{"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-padding","entry":"get_padding","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":84,"n_papers_ran":75,"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":22,"n_samples_ran":13,"n_samples_fingerprinted":12,"n_places":84,"n_places_pointer_only":20,"by_status":{"ran_honours":6,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":7,"unverified":9},"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":"2608.12099","paper":"/paper/arxiv-2608-12099","title":"RT-SEMamba: Real-Time Speech Enhancement Mamba via Progressive Knowledge Distillation","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"RoyChao19477/RT-SEMamba","path":"models/codec_module.py","file_url":"https://github.com/RoyChao19477/RT-SEMamba/blob/HEAD/models/codec_module.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"8d8c73f0ce5fe86b","mcp_get_code":{"code_sha256":"8d8c73f0ce5fe86b"}},{"arxiv_id":"2608.07713","paper":"/paper/arxiv-2608-07713","title":"Tokenizer-Generator Coupling in Medical Image Generation","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"liamchalcroft/medtokenizers","path":"src/medtokenizers/modules/layers.py","file_url":"https://github.com/liamchalcroft/medtokenizers/blob/HEAD/src/medtokenizers/modules/layers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b10e8e79b1c89c97","mcp_get_code":{"code_sha256":"b10e8e79b1c89c97"}},{"arxiv_id":"2507.20731","paper":null,"title":"arXiv:2507.20731","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"Andong-Li-speech/RNDVoC","path":"utils.py","file_url":"https://github.com/Andong-Li-speech/RNDVoC/blob/HEAD/utils.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2504.00858","paper":"/paper/whispering-under-the-eaves-protecting-user","title":"Whispering Under the Eaves: Protecting User Privacy Against Commercial and LLM-powered Automatic Speech Recognition Systems","date":"2025-04-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"WeifeiJin/AudioShield","path":"commons.py","file_url":"https://github.com/WeifeiJin/AudioShield/blob/HEAD/commons.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2410.23623","paper":"/paper/on-learning-multi-modal-forgery","title":"On Learning Multi-Modal Forgery Representation for Diffusion Generated Video Detection","date":"2024-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sparklexfantasy/mm-det","path":"models/vit/resnet.py","file_url":"https://github.com/sparklexfantasy/mm-det/blob/HEAD/models/vit/resnet.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":"10e6af69cd89654c","mcp_get_code":{"code_sha256":"10e6af69cd89654c"}},{"arxiv_id":"2410.20742","paper":"/paper/mitigating-unauthorized-speech-synthesis-for","title":"Mitigating Unauthorized Speech Synthesis for Voice Protection","date":"2024-10-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wxzyd123/pivotal_objective_perturbation","path":"vits/commons.py","file_url":"https://github.com/wxzyd123/pivotal_objective_perturbation/blob/HEAD/vits/commons.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2409.19865","paper":"/paper/tokenbinder-text-video-retrieval-with-one-to","title":"TokenBinder: Text-Video Retrieval with One-to-Many Alignment Paradigm","date":"2024-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bingqingzhang/TokenBinder","path":"src/datasets/data_utils.py","file_url":"https://github.com/bingqingzhang/TokenBinder/blob/HEAD/src/datasets/data_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0cf387da46369b1a","mcp_get_code":{"code_sha256":"0cf387da46369b1a"}},{"arxiv_id":"2409.12346","paper":"/paper/simultaneous-music-separation-and-generation","title":"Simultaneous Music Separation and Generation Using Multi-Track Latent Diffusion Models","date":null,"month_inferred_from_arxiv_id":"2024-09","title_source":"archive","repo":"karchkha/msg-ld","path":"src/hifigan/models.py","file_url":"https://github.com/karchkha/msg-ld/blob/HEAD/src/hifigan/models.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2409.00587","paper":"/paper/flux-that-plays-music","title":"FLUX that Plays Music","date":"2024-09-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"feizc/fluxmusic","path":"audioldm2/hifigan/models.py","file_url":"https://github.com/feizc/fluxmusic/blob/HEAD/audioldm2/hifigan/models.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2408.15297","paper":"/paper/yolo-stutter-end-to-end-region-wise-speech","title":"YOLO-Stutter: End-to-end Region-Wise Speech Dysfluency Detection","date":"2024-08-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rorizzz/yolo-stutter","path":"yolo-stutter/utils/vits/commons.py","file_url":"https://github.com/rorizzz/yolo-stutter/blob/HEAD/yolo-stutter/utils/vits/commons.