamics in Autoregressive and Diffusion Language Models","date":"2026-02-01","month_inferred_from_arxiv_id":null,"title_source":"syntology","repo":"shuita2333/PAD-codes","path":"LLaDA-PAD/generate-PAD.py","file_url":"https://github.com/shuita2333/PAD-codes/blob/HEAD/LLaDA-PAD/generate-PAD.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, shuita2333/PAD-codes when it was checked","code_sha256":"72a32148829c38b2","code_sha256_prefix":"72a32148829c38b2","mcp_get_code":{"code_sha256":"72a32148829c38b2"}},{"arxiv_id":"2602.02600","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2602-02600","title":"Step-Wise Refusal Dynamics in Autoregressive and Diffusion Language Models","date":"2026-02-01","month_inferred_from_arxiv_id":null,"title_source":"syntology","repo":"shuita2333/PAD-codes","path":"MMaDA-PAD/models/modeling_mmada.py","file_url":"https://github.com/shuita2333/PAD-codes/blob/HEAD/MMaDA-PAD/models/modeling_mmada.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, shuita2333/PAD-codes when it was checked","code_sha256":"615ec9b280bef7c6","code_sha256_prefix":"615ec9b280bef7c6","mcp_get_code":{"code_sha256":"615ec9b280bef7c6"}},{"arxiv_id":"2601.22527","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2601-22527","title":"ρ-EOS: Training-free Bidirectional Variable-Length Control for Masked Diffusion LLMs","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"yjyddq/rho-EOS","path":"models/LLaDA_rho_EOS.py","file_url":"https://github.com/yjyddq/rho-EOS/blob/HEAD/models/LLaDA_rho_EOS.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"2eceb68d6f6d3d37","code_sha256_prefix":"2eceb68d6f6d3d37","mcp_get_code":{"code_sha256":"2eceb68d6f6d3d37"}},{"arxiv_id":"2601.22527","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2601-22527","title":"ρ-EOS: Training-free Bidirectional Variable-Length Control for Masked Diffusion LLMs","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"yjyddq/rho-EOS","path":"models/LLaDA.py","file_url":"https://github.com/yjyddq/rho-EOS/blob/HEAD/models/LLaDA.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"3d179b42fcc82ef2","code_sha256_prefix":"3d179b42fcc82ef2","mcp_get_code":{"code_sha256":"3d179b42fcc82ef2"}},{"arxiv_id":"2601.21484","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2601-21484","title":"ETS: Energy-Guided Test-Time Scaling for Training-Free RL Alignment","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"sheriyuo/ETS","path":"llada/ets_is.py","file_url":"https://github.com/sheriyuo/ETS/blob/HEAD/llada/ets_is.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, sheriyuo/ETS when it was checked","code_sha256":"b95cadfa99b9514d","code_sha256_prefix":"b95cadfa99b9514d","mcp_get_code":{"code_sha256":"b95cadfa99b9514d"}},{"arxiv_id":"2601.07894","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2601-07894","title":"Revealing the Attention Floating Mechanism in Masked Diffusion Models","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"NEUIR/Attention-Floating","path":"src/attention_extraction/Llada.py","file_url":"https://github.com/NEUIR/Attention-Floating/blob/HEAD/src/attention_extraction/Llada.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, NEUIR/Attention-Floating when it was checked","code_sha256":"2340e6453f04571f","code_sha256_prefix":"2340e6453f04571f","mcp_get_code":{"code_sha256":"2340e6453f04571f"}},{"arxiv_id":"2601.02236","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2601-02236","title":"CD 4 LM: Consistency Distillation and aDaptive Decoding for Diffusion Language Models","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"yihao-liang/CDLM","path":"evaluation/dllm_eval/models/LLaDA.py","file_url":"https://github.com/yihao-liang/CDLM/blob/HEAD/evaluation/dllm_eval/models/LLaDA.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"3d179b42fcc82ef2","code_sha256_prefix":"3d179b42fcc82ef2","mcp_get_code":{"code_sha256":"3d179b42fcc82ef2"}},{"arxiv_id":"2511.05664","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2511-05664","title":"KLASS: KL-Guided Fast Inference in Masked Diffusion Models","date":null,"month_inferred_from_arxiv_id":"2025-11","title_source":"syntology","repo":null,"path":"","file_url":null,"status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"inline_ok_link":false,"withheld_clause":"this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it","code_sha256":"a5334721ab55f48f","code_sha256_prefix":"a5334721ab55f48f","mcp_get_code":{"code_sha256":"a5334721ab55f48f"}},{"arxiv_id":"2511.02077","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2511-02077","title":"Beyond Static Cutoffs: One-Shot Dynamic Thresholding for Diffusion Language Models","date":null,"month_inferred_from_arxiv_id":"2025-11","title_source":"syntology","repo":"jackshen-1215/osdt","path":"osdt/llada_generate_osdt.py","file_url":"https://github.com/jackshen-1215/osdt/blob/HEAD/osdt/llada_generate_osdt.