{"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":"/code/get-num-transfer-tokens","entry":"get_num_transfer_tokens","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+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.","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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":22,"n_papers_ran":17,"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":13,"n_samples_ran":8,"n_samples_fingerprinted":1,"n_places":26,"n_places_pointer_only":14,"by_status":{"ran_honours":3,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":3,"unverified":5},"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":"2607.28166","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","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"befea8ff69c3c190","mcp_get_code":{"code_sha256":"befea8ff69c3c190"}},{"arxiv_id":"2606.18195","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","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c3a8d456e319a4cd","mcp_get_code":{"code_sha256":"c3a8d456e319a4cd"}},{"arxiv_id":"2606.04974","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_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"616687ef1e9b4bb3","mcp_get_code":{"code_sha256":"616687ef1e9b4bb3"}},{"arxiv_id":"2605.23215","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","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e09479b4e819c39d","mcp_get_code":{"code_sha256":"e09479b4e819c39d"}},{"arxiv_id":"2605.16941","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_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6f22da9cc766ffbe","mcp_get_code":{"code_sha256":"6f22da9cc766ffbe"}},{"arxiv_id":"2605.09536","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","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"befea8ff69c3c190","mcp_get_code":{"code_sha256":"befea8ff69c3c190"}},{"arxiv_id":"2605.02263","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_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0b9c375ad9242640","mcp_get_code":{"code_sha256":"0b9c375ad9242640"}},{"arxiv_id":"2604.18995","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":"dream/model/generation_utils_block.py","file_url":"https://github.com/GATECH-EIC/R2-dLLM/blob/HEAD/dream/model/generation_utils_block.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6f22da9cc766ffbe","mcp_get_code":{"code_sha256":"6f22da9cc766ffbe"}},{"arxiv_id":"2602.06462","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","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c3a8d456e319a4cd","mcp_get_code":{"code_sha256":"c3a8d456e319a4cd"}},{"arxiv_id":"2602.05992","paper":"/paper/arxiv-2602-05992","title":"DSB: Dynamic Sliding Block Scheduling for Diffusion LLMs","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"lizhuo-luo/DSB","path":"llada/generate.py","file_url":"https://github.com/lizhuo-luo/DSB/blob/HEAD/llada/generate.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e95adfb19ea21d20","mcp_get_code":{"code_sha256":"e95adfb19ea21d20"}},{"arxiv_id":"2602.02600","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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b7cee2ce433da95c","mcp_get_code":{"code_sha256":"b7cee2ce433da95c"}},{"arxiv_id":"2602.02600","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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"65934529afeabeff","mcp_get_code":{"code_sha256":"65934529afeabeff"}},{"arxiv_id":"2601.22527","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,"code_sha256_prefix":"e0d3b8594adea583","mcp_get_code":{"code_sha256":"e0d3b8594adea583"}},{"arxiv_id":"2601.07894","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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"623e32f834b5c999","mcp_get_code":{"code_sha256":"623e32f834b5c999"}},{"arxiv_id":"2601.02236","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,"code_sha256_prefix":"e0d3b8594adea583","mcp_get_code":{"code_sha256":"e0d3b8594adea583"}},{"arxiv_id":"2511.05664","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_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"6f22da9cc766ffbe","mcp_get_code":{"code_sha256":"6f22da9cc766ffbe"}},{"arxiv_id":"2511.02077","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_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e5fea1962f28fc68","mcp_get_code":{"code_sha256":"e5fea1962f28fc68"}},{"arxiv_id":"2509.15188","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_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6f22da9cc766ffbe","mcp_get_code":{"code_sha256":"6f22da9cc766ffbe"}},{"arxiv_id":"2509.15188","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":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"befea8ff69c3c190","mcp_get_code":{"code_sha256":"befea8ff69c3c190"}},{"arxiv_id":"2507.11097","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_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"6f22da9cc766ffbe","mcp_get_code":{"code_sha256":"6f22da9cc766ffbe"}},{"arxiv_id":"2507.11097","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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"65934529afeabeff","mcp_get_code":{"code_sha256":"65934529afeabeff"}},{"arxiv_id":"2506.15735","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_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6f22da9cc766ffbe","mcp_get_code":{"code_sha256":"6f22da9cc766ffbe"}},{"arxiv_id":"2506.06295","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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ab0375db4fa54d7c","mcp_get_code":{"code_sha256":"ab0375db4fa54d7c"}},{"arxiv_id":"2505.15809","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_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6f22da9cc766ffbe","mcp_get_code":{"code_sha256":"6f22da9cc766ffbe"}},{"arxiv_id":"2505.15809","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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"65934529afeabeff","mcp_get_code":{"code_sha256":"65934529afeabeff"}},{"arxiv_id":"2502.09992","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_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6f22da9cc766ffbe","mcp_get_code":{"code_sha256":"6f22da9cc766ffbe"}}]}