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2407.02869","paper":"/paper/picoaudio-enabling-precise-timestamp-and","title":"PicoAudio: Enabling Precise Timestamp and Frequency Controllability of Audio Events in Text-to-audio Generation","date":null,"month_inferred_from_arxiv_id":"2024-07","title_source":"archive","repo":"picoaudio/picoaudio","path":"picoaudio/audioldm/hifigan/models.py","file_url":"https://github.com/picoaudio/picoaudio/blob/HEAD/picoaudio/audioldm/hifigan/models.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2406.15487","paper":"/paper/2406-15487","title":"Improving Text-To-Audio Models with Synthetic Captions","date":"2024-06-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"declare-lab/tango","path":"audioldm/hifigan/models.py","file_url":"https://github.com/declare-lab/tango/blob/HEAD/audioldm/hifigan/models.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2406.10056","paper":"/paper/uniaudio-1-5-large-language-model-driven","title":"UniAudio 1.5: Large Language Model-driven Audio Codec is A Few-shot Audio Task Learner","date":null,"month_inferred_from_arxiv_id":"2024-06","title_source":"archive","repo":"yangdongchao/llm-codec","path":"codec/module.py","file_url":"https://github.com/yangdongchao/llm-codec/blob/HEAD/codec/module.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2406.04673","paper":"/paper/melfusion-synthesizing-music-from-image-and","title":"MeLFusion: Synthesizing Music from Image and Language Cues using Diffusion Models","date":"2024-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"schowdhury671/melfusion","path":"audioldm/hifigan/models.py","file_url":"https://github.com/schowdhury671/melfusion/blob/HEAD/audioldm/hifigan/models.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2406.02250","paper":"/paper/multi-stage-speech-bandwidth-extension-with","title":"Multi-Stage Speech Bandwidth Extension with Flexible Sampling Rate Control","date":"2024-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yxlu-0102/AP-BWE","path":"utils.py","file_url":"https://github.com/yxlu-0102/AP-BWE/blob/HEAD/utils.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2406.00320","paper":"/paper/frieren-efficient-video-to-audio-generation","title":"Frieren: Efficient Video-to-Audio Generation Network with Rectified Flow Matching","date":"2024-06-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cyanbx/Frieren-V2A","path":"Frieren/vocoder/bigvgan/models.py","file_url":"https://github.com/cyanbx/Frieren-V2A/blob/HEAD/Frieren/vocoder/bigvgan/models.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2406.04350","paper":"/paper/prompt-guided-precise-audio-editing-with","title":"Prompt-guided Precise Audio Editing with Diffusion Models","date":"2024-05-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"haoheliu/audioldm","path":"audioldm/hifigan/models.py","file_url":"https://github.com/haoheliu/audioldm/blob/HEAD/audioldm/hifigan/models.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2405.16466","paper":"/paper/high-performance-temporal-reversible-spiking","title":"High-Performance Temporal Reversible Spiking Neural Networks with $O(L)$ Training Memory and $O(1)$ Inference Cost","date":"2024-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MindSpore-scientific-2/code-7","path":"ms_spike_modules.py","file_url":"https://github.com/MindSpore-scientific-2/code-7/blob/HEAD/ms_spike_modules.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":"e2a6feec71c8cf83","mcp_get_code":{"code_sha256":"e2a6feec71c8cf83"}},{"arxiv_id":"2405.06573","paper":"/paper/an-investigation-of-incorporating-mamba-for","title":"An Investigation of Incorporating Mamba for Speech Enhancement","date":"2024-05-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"roychao19477/semamba","path":"models/codec_module.py","file_url":"https://github.com/roychao19477/semamba/blob/HEAD/models/codec_module.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"3ae5fbca1fc048c3","mcp_get_code":{"code_sha256":"3ae5fbca1fc048c3"}},{"arxiv_id":"2405.04752","paper":"/paper/hilcodec-high-fidelity-and-lightweight-neural","title":"HILCodec: High-Fidelity and Lightweight Neural Audio Codec","date":"2024-05-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aask1357/hilcodec","path":"models/hilcodec/avocodo.py","file_url":"https://github.com/aask1357/hilcodec/blob/HEAD/models/hilcodec/avocodo.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e28f4ff393bc05c9","mcp_get_code":{"code_sha256":"e28f4ff393bc05c9"}},{"arxiv_id":"2405.00233","paper":"/paper/semanticodec-an-ultra-low-bitrate-semantic","title":"SemantiCodec: An Ultra Low Bitrate Semantic Audio Codec for General Sound","date":"2024-04-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"haoheliu/SemantiCodec-inference","path":"semanticodec/modules/decoder/hifigan/models.py","file_url":"https://github.com/haoheliu/SemantiCodec-inference/blob/HEAD/semanticodec/modules/decoder/hifigan/models.