{"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/round-ste","entry":"round_ste","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":18,"n_papers_ran":15,"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":6,"n_samples_ran":3,"n_samples_fingerprinted":3,"n_places":18,"n_places_pointer_only":8,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":0,"ran":0,"unverified":3},"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":"2602.02546","paper":"/paper/arxiv-2602-02546","title":"D 2 Quant: Accurate Low-bit Post-Training Weight Quantization for LLMs","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"XIANGLONGYAN/D2Quant","path":"d2quant/quantization/quantizer.py","file_url":"https://github.com/XIANGLONGYAN/D2Quant/blob/HEAD/d2quant/quantization/quantizer.py","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"675da8641c602b03","mcp_get_code":{"code_sha256":"675da8641c602b03"}},{"arxiv_id":"2601.17124","paper":"/paper/arxiv-2601-17124","title":"iFSQ: Improving FSQ for Image Generation with 1 Line of Code","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Tencent-Hunyuan/iFSQ","path":"ifsq/src/model/modules/fsq.py","file_url":"https://github.com/Tencent-Hunyuan/iFSQ/blob/HEAD/ifsq/src/model/modules/fsq.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"47dd83e6ed9c70bc","mcp_get_code":{"code_sha256":"47dd83e6ed9c70bc"}},{"arxiv_id":"2501.13987","paper":"/paper/ostquant-refining-large-language-model","title":"OstQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting","date":"2025-01-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"brotherhappy/ostquant","path":"quant/quantizer.py","file_url":"https://github.com/brotherhappy/ostquant/blob/HEAD/quant/quantizer.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":"7f3de8a175cf4839","mcp_get_code":{"code_sha256":"7f3de8a175cf4839"}},{"arxiv_id":"2412.11549","paper":"/paper/mpq-dm-mixed-precision-quantization-for","title":"MPQ-DM: Mixed Precision Quantization for Extremely Low Bit Diffusion Models","date":"2024-12-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cantbebetter2/mpq-dm","path":"quant_scripts/quant_layer.py","file_url":"https://github.com/cantbebetter2/mpq-dm/blob/HEAD/quant_scripts/quant_layer.py","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"675da8641c602b03","mcp_get_code":{"code_sha256":"675da8641c602b03"}},{"arxiv_id":"2411.19842","paper":"/paper/scaling-transformers-for-low-bitrate-high","title":"Scaling Transformers for Low-Bitrate High-Quality Speech Coding","date":"2024-11-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Stability-AI/stable-codec","path":"stable_codec/fsq.py","file_url":"https://github.com/Stability-AI/stable-codec/blob/HEAD/stable_codec/fsq.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d939321c387018aa","mcp_get_code":{"code_sha256":"d939321c387018aa"}},{"arxiv_id":"2410.21759","paper":"/paper/intlora-integral-low-rank-adaptation-of","title":"IntLoRA: Integral Low-rank Adaptation of Quantized Diffusion Models","date":"2024-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"csguoh/intlora","path":"utils/intlora_shift.py","file_url":"https://github.com/csguoh/intlora/blob/HEAD/utils/intlora_shift.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d5bbfd113cf7fe02","mcp_get_code":{"code_sha256":"d5bbfd113cf7fe02"}},{"arxiv_id":"2405.16005","paper":"/paper/ptq4dit-post-training-quantization-for","title":"PTQ4DiT: Post-training Quantization for Diffusion Transformers","date":"2024-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"675da8641c602b03","mcp_get_code":{"code_sha256":"675da8641c602b03"}},{"arxiv_id":"2405.03144","paper":"/paper/ptq4sam-post-training-quantization-for","title":"PTQ4SAM: Post-Training Quantization for Segment Anything","date":"2024-05-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chengtao-lv/PTQ4SAM","path":"ptq4sam/quantization/util_quant.py","file_url":"https://github.com/chengtao-lv/PTQ4SAM/blob/HEAD/ptq4sam/quantization/util_quant.py","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"675da8641c602b03","mcp_get_code":{"code_sha256":"675da8641c602b03"}},{"arxiv_id":"2403.19140","paper":"/paper/qncd-quantization-noise-correction-for","title":"QNCD: Quantization Noise Correction for Diffusion