{"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-peft-state-non-lora-maybe-zero-3","entry":"get_peft_state_non_lora_maybe_zero_3","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":24,"n_papers_ran":0,"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":4,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":24,"n_places_pointer_only":14,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":4},"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":"2605.20247","paper":"/paper/arxiv-2605-20247","title":"CP-MoE: Consistency-Preserving Mixture-of-Experts for Continual Learning","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"YangLiu-Lewis/CP-MoE","path":"llava/train/train_MOE.py","file_url":"https://github.com/YangLiu-Lewis/CP-MoE/blob/HEAD/llava/train/train_MOE.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1c53657305b66e9f","mcp_get_code":{"code_sha256":"1c53657305b66e9f"}},{"arxiv_id":"2605.18903","paper":"/paper/arxiv-2605-18903","title":"Reasoning Portability: Guiding Continual Learning for MLLMs in the RLVR Era","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"lluosi/RDB-CL","path":"ETrain/Train/Base_trainer.py","file_url":"https://github.com/lluosi/RDB-CL/blob/HEAD/ETrain/Train/Base_trainer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1c53657305b66e9f","mcp_get_code":{"code_sha256":"1c53657305b66e9f"}},{"arxiv_id":"2601.02443","paper":"/paper/arxiv-2601-02443","title":"Evaluating the Diagnostic Classification Ability of Multimodal Large Language Models: Insights from the Osteoarthritis Initiative","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"wanglihx/LLaVA-OA","path":"train_weighted.py","file_url":"https://github.com/wanglihx/LLaVA-OA/blob/HEAD/train_weighted.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1c53657305b66e9f","mcp_get_code":{"code_sha256":"1c53657305b66e9f"}},{"arxiv_id":"2510.17847","paper":"/paper/arxiv-2510-17847","title":"COIDO: Efficient Data Selection for Visual Instruction Tuning via Coupled Importance-Diversity Optimization","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"SuDIS-ZJU/CoIDO","path":"coido_scorer/stage1.py","file_url":"https://github.com/SuDIS-ZJU/CoIDO/blob/HEAD/coido_scorer/stage1.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"code_sha256_prefix":"3474fd37c97a48d0","mcp_get_code":{"code_sha256":"3474fd37c97a48d0"}},{"arxiv_id":"2503.11832","paper":"/paper/safety-mirage-how-spurious-correlations","title":"Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-tuning","date":"2025-03-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OPTML-Group/VLM-Safety-Unlearn","path":"llava/train/train_unlearn.py","file_url":"https://github.com/OPTML-Group/VLM-Safety-Unlearn/blob/HEAD/llava/train/train_unlearn.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1c53657305b66e9f","mcp_get_code":{"code_sha256":"1c53657305b66e9f"}},{"arxiv_id":"2503.00723","paper":"/paper/re-imagining-multimodal-instruction-tuning-a","title":"Re-Imagining Multimodal Instruction Tuning: A Representation View","date":"2025-03-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"1c53657305b66e9f","mcp_get_code":{"code_sha256":"1c53657305b66e9f"}},{"arxiv_id":"2501.09695","paper":"/paper/mitigating-hallucinations-in-large-vision-3","title":"Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key","date":"2025-01-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhyang2226/opa-dpo","path":"opadpo/opa_train.py","file_url":"https://github.com/zhyang2226/opa-dpo/blob/HEAD/opadpo/opa_train.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"1c53657305b66e9f","mcp_get_code":{"code_sha256":"1c53657305b66e9f"}},{"arxiv_id":"2410.22313","paper":"/paper/senna-bridging-large-vision-language-models","title":"Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving","date":"2024-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hustvl/senna","path":"llava/senna/train_senna_llava_laion_pretrain.py","file_url":"https://github.com/hustvl/senna/blob/HEAD/llava/senna/train_senna_llava_laion_pretrain.