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2404.14381","paper":"/paper/tavgbench-benchmarking-text-to-audible-video","title":"TAVGBench: Benchmarking Text to Audible-Video Generation","date":"2024-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"opennlplab/tavgbench","path":"audioldm/hifigan/models.py","file_url":"https://github.com/opennlplab/tavgbench/blob/HEAD/audioldm/hifigan/models.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2404.05102","paper":"/paper/lhu-net-a-light-hybrid-u-net-for-cost","title":"LHU-Net: A Light Hybrid U-Net for Cost-Efficient, High-Performance Volumetric Medical Image Segmentation","date":"2024-04-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xmindflow/lhunet","path":"src/lhunet/blocks/base.py","file_url":"https://github.com/xmindflow/lhunet/blob/HEAD/src/lhunet/blocks/base.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":"151da3467d6ad085","mcp_get_code":{"code_sha256":"151da3467d6ad085"}},{"arxiv_id":"2403.17008","paper":"/paper/flashface-human-image-personalization-with","title":"FlashFace: Human Image Personalization with High-fidelity Identity Preservation","date":"2024-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ali-vilab/FlashFace","path":"flashface/all_finetune/utils.py","file_url":"https://github.com/ali-vilab/FlashFace/blob/HEAD/flashface/all_finetune/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"a5d1b4f3238f5aab","mcp_get_code":{"code_sha256":"a5d1b4f3238f5aab"}},{"arxiv_id":"2312.11947","paper":"/paper/emotion-rendering-for-conversational-speech","title":"Emotion Rendering for Conversational Speech Synthesis with Heterogeneous Graph-Based Context Modeling","date":"2023-12-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"walker-hyf/ecss","path":"hifigan/models.py","file_url":"https://github.com/walker-hyf/ecss/blob/HEAD/hifigan/models.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2312.01479","paper":"/paper/openvoice-versatile-instant-voice-cloning","title":"OpenVoice: Versatile Instant Voice Cloning","date":"2023-12-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"myshell-ai/openvoice","path":"openvoice/commons.py","file_url":"https://github.com/myshell-ai/openvoice/blob/HEAD/openvoice/commons.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2311.14957","paper":"/paper/multi-scale-sub-band-constant-q-transform","title":"Multi-Scale Sub-Band Constant-Q Transform Discriminator for High-Fidelity Vocoder","date":null,"month_inferred_from_arxiv_id":"2023-11","title_source":"archive","repo":"nvidia/bigvgan","path":"utils.py","file_url":"https://github.com/nvidia/bigvgan/blob/HEAD/utils.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2311.08355","paper":"/paper/mustango-toward-controllable-text-to-music","title":"Mustango: Toward Controllable Text-to-Music Generation","date":"2023-11-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amaai-lab/mustango","path":"audioldm/hifigan/models.py","file_url":"https://github.com/amaai-lab/mustango/blob/HEAD/audioldm/hifigan/models.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2311.04693","paper":"/paper/diff-hiervc-diffusion-based-hierarchical","title":"Diff-HierVC: Diffusion-based Hierarchical Voice Conversion with Robust Pitch Generation and Masked Prior for Zero-shot Speaker Adaptation","date":"2023-11-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hayeong0/Diff-HierVC","path":"module/commons.py","file_url":"https://github.com/hayeong0/Diff-HierVC/blob/HEAD/module/commons.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2310.14344","paper":"/paper/what-s-in-a-prior-learned-proximal-networks","title":"What's in a Prior? Learned Proximal Networks for Inverse Problems","date":"2023-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sulam-group/learned-proximal-networks","path":"lpn/networks/lpn_mnist.py","file_url":"https://github.com/sulam-group/learned-proximal-networks/blob/HEAD/lpn/networks/lpn_mnist.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":"79771be175dbb37c","mcp_get_code":{"code_sha256":"79771be175dbb37c"}},{"arxiv_id":"2310.04412","paper":"/paper/fedconv-enhancing-convolutional-neural","title":"FedConv: Enhancing Convolutional Neural Networks for Handling Data Heterogeneity in Federated Learning","date":"2023-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ucsc-vlaa/fedconv","path":"models/fedconv.py","file_url":"https://github.com/ucsc-vlaa/fedconv/blob/HEAD/models/fedconv.