{"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/apply-rotary-pos-emb-vision","entry":"apply_rotary_pos_emb_vision","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":20,"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":7,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":20,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":7},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2607.21595","paper":"/paper/arxiv-2607-21595","title":"3D-Aware VLMs with Implicit and Explicit Geometries","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"Vegetebird/VLM-IE3D","path":"common/utils.py","file_url":"https://github.com/Vegetebird/VLM-IE3D/blob/HEAD/common/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ffa41b4771980f66","mcp_get_code":{"code_sha256":"ffa41b4771980f66"}},{"arxiv_id":"2606.16158","paper":"/paper/arxiv-2606-16158","title":"Focus When Necessary: Adaptive Routing and Collaborative Grounding for Training-Free Visual Grounding","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"TencentBAC/LazyMCoT","path":"Qwen2.5/modeling_qwen2_5_vl_re_infer.py","file_url":"https://github.com/TencentBAC/LazyMCoT/blob/HEAD/Qwen2.5/modeling_qwen2_5_vl_re_infer.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":"049747a79920f0f7","mcp_get_code":{"code_sha256":"049747a79920f0f7"}},{"arxiv_id":"2606.15880","paper":"/paper/arxiv-2606-15880","title":"Deep Residual Injection for Full-Spectrum Forensic Signal Perception in Multimodal Large Language Models","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"KQL11/Deep-VRM","path":"Models/DeepVRM/modeling_qwen2_5_vl.py","file_url":"https://github.com/KQL11/Deep-VRM/blob/HEAD/Models/DeepVRM/modeling_qwen2_5_vl.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":"049747a79920f0f7","mcp_get_code":{"code_sha256":"049747a79920f0f7"}},{"arxiv_id":"2602.22278","paper":"/paper/arxiv-2602-22278","title":"RETLLM: Training and Data-Free MLLMs for Multimodal Information Retrieval","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"alivecat05/RETLLM","path":"modeling_qwen2_5_vl.py","file_url":"https://github.com/alivecat05/RETLLM/blob/HEAD/modeling_qwen2_5_vl.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":"09445ca10af72017","mcp_get_code":{"code_sha256":"09445ca10af72017"}},{"arxiv_id":"2602.01173","paper":"/paper/arxiv-2602-01173","title":"EEmo-Logic: A Unified Dataset and Multi-Stage Framework for Comprehensive Image-Evoked Emotion Assessment","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"workerred/EEmo-Logic","path":"train/Stage_2/modeling_qwen2_5_vl.py","file_url":"https://github.com/workerred/EEmo-Logic/blob/HEAD/train/Stage_2/modeling_qwen2_5_vl.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"09445ca10af72017","mcp_get_code":{"code_sha256":"09445ca10af72017"}},{"arxiv_id":"2509.15235","paper":"/paper/arxiv-2509-15235","title":"ViSpec: Accelerating Vision-Language Models with Vision-Aware Speculative Decoding","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"KangJialiang/ViSpec","path":"vispec/model/modeling_qwen2_5_vl_kv.py","file_url":"https://github.com/KangJialiang/ViSpec/blob/HEAD/vispec/model/modeling_qwen2_5_vl_kv.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":"50a09accb6ca2549","mcp_get_code":{"code_sha256":"50a09accb6ca2549"}},{"arxiv_id":"2509.01986","paper":"/paper/arxiv-2509-01986","title":"Draw-In-Mind: Rebalancing Designer-Painter Roles in Unified Multimodal Models Benefits Image Editing","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"showlab/DIM","path":"models/modeling_qwen2_5_vl.py","file_url":"https://github.com/showlab/DIM/blob/HEAD/models/modeling_qwen2_5_vl.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"09445ca10af72017","mcp_get_code":{"code_sha256":"09445ca10af72017"}},{"arxiv_id":"2506.15220","paper":"/paper/video-salmonn-2-captioning-enhanced-audio","title":"video-SALMONN 2: Captioning-Enhanced Audio-Visual Large Language Models","date":"2025-06-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bytedance/video-salmonn-2","path":"video_SALMONN2_pro/qwenvl/model/modeling_qwen3_vl.py","file_url":"https://github.com/bytedance/video-salmonn-2/blob/HEAD/video_SALMONN2_pro/qwenvl/model/modeling_qwen3_vl.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":"049747a79920f0f7","mcp_get_code":{"code_sha256":"049747a79920f0f7"}},{"arxiv_id":"2506.04779","paper":"/paper/mmsu-a-massive-multi-task-spoken-language","title":"MMSU: A Massive Multi-task Spoken Language Understanding and Reasoning Benchmark","date":"2025-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"QwenLM/Qwen2.5-Omni","path":"low-VRAM-mode/modeling_qwen2_5_omni_low_VRAM_mode.py","file_url":"https://github.com/QwenLM/Qwen2.5-Omni/blob/HEAD/low-VRAM-mode/modeling_qwen2_5_omni_low_VRAM_mode.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"c4adc11c6d565fb8","mcp_get_code":{"code_sha256":"c4adc11c6d565fb8"}},{"arxiv_id":"2505.21906","paper":"/paper/vision-language-action-model-with-open-world","title":"ChatVLA-2: Vision-Language-Action Model with Open-World Embodied Reasoning from Pretrained Knowledge","date":"2025-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tutujingyugang1/ChatVLA_public","path":"qwen2_vla/models/modeling_qwen2_vla.py","file_url":"https://github.com/tutujingyugang1/ChatVLA_public/blob/HEAD/qwen2_vla/models/modeling_qwen2_vla.