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, jackshen-1215/osdt when it was checked","code_sha256":"cea29bbf70d23ead","code_sha256_prefix":"cea29bbf70d23ead","mcp_get_code":{"code_sha256":"cea29bbf70d23ead"}},{"arxiv_id":"2509.15188","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2509-15188","title":"Fast and Fluent Diffusion Language Models via Convolutional Decoding and Rejective Fine-tuning","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"ybseo-ac/Conv","path":"generate_yb.py","file_url":"https://github.com/ybseo-ac/Conv/blob/HEAD/generate_yb.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ybseo-ac/Conv when it was checked","code_sha256":"a5334721ab55f48f","code_sha256_prefix":"a5334721ab55f48f","mcp_get_code":{"code_sha256":"a5334721ab55f48f"}},{"arxiv_id":"2509.15188","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2509-15188","title":"Fast and Fluent Diffusion Language Models via Convolutional Decoding and Rejective Fine-tuning","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"ybseo-ac/Conv","path":"gen1_2_answer_generation_llada.py","file_url":"https://github.com/ybseo-ac/Conv/blob/HEAD/gen1_2_answer_generation_llada.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ybseo-ac/Conv when it was checked","code_sha256":"529aefed4b15eb2b","code_sha256_prefix":"529aefed4b15eb2b","mcp_get_code":{"code_sha256":"529aefed4b15eb2b"}},{"arxiv_id":"2507.11097","arxiv_id_is_arxiv":true,"paper":"/paper/the-devil-behind-the-mask-an-emergent-safety","title":"The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs","date":"2025-07-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zichenwen1/dija","path":"MMaDA/generate.py","file_url":"https://github.com/zichenwen1/dija/blob/HEAD/MMaDA/generate.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from ml-gsai/llada, and GitHub detected no licence in that repository when it was checked","code_sha256":"a5334721ab55f48f","code_sha256_prefix":"a5334721ab55f48f","mcp_get_code":{"code_sha256":"a5334721ab55f48f"}},{"arxiv_id":"2507.11097","arxiv_id_is_arxiv":true,"paper":"/paper/the-devil-behind-the-mask-an-emergent-safety","title":"The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs","date":"2025-07-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zichenwen1/dija","path":"MMaDA/models/modeling_mmada.py","file_url":"https://github.com/zichenwen1/dija/blob/HEAD/MMaDA/models/modeling_mmada.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from shuita2333/PAD-codes, and GitHub detected no licence in that repository when it was checked","code_sha256":"615ec9b280bef7c6","code_sha256_prefix":"615ec9b280bef7c6","mcp_get_code":{"code_sha256":"615ec9b280bef7c6"}},{"arxiv_id":"2506.15735","arxiv_id_is_arxiv":true,"paper":null,"title":"arXiv:2506.15735","date":null,"month_inferred_from_arxiv_id":"2025-06","title_source":null,"repo":"lasr-eliciting-contexts/ContextBench","path":"src/contextbench/llada/generate.py","file_url":"https://github.com/lasr-eliciting-contexts/ContextBench/blob/HEAD/src/contextbench/llada/generate.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, lasr-eliciting-contexts/ContextBench when it was checked","code_sha256":"a5334721ab55f48f","code_sha256_prefix":"a5334721ab55f48f","mcp_get_code":{"code_sha256":"a5334721ab55f48f"}},{"arxiv_id":"2506.06295","arxiv_id_is_arxiv":true,"paper":"/paper/dllm-cache-accelerating-diffusion-large","title":"dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching","date":"2025-05-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"maomaocun/dLLM-cache","path":"demo_MMada_cache.py","file_url":"https://github.com/maomaocun/dLLM-cache/blob/HEAD/demo_MMada_cache.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"008ab2cfccca5ac2","code_sha256_prefix":"008ab2cfccca5ac2","mcp_get_code":{"code_sha256":"008ab2cfccca5ac2"}},{"arxiv_id":"2506.06295","arxiv_id_is_arxiv":true,"paper":"/paper/dllm-cache-accelerating-diffusion-large","title":"dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching","date":"2025-05-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"maomaocun/dLLM-cache","path":"demo_MMada_mmu_cache.py","file_url":"https://github.com/maomaocun/dLLM-cache/blob/HEAD/demo_MMada_mmu_cache.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"22cb8c51f0a9038f","code_sha256_prefix":"22cb8c51f0a9038f","mcp_get_code":{"code_sha256":"22cb8c51f0a9038f"}},{"arxiv_id":"2505.15809","arxiv_id_is_arxiv":true,"paper":"/paper/mmada-multimodal-large-diffusion-language","title":"MMaDA: Multimodal Large Diffusion Language Models","date":"2025-05-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Gen-Verse/MMaDA","path":"generate.py","file_url":"https://github.com/Gen-Verse/MMaDA/blob/HEAD/generate.