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9b02c1068795fd5b","mcp_get_code":{"code_sha256":"9b02c1068795fd5b"}},{"arxiv_id":"2310.01889","paper":"/paper/ring-attention-with-blockwise-transformers","title":"Ring Attention with Blockwise Transformers for Near-Infinite Context","date":"2023-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"seongho608/ringformer","path":"commons.py","file_url":"https://github.com/seongho608/ringformer/blob/HEAD/commons.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2310.00567","paper":"/paper/understanding-the-robustness-of-randomized","title":"Understanding the Robustness of Randomized Feature Defense Against Query-Based Adversarial Attacks","date":"2023-10-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mail-research/randomized_defenses","path":"models/resnet.py","file_url":"https://github.com/mail-research/randomized_defenses/blob/HEAD/models/resnet.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"9b02c1068795fd5b","mcp_get_code":{"code_sha256":"9b02c1068795fd5b"}},{"arxiv_id":"2309.10740","paper":"/paper/accelerating-diffusion-based-text-to-audio","title":"ConsistencyTTA: Accelerating Diffusion-Based Text-to-Audio Generation with Consistency Distillation","date":"2023-09-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Bai-YT/ConsistencyTTA","path":"audioldm/hifigan/models.py","file_url":"https://github.com/Bai-YT/ConsistencyTTA/blob/HEAD/audioldm/hifigan/models.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2308.16692","paper":"/paper/speechtokenizer-unified-speech-tokenizer-for","title":"SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models","date":"2023-08-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZhangXInFD/SpeechTokenizer","path":"speechtokenizer/discriminators.py","file_url":"https://github.com/ZhangXInFD/SpeechTokenizer/blob/HEAD/speechtokenizer/discriminators.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2308.08926","paper":"/paper/explicit-estimation-of-magnitude-and-phase","title":"Explicit Estimation of Magnitude and Phase Spectra in Parallel for High-Quality Speech Enhancement","date":"2023-08-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yxlu-0102/MP-SENet","path":"models/conformer.py","file_url":"https://github.com/yxlu-0102/MP-SENet/blob/HEAD/models/conformer.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2308.05734","paper":"/paper/audioldm-2-learning-holistic-audio-generation","title":"AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining","date":"2023-08-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"haoheliu/AudioLDM2","path":"audioldm2/hifigan/models.py","file_url":"https://github.com/haoheliu/AudioLDM2/blob/HEAD/audioldm2/hifigan/models.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2308.01546","paper":"/paper/musicldm-enhancing-novelty-in-text-to-music","title":"MusicLDM: Enhancing Novelty in Text-to-Music Generation Using Beat-Synchronous Mixup Strategies","date":"2023-08-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"retrocirce/musicldm","path":"interface/src/hifigan/models.py","file_url":"https://github.com/retrocirce/musicldm/blob/HEAD/interface/src/hifigan/models.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2305.19709","paper":"/paper/xphonebert-a-pre-trained-multilingual-model","title":"XPhoneBERT: A Pre-trained Multilingual Model for Phoneme Representations for Text-to-Speech","date":"2023-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vinairesearch/xphonebert","path":"VITS_with_XPhoneBERT/commons.py","file_url":"https://github.com/vinairesearch/xphonebert/blob/HEAD/VITS_with_XPhoneBERT/commons.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2303.08594","paper":"/paper/fastinst-a-simple-query-based-model-for-real","title":"FastInst: A Simple Query-Based Model for Real-Time Instance Segmentation","date":"2023-03-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"junjiehe96/fastinst","path":"fastinst/modeling/backbone/resnet.py","file_url":"https://github.com/junjiehe96/fastinst/blob/HEAD/fastinst/modeling/backbone/resnet.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9b02c1068795fd5b","mcp_get_code":{"code_sha256":"9b02c1068795fd5b"}},{"arxiv_id":"2303.04995","paper":"/paper/text-visual-prompting-for-efficient-2d","title":"Text-Visual Prompting for Efficient 2D Temporal Video Grounding","date":"2023-03-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"intel/TVP","path":"src/datasets/data_utils.py","file_url":"https://github.com/intel/TVP/blob/HEAD/src/datasets/data_utils.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":"0cf387da46369b1a","mcp_get_code":{"code_sha256":"0cf387da46369b1a"}},{"arxiv_id":"2301.06116","paper":"/paper/maximally-compact-and-separated-features-with","title":"Maximally Compact and Separated Features with Regular Polytope Networks","date":"2023-01-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"matteo-bruni/regular-polytope-networks","path":"models/imagenet/timm_fixed_resnet.py","file_url":"https://github.com/matteo-bruni/regular-polytope-networks/blob/HEAD/models/imagenet/timm_fixed_resnet.