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":"1c53657305b66e9f","mcp_get_code":{"code_sha256":"1c53657305b66e9f"}},{"arxiv_id":"2410.16198","paper":"/paper/improve-vision-language-model-chain-of","title":"Improve Vision Language Model Chain-of-thought Reasoning","date":"2024-10-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"riflezhang/llava-hound-dpo","path":"llava_hound_dpo/dpo_scripts/run_dpo.py","file_url":"https://github.com/riflezhang/llava-hound-dpo/blob/HEAD/llava_hound_dpo/dpo_scripts/run_dpo.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1c53657305b66e9f","mcp_get_code":{"code_sha256":"1c53657305b66e9f"}},{"arxiv_id":"2410.13360","paper":"/paper/remember-retrieve-and-generate-understanding","title":"RAP: Retrieval-Augmented Personalization for Multimodal Large Language Models","date":"2024-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hoar012/rap-mllm","path":"llava/train/rap_train.py","file_url":"https://github.com/hoar012/rap-mllm/blob/HEAD/llava/train/rap_train.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1c53657305b66e9f","mcp_get_code":{"code_sha256":"1c53657305b66e9f"}},{"arxiv_id":"2410.05643","paper":"/paper/trace-temporal-grounding-video-llm-via-causal","title":"TRACE: Temporal Grounding Video LLM via Causal Event Modeling","date":"2024-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gyxxyg/trace","path":"trace/train_mt.py","file_url":"https://github.com/gyxxyg/trace/blob/HEAD/trace/train_mt.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":"1c53657305b66e9f","mcp_get_code":{"code_sha256":"1c53657305b66e9f"}},{"arxiv_id":"2408.11305","paper":"/paper/unifashion-a-unified-vision-language-model","title":"UniFashion: A Unified Vision-Language Model for Multimodal Fashion Retrieval and Generation","date":"2024-08-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xiangyu-mm/UniFashion","path":"src/blip_fine_tune_2.py","file_url":"https://github.com/xiangyu-mm/UniFashion/blob/HEAD/src/blip_fine_tune_2.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b6d749eb9a3b3158","mcp_get_code":{"code_sha256":"b6d749eb9a3b3158"}},{"arxiv_id":"2406.19973","paper":"/paper/stllava-med-self-training-large-language-and","title":"STLLaVA-Med: Self-Training Large Language and Vision Assistant for Medical Question-Answering","date":"2024-06-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"heliossun/stllava-med","path":"train_dpo.py","file_url":"https://github.com/heliossun/stllava-med/blob/HEAD/train_dpo.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1c53657305b66e9f","mcp_get_code":{"code_sha256":"1c53657305b66e9f"}},{"arxiv_id":"2406.11839","paper":"/paper/mdpo-conditional-preference-optimization-for","title":"mDPO: Conditional Preference Optimization for Multimodal Large Language Models","date":"2024-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"luka-group/mDPO","path":"bunny/run_mdpo_bunny.py","file_url":"https://github.com/luka-group/mDPO/blob/HEAD/bunny/run_mdpo_bunny.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1c53657305b66e9f","mcp_get_code":{"code_sha256":"1c53657305b66e9f"}},{"arxiv_id":"2406.11280","paper":"/paper/i-srt-aligning-large-multimodal-models-for","title":"ISR-DPO: Aligning Large Multimodal Models for Videos by Iterative Self-Retrospective DPO","date":"2024-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yonseivnl/vlm-rlaif","path":"RLAIF/finetune_policy_init.py","file_url":"https://github.com/yonseivnl/vlm-rlaif/blob/HEAD/RLAIF/finetune_policy_init.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":"1c53657305b66e9f","mcp_get_code":{"code_sha256":"1c53657305b66e9f"}},{"arxiv_id":"2406.06040","paper":"/paper/vript-a-video-is-worth-thousands-of-words","title":"Vript: A Video Is Worth Thousands of Words","date":"2024-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mutonix/Vript","path":"vriptor/train_hf.py","file_url":"https://github.com/mutonix/Vript/blob/HEAD/vriptor/train_hf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1c53657305b66e9f","mcp_get_code":{"code_sha256":"1c53657305b66e9f"}},{"arxiv_id":"2405.21075","paper":"/paper/video-mme-the-first-ever-comprehensive","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","date":"2024-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PhysGame/PhysGame","path":"train_dpo.py","file_url":"https://github.com/PhysGame/PhysGame/blob/HEAD/train_dpo.