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from ml-gsai/llada, and GitHub detected no licence in that repository when it was checked","code_sha256":"a5334721ab55f48f","code_sha256_prefix":"a5334721ab55f48f","mcp_get_code":{"code_sha256":"a5334721ab55f48f"}},{"arxiv_id":"2505.15809","arxiv_id_is_arxiv":true,"paper":"/paper/mmada-multimodal-large-diffusion-language","title":"MMaDA: Multimodal Large Diffusion Language Models","date":"2025-05-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Gen-Verse/MMaDA","path":"models/modeling_mmada.py","file_url":"https://github.com/Gen-Verse/MMaDA/blob/HEAD/models/modeling_mmada.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from shuita2333/PAD-codes, and GitHub detected no licence in that repository when it was checked","code_sha256":"615ec9b280bef7c6","code_sha256_prefix":"615ec9b280bef7c6","mcp_get_code":{"code_sha256":"615ec9b280bef7c6"}},{"arxiv_id":"2502.09992","arxiv_id_is_arxiv":true,"paper":"/paper/large-language-diffusion-models","title":"Large Language Diffusion Models","date":"2025-02-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ml-gsai/llada","path":"generate.py","file_url":"https://github.com/ml-gsai/llada/blob/HEAD/generate.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ml-gsai/llada when it was checked","code_sha256":"a5334721ab55f48f","code_sha256_prefix":"a5334721ab55f48f","mcp_get_code":{"code_sha256":"a5334721ab55f48f"}},{"arxiv_id":"2411.06959","arxiv_id_is_arxiv":true,"paper":"/paper/enat-rethinking-spatial-temporal-interactions","title":"ENAT: Rethinking Spatial-temporal Interactions in Token-based Image Synthesis","date":"2024-11-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leaplabthu/enat","path":"libs/nat_misc.py","file_url":"https://github.com/leaplabthu/enat/blob/HEAD/libs/nat_misc.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, leaplabthu/enat when it was checked","code_sha256":"9ef9985f5609c318","code_sha256_prefix":"9ef9985f5609c318","mcp_get_code":{"code_sha256":"9ef9985f5609c318"}},{"arxiv_id":"2406.05478","arxiv_id_is_arxiv":true,"paper":"/paper/revisiting-non-autoregressive-transformers","title":"Revisiting Non-Autoregressive Transformers for Efficient Image Synthesis","date":"2024-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leaplabthu/improvednat","path":"libs/nat_misc.py","file_url":"https://github.com/leaplabthu/improvednat/blob/HEAD/libs/nat_misc.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"9ef9985f5609c318","code_sha256_prefix":"9ef9985f5609c318","mcp_get_code":{"code_sha256":"9ef9985f5609c318"}},{"arxiv_id":"2310.12362","arxiv_id_is_arxiv":true,"paper":"/paper/remark-llm-a-robust-and-efficient","title":"REMARK-LLM: A Robust and Efficient Watermarking Framework for Generative Large Language Models","date":"2023-10-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ruisizhang123/REMARK-LLM","path":"inference.py","file_url":"https://github.com/ruisizhang123/REMARK-LLM/blob/HEAD/inference.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ruisizhang123/REMARK-LLM when it was checked","code_sha256":"2d1739ff0a683922","code_sha256_prefix":"2d1739ff0a683922","mcp_get_code":{"code_sha256":"2d1739ff0a683922"}},{"arxiv_id":"2301.00704","arxiv_id_is_arxiv":true,"paper":"/paper/muse-text-to-image-generation-via-masked","title":"Muse: Text-To-Image Generation via Masked Generative Transformers","date":"2023-01-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"baaivision/muse-pytorch","path":"libs/muse.py","file_url":"https://github.com/baaivision/muse-pytorch/blob/HEAD/libs/muse.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"9ef9985f5609c318","code_sha256_prefix":"9ef9985f5609c318","mcp_get_code":{"code_sha256":"9ef9985f5609c318"}},{"arxiv_id":"Hertz_Style_Aligned_Image_Generation_via_Shared_Attention_CVPR_2024_paper","arxiv_id_is_arxiv":false,"paper":null,"title":"CVF open access id Hertz_Style_Aligned_Image_Generation_via_Shared_Attention_CVPR_2024_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"baaivision/MUSE-Pytorch","path":"libs/muse.py","file_url":"https://github.com/baaivision/MUSE-Pytorch/blob/HEAD/libs/muse.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"9ef9985f5609c318","code_sha256_prefix":"9ef9985f5609c318","mcp_get_code":{"code_sha256":"9ef9985f5609c318"}}],"record_sha256":"9101342da005d71b45ab6e1f64ba282161ca514ed72984cfb1473514166c4591","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}