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9b02c1068795fd5b","mcp_get_code":{"code_sha256":"9b02c1068795fd5b"}},{"arxiv_id":"2212.14518","paper":"/paper/resgrad-residual-denoising-diffusion","title":"ResGrad: Residual Denoising Diffusion Probabilistic Models for Text to Speech","date":"2022-12-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"majidAdibian77/ResGrad","path":"vocoder/models.py","file_url":"https://github.com/majidAdibian77/ResGrad/blob/HEAD/vocoder/models.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2212.14227","paper":"/paper/styletts-vc-one-shot-voice-conversion-by","title":"StyleTTS-VC: One-Shot Voice Conversion by Knowledge Transfer from Style-Based TTS Models","date":"2022-12-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yl4579/StyleTTS-VC","path":"Demo/hifi-gan/vocoder_utils.py","file_url":"https://github.com/yl4579/StyleTTS-VC/blob/HEAD/Demo/hifi-gan/vocoder_utils.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2211.02701","paper":"/paper/monai-an-open-source-framework-for-deep","title":"MONAI: An open-source framework for deep learning in healthcare","date":"2022-11-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yaziciz/GLIMS","path":"Modules/conv_generator.py","file_url":"https://github.com/yaziciz/GLIMS/blob/HEAD/Modules/conv_generator.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3d2504e21805394d","mcp_get_code":{"code_sha256":"3d2504e21805394d"}},{"arxiv_id":"2208.10169","paper":"/paper/multi-granularity-distillation-scheme-towards","title":"Multi-Granularity Distillation Scheme Towards Lightweight Semi-Supervised Semantic Segmentation","date":"2022-08-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JayQine/MGD-SSSS","path":"exp.city/city8.resnet18_deeplabv3plus/wide_resnet.py","file_url":"https://github.com/JayQine/MGD-SSSS/blob/HEAD/exp.city/city8.resnet18_deeplabv3plus/wide_resnet.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9b02c1068795fd5b","mcp_get_code":{"code_sha256":"9b02c1068795fd5b"}},{"arxiv_id":"2207.06953","paper":"/paper/tackling-background-distraction-in-video","title":"Tackling Background Distraction in Video Object Segmentation","date":"2022-07-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"suhwan-cho/tbd","path":"tbd.py","file_url":"https://github.com/suhwan-cho/tbd/blob/HEAD/tbd.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"35390a54a05ee368","mcp_get_code":{"code_sha256":"35390a54a05ee368"}},{"arxiv_id":"2207.01063","paper":"/paper/dailytalk-spoken-dialogue-dataset-for","title":"DailyTalk: Spoken Dialogue Dataset for Conversational Text-to-Speech","date":"2022-07-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"keonlee9420/DailyTalk","path":"hifigan/models.py","file_url":"https://github.com/keonlee9420/DailyTalk/blob/HEAD/hifigan/models.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2206.04658","paper":"/paper/bigvgan-a-universal-neural-vocoder-with-large","title":"BigVGAN: A Universal Neural Vocoder with Large-Scale Training","date":"2022-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sh-lee-prml/BigVGAN","path":"commons.py","file_url":"https://github.com/sh-lee-prml/BigVGAN/blob/HEAD/commons.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2206.03452","paper":"/paper/can-cnns-be-more-robust-than-transformers","title":"Can CNNs Be More Robust Than Transformers?","date":"2022-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ucsc-vlaa/robustcnn","path":"timm/models/robust_resnet.py","file_url":"https://github.com/ucsc-vlaa/robustcnn/blob/HEAD/timm/models/robust_resnet.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9b02c1068795fd5b","mcp_get_code":{"code_sha256":"9b02c1068795fd5b"}},{"arxiv_id":"2206.03428","paper":"/paper/revealing-single-frame-bias-for-video-and","title":"Revealing Single Frame Bias for Video-and-Language Learning","date":"2022-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jayleicn/ClipBERT","path":"src/datasets/data_utils.py","file_url":"https://github.com/jayleicn/ClipBERT/blob/HEAD/src/datasets/data_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0cf387da46369b1a","mcp_get_code":{"code_sha256":"0cf387da46369b1a"}},{"arxiv_id":"2206.00843","paper":"/paper/depthshrinker-a-new-compression-paradigm","title":"DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks","date":"2022-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/depthshrinker","path":"models/efficientnet_blocks.py","file_url":"https://github.com/facebookresearch/depthshrinker/blob/HEAD/models/efficientnet_blocks.