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":"1c53657305b66e9f","mcp_get_code":{"code_sha256":"1c53657305b66e9f"}},{"arxiv_id":"2405.16919","paper":"/paper/vocot-unleashing-visually-grounded-multi-step","title":"VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Models","date":"2024-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rupertluo/vocot","path":"train_volcano.py","file_url":"https://github.com/rupertluo/vocot/blob/HEAD/train_volcano.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"95fa5f303fe6207c","mcp_get_code":{"code_sha256":"95fa5f303fe6207c"}},{"arxiv_id":"2402.18695","paper":"/paper/grounding-language-models-for-visual-entity","title":"Grounding Language Models for Visual Entity Recognition","date":"2024-02-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mrzilinxiao/autover","path":"train_oven.py","file_url":"https://github.com/mrzilinxiao/autover/blob/HEAD/train_oven.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":"1c53657305b66e9f","mcp_get_code":{"code_sha256":"1c53657305b66e9f"}},{"arxiv_id":"2402.12501","paper":"/paper/your-vision-language-model-itself-is-a-strong","title":"Your Vision-Language Model Itself Is a Strong Filter: Towards High-Quality Instruction Tuning with Data Selection","date":"2024-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rayruibochen/self-filter","path":"self_filter/stage1.py","file_url":"https://github.com/rayruibochen/self-filter/blob/HEAD/self_filter/stage1.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"code_sha256_prefix":"1c53657305b66e9f","mcp_get_code":{"code_sha256":"1c53657305b66e9f"}},{"arxiv_id":"2401.02330","paper":"/paper/llava-ph-efficient-multi-modal-assistant-with","title":"LLaVA-Phi: Efficient Multi-Modal Assistant with Small Language Model","date":"2024-01-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhuyiche/llava-phi","path":"llava_phi/train/convert_model2base_llava_phi.py","file_url":"https://github.com/zhuyiche/llava-phi/blob/HEAD/llava_phi/train/convert_model2base_llava_phi.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1c53657305b66e9f","mcp_get_code":{"code_sha256":"1c53657305b66e9f"}},{"arxiv_id":"2312.02949","paper":"/paper/llava-grounding-grounded-visual-chat-with","title":"LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Models","date":"2023-12-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ux-decoder/llava-grounding","path":"llava/train/train_grounding_1st.py","file_url":"https://github.com/ux-decoder/llava-grounding/blob/HEAD/llava/train/train_grounding_1st.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":"1c53657305b66e9f","mcp_get_code":{"code_sha256":"1c53657305b66e9f"}},{"arxiv_id":"2310.01779","paper":"/paper/halle-switch-rethinking-and-controlling","title":"HallE-Control: Controlling Object Hallucination in Large Multimodal Models","date":"2023-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bronyayang/HallE_Switch","path":"llava/train/train_switch.py","file_url":"https://github.com/bronyayang/HallE_Switch/blob/HEAD/llava/train/train_switch.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1c53657305b66e9f","mcp_get_code":{"code_sha256":"1c53657305b66e9f"}},{"arxiv_id":"Wang_SMoLoRA_Exploring_and_Defying_Dual_Catastrophic_Forgetting_in_Continual_Visual_ICCV_2025_paper","paper":null,"title":"arXiv:Wang_SMoLoRA_Exploring_and_Defying_Dual_Catastrophic_Forgetting_in_Continual_Visual_ICCV_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Minato-Zackie/SMoLoRA","path":"llava/train/train_SMoLoRA.py","file_url":"https://github.com/Minato-Zackie/SMoLoRA/blob/HEAD/llava/train/train_SMoLoRA.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":"1c53657305b66e9f","mcp_get_code":{"code_sha256":"1c53657305b66e9f"}}]}