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"48f12d3a9c4a15e8","mcp_get_code":{"code_sha256":"48f12d3a9c4a15e8"}},{"arxiv_id":"2504.21403","paper":null,"title":"arXiv:2504.21403","date":null,"month_inferred_from_arxiv_id":"2025-04","title_source":null,"repo":"ANDgate99/Explore-Then-Select","path":"model/modeling_qwen2_5_vl.py","file_url":"https://github.com/ANDgate99/Explore-Then-Select/blob/HEAD/model/modeling_qwen2_5_vl.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"50a09accb6ca2549","mcp_get_code":{"code_sha256":"50a09accb6ca2549"}},{"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-v1.1","path":"vargpt_qwen_v1_1/modeling_vargpt_qwen2_vl.py","file_url":"https://github.com/vargpt-family/vargpt-v1.1/blob/HEAD/vargpt_qwen_v1_1/modeling_vargpt_qwen2_vl.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":"48f12d3a9c4a15e8","mcp_get_code":{"code_sha256":"48f12d3a9c4a15e8"}},{"arxiv_id":"2503.11187","paper":"/paper/fastvid-dynamic-density-pruning-for-fast","title":"FastVID: Dynamic Density Pruning for Fast Video Large Language Models","date":"2025-03-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lunarshen/fastvid","path":"fastvid_qwen25vl/lmms-eval/lmms_eval/models/qwenvlutils/modeling_qwen2_5_vl.py","file_url":"https://github.com/lunarshen/fastvid/blob/HEAD/fastvid_qwen25vl/lmms-eval/lmms_eval/models/qwenvlutils/modeling_qwen2_5_vl.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"09445ca10af72017","mcp_get_code":{"code_sha256":"09445ca10af72017"}},{"arxiv_id":"2502.11494","paper":"/paper/stop-looking-for-important-tokens-in","title":"Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More","date":"2025-02-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zichenwen1/dart","path":"Qwen2_5-VL/Qwen2_5VL_DART/modeling_qwen2_5_vl_self.py","file_url":"https://github.com/zichenwen1/dart/blob/HEAD/Qwen2_5-VL/Qwen2_5VL_DART/modeling_qwen2_5_vl_self.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":"049747a79920f0f7","mcp_get_code":{"code_sha256":"049747a79920f0f7"}},{"arxiv_id":"2501.13106","paper":"/paper/videollama-3-frontier-multimodal-foundation","title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","date":"2025-01-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"damo-nlp-sg/videollama3","path":"inference/transformers_api/modeling_videollama3_encoder.py","file_url":"https://github.com/damo-nlp-sg/videollama3/blob/HEAD/inference/transformers_api/modeling_videollama3_encoder.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":"48f12d3a9c4a15e8","mcp_get_code":{"code_sha256":"48f12d3a9c4a15e8"}},{"arxiv_id":"2412.04467","paper":"/paper/visionzip-longer-is-better-but-not-necessary","title":"VisionZip: Longer is Better but Not Necessary in Vision Language Models","date":"2024-12-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dvlab-research/visionzip","path":"Qwen2_5_VL/qwen2_5vl_visionzip.py","file_url":"https://github.com/dvlab-research/visionzip/blob/HEAD/Qwen2_5_VL/qwen2_5vl_visionzip.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":"50a09accb6ca2549","mcp_get_code":{"code_sha256":"50a09accb6ca2549"}},{"arxiv_id":"2411.17465","paper":"/paper/showui-one-vision-language-action-model-for","title":"ShowUI: One Vision-Language-Action Model for GUI Visual Agent","date":"2024-11-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"showlab/showui","path":"model/showui/modeling_showui.py","file_url":"https://github.com/showlab/showui/blob/HEAD/model/showui/modeling_showui.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":"48f12d3a9c4a15e8","mcp_get_code":{"code_sha256":"48f12d3a9c4a15e8"}},{"arxiv_id":"2410.06169","paper":"/paper/quadratic-is-not-what-you-need-for-multimodal","title":"Treat Visual Tokens as Text? But Your MLLM Only Needs Fewer Efforts to See","date":"2024-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZhangAIPI/YOPO_MLLM_Pruning","path":"modeling_qwen2_vl.py","file_url":"https://github.com/ZhangAIPI/YOPO_MLLM_Pruning/blob/HEAD/modeling_qwen2_vl.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"48f12d3a9c4a15e8","mcp_get_code":{"code_sha256":"48f12d3a9c4a15e8"}},{"arxiv_id":"2407.17331","paper":"/paper/multi-label-cluster-discrimination-for-visual","title":"Multi-label Cluster Discrimination for Visual Representation Learning","date":"2024-07-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"deepglint/unicom","path":"mlcd/vit_rope2d_hf.py","file_url":"https://github.com/deepglint/unicom/blob/HEAD/mlcd/vit_rope2d_hf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9cbc76fa9f2e80cb","mcp_get_code":{"code_sha256":"9cbc76fa9f2e80cb"}},{"arxiv_id":"Lin_ShowUI_One_Vision-Language-Action_Model_for_GUI_Visual_Agent_CVPR_2025_paper","paper":null,"title":"arXiv:Lin_ShowUI_One_Vision-Language-Action_Model_for_GUI_Visual_Agent_CVPR_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"showlab/ShowUI","path":"model/showui/modeling_showui.py","file_url":"https://github.com/showlab/ShowUI/blob/HEAD/model/showui/modeling_showui.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":"48f12d3a9c4a15e8","mcp_get_code":{"code_sha256":"48f12d3a9c4a15e8"}}]}