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"73876e077d3acdf5","mcp_get_code":{"code_sha256":"73876e077d3acdf5"}},{"arxiv_id":"2205.15439","paper":"/paper/styletts-a-style-based-generative-model-for","title":"StyleTTS: A Style-Based Generative Model for Natural and Diverse Text-to-Speech Synthesis","date":"2022-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yl4579/StyleTTS","path":"Demo/hifi-gan/vocoder_utils.py","file_url":"https://github.com/yl4579/StyleTTS/blob/HEAD/Demo/hifi-gan/vocoder_utils.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2205.13490","paper":"/paper/semaffinet-semantic-affine-transformation-for","title":"SemAffiNet: Semantic-Affine Transformation for Point Cloud Segmentation","date":"2022-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wangzy22/SemAffiNet","path":"models/resnet_d.py","file_url":"https://github.com/wangzy22/SemAffiNet/blob/HEAD/models/resnet_d.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9b02c1068795fd5b","mcp_get_code":{"code_sha256":"9b02c1068795fd5b"}},{"arxiv_id":"2205.08993","paper":"/paper/leveraging-pseudo-labeled-data-to-improve","title":"Leveraging Pseudo-labeled Data to Improve Direct Speech-to-Speech Translation","date":"2022-05-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fengpeng-yue/speech-to-speech-translation","path":"fairseq/models/text_to_speech/hifigan.py","file_url":"https://github.com/fengpeng-yue/speech-to-speech-translation/blob/HEAD/fairseq/models/text_to_speech/hifigan.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"e2d8bffab41b5bf5","mcp_get_code":{"code_sha256":"e2d8bffab41b5bf5"}},{"arxiv_id":"2204.05841","paper":"/paper/voicefixer-a-unified-framework-for-high","title":"VoiceFixer: A Unified Framework for High-Fidelity Speech Restoration","date":"2022-04-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"haoheliu/voicefixer","path":"voicefixer/vocoder/model/res_msd.py","file_url":"https://github.com/haoheliu/voicefixer/blob/HEAD/voicefixer/vocoder/model/res_msd.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2203.13086","paper":"/paper/hifi-a-unified-framework-for-neural-vocoding","title":"HiFi++: a Unified Framework for Bandwidth Extension and Speech Enhancement","date":"2022-03-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rishikksh20/HiFiplusplus-pytorch","path":"utils.py","file_url":"https://github.com/rishikksh20/HiFiplusplus-pytorch/blob/HEAD/utils.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2203.12827","paper":"/paper/sparse-instance-activation-for-real-time","title":"Sparse Instance Activation for Real-Time Instance Segmentation","date":"2022-03-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hustvl/sparseinst","path":"sparseinst/backbones/resnet.py","file_url":"https://github.com/hustvl/sparseinst/blob/HEAD/sparseinst/backbones/resnet.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9b02c1068795fd5b","mcp_get_code":{"code_sha256":"9b02c1068795fd5b"}},{"arxiv_id":"2203.02395","paper":"/paper/istftnet-fast-and-lightweight-mel-spectrogram","title":"iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform","date":"2022-03-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hcy71o/autovocoder","path":"utils.py","file_url":"https://github.com/hcy71o/autovocoder/blob/HEAD/utils.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2202.13277","paper":"/paper/learning-the-beauty-in-songs-neural-singing","title":"Learning the Beauty in Songs: Neural Singing Voice Beautifier","date":"2022-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MoonInTheRiver/DiffSinger","path":"modules/hifigan/hifigan.py","file_url":"https://github.com/MoonInTheRiver/DiffSinger/blob/HEAD/modules/hifigan/hifigan.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2202.07359","paper":"/paper/textless-lib-a-library-for-textless-spoken","title":"textless-lib: a Library for Textless Spoken Language Processing","date":"2022-02-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/textlesslib","path":"textless/vocoders/hifigan/vocoder.py","file_url":"https://github.com/facebookresearch/textlesslib/blob/HEAD/textless/vocoders/hifigan/vocoder.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e2d8bffab41b5bf5","mcp_get_code":{"code_sha256":"e2d8bffab41b5bf5"}},{"arxiv_id":"2201.12904","paper":"/paper/coin-data-agnostic-neural-compression","title":"COIN++: Neural Compression Across Modalities","date":"2022-01-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"emiliendupont/coinpp","path":"coinpp/patching.py","file_url":"https://github.com/emiliendupont/coinpp/blob/HEAD/coinpp/patching.