Models","date":"2024-03-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"huanpengchu/qncd","path":"quant/quant_layer.py","file_url":"https://github.com/huanpengchu/qncd/blob/HEAD/quant/quant_layer.py","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"675da8641c602b03","mcp_get_code":{"code_sha256":"675da8641c602b03"}},{"arxiv_id":"2402.03666","paper":"/paper/quest-low-bit-diffusion-model-quantization","title":"QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuning","date":"2024-02-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hatchetProject/QuEST","path":"qdiff/quant_layer.py","file_url":"https://github.com/hatchetProject/QuEST/blob/HEAD/qdiff/quant_layer.py","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"675da8641c602b03","mcp_get_code":{"code_sha256":"675da8641c602b03"}},{"arxiv_id":"2311.06322","paper":"/paper/post-training-quantization-with-progressive","title":"Post-training Quantization for Text-to-Image Diffusion Models with Progressive Calibration and Activation Relaxing","date":"2023-11-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tsa18/PCR","path":"quantization_tools/quantization/loss.py","file_url":"https://github.com/tsa18/PCR/blob/HEAD/quantization_tools/quantization/loss.py","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"675da8641c602b03","mcp_get_code":{"code_sha256":"675da8641c602b03"}},{"arxiv_id":"2310.03270","paper":"/paper/efficientdm-efficient-quantization-aware-fine","title":"EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models","date":"2023-10-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ThisisBillhe/EfficientDM","path":"quant_scripts/quant_layer.py","file_url":"https://github.com/ThisisBillhe/EfficientDM/blob/HEAD/quant_scripts/quant_layer.py","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"675da8641c602b03","mcp_get_code":{"code_sha256":"675da8641c602b03"}},{"arxiv_id":"2309.15505","paper":"/paper/finite-scalar-quantization-vq-vae-made-simple","title":"Finite Scalar Quantization: VQ-VAE Made Simple","date":"2023-09-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Nikolai10/FSQ","path":"finite_scalar_quantization.py","file_url":"https://github.com/Nikolai10/FSQ/blob/HEAD/finite_scalar_quantization.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":"686267c77ebae16c","mcp_get_code":{"code_sha256":"686267c77ebae16c"}},{"arxiv_id":"2308.07650","paper":"/paper/eq-net-elastic-quantization-neural-networks","title":"EQ-Net: Elastic Quantization Neural Networks","date":"2023-08-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xuke225/EQ-Net","path":"module/base_lsq.py","file_url":"https://github.com/xuke225/EQ-Net/blob/HEAD/module/base_lsq.py","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"675da8641c602b03","mcp_get_code":{"code_sha256":"675da8641c602b03"}},{"arxiv_id":"2308.06744","paper":"/paper/token-scaled-logit-distillation-for-ternary-1","title":"Token-Scaled Logit Distillation for Ternary Weight Generative Language Models","date":"2023-08-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aiha-lab/TSLD","path":"utils/utils_quant.py","file_url":"https://github.com/aiha-lab/TSLD/blob/HEAD/utils/utils_quant.py","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"675da8641c602b03","mcp_get_code":{"code_sha256":"675da8641c602b03"}},{"arxiv_id":"2203.05740","paper":"/paper/qdrop-randomly-dropping-quantization-for-1","title":"QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization","date":"2022-03-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"modeltc/mqbench","path":"mqbench/fake_quantize/qdrop_quantizer.py","file_url":"https://github.com/modeltc/mqbench/blob/HEAD/mqbench/fake_quantize/qdrop_quantizer.py","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"675da8641c602b03","mcp_get_code":{"code_sha256":"675da8641c602b03"}},{"arxiv_id":"Zhang_AHCPTQ_Accurate_and_Hardware-Compatible_Post-Training_Quantization_for_Segment_Anything_Model_ICCV_2025_paper","paper":null,"title":"arXiv:Zhang_AHCPTQ_Accurate_and_Hardware-Compatible_Post-Training_Quantization_for_Segment_Anything_Model_ICCV_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Keio-CSG/AHCPTQ","path":"ahcptq/quantization/util_quant.py","file_url":"https://github.com/Keio-CSG/AHCPTQ/blob/HEAD/ahcptq/quantization/util_quant.py","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"675da8641c602b03","mcp_get_code":{"code_sha256":"675da8641c602b03"}},{"arxiv_id":"Liu_PD-Quant_Post-Training_Quantization_Based_on_Prediction_Difference_Metric_CVPR_2023_paper","paper":null,"title":"arXiv:Liu_PD-Quant_Post-Training_Quantization_Based_on_Prediction_Difference_Metric_CVPR_2023_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"hustvl/PD-Quant","path":"quant/quant_layer.py","file_url":"https://github.com/hustvl/PD-Quant/blob/HEAD/quant/quant_layer.py","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"675da8641c602b03","mcp_get_code":{"code_sha256":"675da8641c602b03"}}]}