{"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/make-attn","entry":"make_attn","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":1,"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":9,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":22,"n_places_pointer_only":7,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":0,"unverified":8},"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":"2601.07293","paper":"/paper/arxiv-2601-07293","title":"Inference-Time Scaling for Visual AutoRegressive modeling by Searching Representative Samples","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"WD7ang/VAR-Scaling","path":"VAR-main/models/basic_vae.py","file_url":"https://github.com/WD7ang/VAR-Scaling/blob/HEAD/VAR-main/models/basic_vae.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"793c7e2489dd8dfc","mcp_get_code":{"code_sha256":"793c7e2489dd8dfc"}},{"arxiv_id":"2508.04122","paper":"/paper/arxiv-2508-04122","title":"Conditional Latent Diffusion Models for Zero-Shot Instance Segmentation","date":null,"month_inferred_from_arxiv_id":"2025-08","title_source":"syntology","repo":"DLR-RM/oc-dit","path":"ocdit/models/ocdit.py","file_url":"https://github.com/DLR-RM/oc-dit/blob/HEAD/ocdit/models/ocdit.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7e141c9d5b330940","mcp_get_code":{"code_sha256":"7e141c9d5b330940"}},{"arxiv_id":"2505.12742","paper":"/paper/mvar-visual-autoregressive-modeling-with","title":"MVAR: Visual Autoregressive Modeling with Scale and Spatial Markovian Conditioning","date":"2025-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"labshuhanggu/mvar","path":"models/basic_vae.py","file_url":"https://github.com/labshuhanggu/mvar/blob/HEAD/models/basic_vae.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"793c7e2489dd8dfc","mcp_get_code":{"code_sha256":"793c7e2489dd8dfc"}},{"arxiv_id":"2504.02949","paper":"/paper/vargpt-v1-1-improve-visual-autoregressive","title":"VARGPT-v1.1: Improve Visual Autoregressive Large Unified Model via Iterative Instruction Tuning and Reinforcement Learning","date":"2025-04-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VARGPT-family/VARGPT","path":"vargpt_llava/var_model/models/basic_vae.py","file_url":"https://github.com/VARGPT-family/VARGPT/blob/HEAD/vargpt_llava/var_model/models/basic_vae.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":"793c7e2489dd8dfc","mcp_get_code":{"code_sha256":"793c7e2489dd8dfc"}},{"arxiv_id":"2501.18993","paper":"/paper/visual-autoregressive-modeling-for-image","title":"Visual Autoregressive Modeling for Image Super-Resolution","date":"2025-01-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qyp2000/varsr","path":"models/basic_vae.py","file_url":"https://github.com/qyp2000/varsr/blob/HEAD/models/basic_vae.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"793c7e2489dd8dfc","mcp_get_code":{"code_sha256":"793c7e2489dd8dfc"}},{"arxiv_id":"2412.04431","paper":"/paper/infinity-scaling-bitwise-autoregressive","title":"Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis","date":"2024-12-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"FoundationVision/VAR","path":"models/basic_vae.py","file_url":"https://github.com/FoundationVision/VAR/blob/HEAD/models/basic_vae.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"793c7e2489dd8dfc","mcp_get_code":{"code_sha256":"793c7e2489dd8dfc"}},{"arxiv_id":"2411.10433","paper":"/paper/m-var-decoupled-scale-wise-autoregressive","title":"M-VAR: Decoupled Scale-wise Autoregressive Modeling for High-Quality Image Generation","date":"2024-11-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"oliverrensu/mvar","path":"models/basic_vae.py","file_url":"https://github.com/oliverrensu/mvar/blob/HEAD/models/basic_vae.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"793c7e2489dd8dfc","mcp_get_code":{"code_sha256":"793c7e2489dd8dfc"}},{"arxiv_id":"2411.06959","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/autoencoder.py","file_url":"https://github.com/leaplabthu/enat/blob/HEAD/libs/autoencoder.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f97adc1ae5efb785","mcp_get_code":{"code_sha256":"f97adc1ae5efb785"}},{"arxiv_id":"2410.10812","paper":"/paper/hart-efficient-visual-generation-with-hybrid","title":"HART: Efficient Visual Generation with Hybrid Autoregressive Transformer","date":"2024-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mit-han-lab/hart","path":"hart/modules/networks/basic_vae.py","file_url":"https://github.com/mit-han-lab/hart/blob/HEAD/hart/modules/networks/basic_vae.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"793c7e2489dd8dfc","mcp_get_code":{"code_sha256":"793c7e2489dd8dfc"}},{"arxiv_id":"2408.16532","paper":"/paper/wavtokenizer-an-efficient-acoustic-discrete","title":"WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling","date":"2024-08-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jishengpeng/wavtokenizer","path":"decoder/models.py","file_url":"https://github.com/jishengpeng/wavtokenizer/blob/HEAD/decoder/models.