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"51be69bc13ec8685","mcp_get_code":{"code_sha256":"51be69bc13ec8685"}},{"arxiv_id":"2201.11972","paper":"/paper/diffgan-tts-high-fidelity-and-efficient-text","title":"DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANs","date":"2022-01-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"komyeongjin/specdiff-gan","path":"hifigan/models.py","file_url":"https://github.com/komyeongjin/specdiff-gan/blob/HEAD/hifigan/models.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2110.10139","paper":"/paper/chunked-autoregressive-gan-for-conditional-1","title":"Chunked Autoregressive GAN for Conditional Waveform Synthesis","date":"2021-10-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"descriptinc/cargan","path":"cargan/model/gantts/generator.py","file_url":"https://github.com/descriptinc/cargan/blob/HEAD/cargan/model/gantts/generator.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"71b22ea23d67828e","mcp_get_code":{"code_sha256":"71b22ea23d67828e"}},{"arxiv_id":"2110.07641","paper":"/paper/non-deep-networks-1","title":"Non-deep Networks","date":"2021-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"imankgoyal/NonDeepNetworks","path":"imagenet/timm/models/resnet.py","file_url":"https://github.com/imankgoyal/NonDeepNetworks/blob/HEAD/imagenet/timm/models/resnet.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"9b02c1068795fd5b","mcp_get_code":{"code_sha256":"9b02c1068795fd5b"}},{"arxiv_id":"2109.15166","paper":"/paper/portaspeech-portable-and-high-quality","title":"PortaSpeech: Portable and High-Quality Generative Text-to-Speech","date":"2021-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"keonlee9420/PortaSpeech","path":"hifigan/models.py","file_url":"https://github.com/keonlee9420/PortaSpeech/blob/HEAD/hifigan/models.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2106.07889","paper":"/paper/univnet-a-neural-vocoder-with-multi","title":"UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation","date":"2021-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rishikksh20/UnivNet-pytorch","path":"utils.py","file_url":"https://github.com/rishikksh20/UnivNet-pytorch/blob/HEAD/utils.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2106.06103","paper":"/paper/conditional-variational-autoencoder-with","title":"Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech","date":null,"month_inferred_from_arxiv_id":"2021-06","title_source":"archive","repo":"isletennos/mmvc_trainer","path":"models.py","file_url":"https://github.com/isletennos/mmvc_trainer/blob/HEAD/models.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2106.03153","paper":"/paper/meta-stylespeech-multi-speaker-adaptive-text","title":"Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation","date":"2021-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"keonlee9420/StyleSpeech","path":"hifigan/models.py","file_url":"https://github.com/keonlee9420/StyleSpeech/blob/HEAD/hifigan/models.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2104.08215","paper":"/paper/bnn-bn-training-binary-neural-networks","title":"\"BNN - BN = ?\": Training Binary Neural Networks without Batch Normalization","date":"2021-04-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VITA-Group/BNN_NoBN","path":"layers.py","file_url":"https://github.com/VITA-Group/BNN_NoBN/blob/HEAD/layers.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"73876e077d3acdf5","mcp_get_code":{"code_sha256":"73876e077d3acdf5"}},{"arxiv_id":"2103.14574","paper":"/paper/parallel-tacotron-2-a-non-autoregressive","title":"Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modeling","date":null,"month_inferred_from_arxiv_id":"2021-03","title_source":"archive","repo":"keonlee9420/Cross-Speaker-Emotion-Transfer","path":"hifigan/models.py","file_url":"https://github.com/keonlee9420/Cross-Speaker-Emotion-Transfer/blob/HEAD/hifigan/models.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2006.06873","paper":"/paper/fastpitch-parallel-text-to-speech-with-pitch","title":"FastPitch: Parallel Text-to-speech with Pitch Prediction","date":"2020-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"keonlee9420/FastPitchFormant","path":"hifigan/models.py","file_url":"https://github.com/keonlee9420/FastPitchFormant/blob/HEAD/hifigan/models.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2006.04558","paper":"/paper/fastspeech-2-fast-and-high-quality-end-to-end","title":"FastSpeech 2: Fast and High-Quality End-to-End Text to Speech","date":"2020-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mtresearcher/FastSpeech2","path":"hifigan/models.py","file_url":"https://github.com/mtresearcher/FastSpeech2/blob/HEAD/hifigan/models.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2003.13678","paper":"/paper/designing-network-design-spaces","title":"Designing Network Design Spaces","date":"2020-03-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZHANGHeng19931123/MutualGuide","path":"models/backbone/gpunet_backbone.py","file_url":"https://github.com/ZHANGHeng19931123/MutualGuide/blob/HEAD/models/backbone/gpunet_backbone.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"73876e077d3acdf5","mcp_get_code":{"code_sha256":"73876e077d3acdf5"}},{"arxiv_id":"1910.10838","paper":"/paper/zero-shot-multi-speaker-text-to-speech-with","title":"Zero-Shot Multi-Speaker Text-To-Speech with State-of-the-art Neural Speaker Embeddings","date":null,"month_inferred_from_arxiv_id":"2019-10","title_source":"archive","repo":"keonlee9420/Comprehensive-Tacotron2","path":"hifigan/models.py","file_url":"https://github.com/keonlee9420/Comprehensive-Tacotron2/blob/HEAD/hifigan/models.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"1909.01187","paper":"/paper/encode-tag-realize-high-precision-text","title":"Encode, Tag, Realize: High-Precision Text Editing","date":"2019-09-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-research/lasertagger","path":"official_transformer/model_utils.py","file_url":"https://github.com/google-research/lasertagger/blob/HEAD/official_transformer/model_utils.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":"759afd2d7986d5ef","mcp_get_code":{"code_sha256":"759afd2d7986d5ef"}},{"arxiv_id":"1807.11164","paper":"/paper/shufflenet-v2-practical-guidelines-for","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","date":"2018-07-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mnicnc404/CartoonGan-tensorflow","path":"layers.py","file_url":"https://github.com/mnicnc404/CartoonGan-tensorflow/blob/HEAD/layers.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":"2fa780cf05243f82","mcp_get_code":{"code_sha256":"2fa780cf05243f82"}},{"arxiv_id":"1806.03185","paper":"/paper/wave-u-net-a-multi-scale-neural-network-for","title":"Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation","date":"2018-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"satvik-venkatesh/Wave-U-net-TF2","path":"wave_u_net.py","file_url":"https://github.com/satvik-venkatesh/Wave-U-net-TF2/blob/HEAD/wave_u_net.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d8372ce707c3095c","mcp_get_code":{"code_sha256":"d8372ce707c3095c"}},{"arxiv_id":"1512.03385","paper":"/paper/deep-residual-learning-for-image-recognition","title":"Deep Residual Learning for Image Recognition","date":"2015-12-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xslidi/EfficientNets_ddl_apex","path":"models/resnet.py","file_url":"https://github.com/xslidi/EfficientNets_ddl_apex/blob/HEAD/models/resnet.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9b02c1068795fd5b","mcp_get_code":{"code_sha256":"9b02c1068795fd5b"}},{"arxiv_id":"0705.2011","paper":"/paper/multi-dimensional-recurrent-neural-networks","title":"Multi-Dimensional Recurrent Neural Networks","date":"2007-05-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jzbjyb/rri_match","path":"represent.py","file_url":"https://github.com/jzbjyb/rri_match/blob/HEAD/represent.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":"3e2732158df7801d","mcp_get_code":{"code_sha256":"3e2732158df7801d"}},{"arxiv_id":"openreview_5EXWftfZlE","paper":null,"title":"arXiv:openreview_5EXWftfZlE","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"XinmengXu/NSC-Net","path":"nsc_net/models/NSCNet.py","file_url":"https://github.com/XinmengXu/NSC-Net/blob/HEAD/nsc_net/models/NSCNet.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"Cai_IIEU_Rethinking_Neural_Feature_Activation_from_Decision-Making_ICCV_2023_paper","paper":null,"title":"arXiv:Cai_IIEU_Rethinking_Neural_Feature_Activation_from_Decision-Making_ICCV_2023_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"SudongCAI/IIEU","path":"MODELS/resnet_elu_timm.py","file_url":"https://github.com/SudongCAI/IIEU/blob/HEAD/MODELS/resnet_elu_timm.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b02c1068795fd5b","mcp_get_code":{"code_sha256":"9b02c1068795fd5b"}},{"arxiv_id":"2024.naacl-long.459","paper":null,"title":"arXiv:2024.naacl-long.459","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"AMAAI-Lab/mustango","path":"audioldm/hifigan/models.py","file_url":"https://github.com/AMAAI-Lab/mustango/blob/HEAD/audioldm/hifigan/models.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"arxiv_id":"2024.findings-acl.404","paper":null,"title":"arXiv:2024.findings-acl.404","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"GalaxyCong/StyleDubber","path":"hifigan/models.py","file_url":"https://github.com/GalaxyCong/StyleDubber/blob/HEAD/hifigan/models.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a26f85d7c72ef39a","mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}}]}