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dba3d5f0d0d4a6f2","mcp_get_code":{"code_sha256":"dba3d5f0d0d4a6f2"}},{"arxiv_id":"2408.08091","paper":"/paper/hair-hypernetworks-based-all-in-one-image","title":"HAIR: Hypernetworks-based All-in-One Image Restoration","date":"2024-08-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"toummHus/HAIR","path":"utils/ResNet.py","file_url":"https://github.com/toummHus/HAIR/blob/HEAD/utils/ResNet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e6bdfc1df5bf356d","mcp_get_code":{"code_sha256":"e6bdfc1df5bf356d"}},{"arxiv_id":"2408.01181","paper":"/paper/2408-01181","title":"VAR-CLIP: Text-to-Image Generator with Visual Auto-Regressive Modeling","date":"2024-08-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"daixiangzi/var-clip","path":"models/basic_vae.py","file_url":"https://github.com/daixiangzi/var-clip/blob/HEAD/models/basic_vae.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"793c7e2489dd8dfc","mcp_get_code":{"code_sha256":"793c7e2489dd8dfc"}},{"arxiv_id":"2408.00372","paper":"/paper/few-shot-defect-image-generation-based-on","title":"Few-shot Defect Image Generation based on Consistency Modeling","date":"2024-08-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ffdd-diffusion/defectdiffu","path":"autoencoder.py","file_url":"https://github.com/ffdd-diffusion/defectdiffu/blob/HEAD/autoencoder.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f97adc1ae5efb785","mcp_get_code":{"code_sha256":"f97adc1ae5efb785"}},{"arxiv_id":"2406.09416","paper":"/paper/alleviating-distortion-in-image-generation","title":"Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models and Time-Dependent Layer Normalization","date":"2024-06-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qihao067/DiMR","path":"libs/autoencoder.py","file_url":"https://github.com/qihao067/DiMR/blob/HEAD/libs/autoencoder.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":"f97adc1ae5efb785","mcp_get_code":{"code_sha256":"f97adc1ae5efb785"}},{"arxiv_id":"2405.17398","paper":"/paper/vista-a-generalizable-driving-world-model","title":"Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability","date":"2024-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"opendrivelab/vista","path":"vwm/models/diffusion.py","file_url":"https://github.com/opendrivelab/vista/blob/HEAD/vwm/models/diffusion.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":"df7cb18ec3f78d30","mcp_get_code":{"code_sha256":"df7cb18ec3f78d30"}},{"arxiv_id":"2405.11273","paper":"/paper/uni-moe-scaling-unified-multimodal-llms-with","title":"Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts","date":"2024-05-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hitsz-tmg/umoe-scaling-unified-multimodal-llms","path":"Uni-MoE-2/decoder/models.py","file_url":"https://github.com/hitsz-tmg/umoe-scaling-unified-multimodal-llms/blob/HEAD/Uni-MoE-2/decoder/models.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"dba3d5f0d0d4a6f2","mcp_get_code":{"code_sha256":"dba3d5f0d0d4a6f2"}},{"arxiv_id":"2404.02905","paper":"/paper/visual-autoregressive-modeling-scalable-image","title":"Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction","date":"2024-04-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"EkaterinaXie/LiteVAR","path":"models/basic_vae.py","file_url":"https://github.com/EkaterinaXie/LiteVAR/blob/HEAD/models/basic_vae.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"793c7e2489dd8dfc","mcp_get_code":{"code_sha256":"793c7e2489dd8dfc"}},{"arxiv_id":"2404.00815","paper":"/paper/towards-realistic-scene-generation-with-lidar","title":"Towards Realistic Scene Generation with LiDAR Diffusion Models","date":"2024-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hancyran/lidar-diffusion","path":"lidm/modules/diffusion/model_lidm.py","file_url":"https://github.com/hancyran/lidar-diffusion/blob/HEAD/lidm/modules/diffusion/model_lidm.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"321eebc8c4fd6b54","mcp_get_code":{"code_sha256":"321eebc8c4fd6b54"}},{"arxiv_id":"2402.14167","paper":"/paper/t-stitch-accelerating-sampling-in-pre-trained","title":"T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching","date":"2024-02-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nvlabs/t-stitch","path":"dit/autoencoder.py","file_url":"https://github.com/nvlabs/t-stitch/blob/HEAD/dit/autoencoder.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f97adc1ae5efb785","mcp_get_code":{"code_sha256":"f97adc1ae5efb785"}},{"arxiv_id":"2306.09305","paper":"/paper/fast-training-of-diffusion-models-with-masked","title":"Fast Training of Diffusion Models with Masked Transformers","date":"2023-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"anima-lab/maskdit","path":"autoencoder.py","file_url":"https://github.com/anima-lab/maskdit/blob/HEAD/autoencoder.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f97adc1ae5efb785","mcp_get_code":{"code_sha256":"f97adc1ae5efb785"}},{"arxiv_id":"2211.13221","paper":"/paper/latent-video-diffusion-models-for-high","title":"Latent Video Diffusion Models for High-Fidelity Long Video Generation","date":"2022-11-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yingqinghe/lvdm","path":"lvdm/models/modules/aemodules.py","file_url":"https://github.com/yingqinghe/lvdm/blob/HEAD/lvdm/models/modules/aemodules.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ff5ec4cc14b9e9b2","mcp_get_code":{"code_sha256":"ff5ec4cc14b9e9b2"}},{"arxiv_id":"2207.12598","paper":"/paper/classifier-free-diffusion-guidance","title":"Classifier-Free Diffusion Guidance","date":"2022-07-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"g4vrel/DDPM","path":"sample.py","file_url":"https://github.com/g4vrel/DDPM/blob/HEAD/sample.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fc896cf6190912f4","mcp_get_code":{"code_sha256":"fc896cf6190912f4"}}]}