{"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-multimodal-rotary-pos-emb","entry":"apply_multimodal_rotary_pos_emb","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-25T09:33:49+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":12,"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":6,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":12,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":6},"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":"2603.00188","paper":"/paper/arxiv-2603-00188","title":"ST-Lite: Training-Free KV Cache Compression with Spatio-Trajectory Guidance for Long-Horizon GUI Agents","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"94wen94/ST-Lite","path":"eval/attention_helpers.py","file_url":"https://github.com/94wen94/ST-Lite/blob/HEAD/eval/attention_helpers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"43bbcae33bbf6761","mcp_get_code":{"code_sha256":"43bbcae33bbf6761"}},{"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":"1a7a4178e97668c1","mcp_get_code":{"code_sha256":"1a7a4178e97668c1"}},{"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":"eb4d16c3bba7cff8","mcp_get_code":{"code_sha256":"eb4d16c3bba7cff8"}},{"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_vl.py","file_url":"https://github.com/ANDgate99/Explore-Then-Select/blob/HEAD/model/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":"377d67df84bbd8e9","mcp_get_code":{"code_sha256":"377d67df84bbd8e9"}},{"arxiv_id":"2504.10462","paper":"/paper/the-scalability-of-simplicity-empirical","title":"The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer","date":"2025-04-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bytedance/sail","path":"modeling_sail.py","file_url":"https://github.com/bytedance/sail/blob/HEAD/modeling_sail.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":"2c5971642e5ce12f","mcp_get_code":{"code_sha256":"2c5971642e5ce12f"}},{"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":"eb4d16c3bba7cff8","mcp_get_code":{"code_sha256":"eb4d16c3bba7cff8"}},{"arxiv_id":"2503.12559","paper":"/paper/adaretake-adaptive-redundancy-reduction-to","title":"AdaReTaKe: Adaptive Redundancy Reduction to Perceive Longer for Video-language Understanding","date":"2025-03-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sczwangxiao/video-flexreduc","path":"retake/longvideo_cache.py","file_url":"https://github.com/sczwangxiao/video-flexreduc/blob/HEAD/retake/longvideo_cache.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8971bec8b941516b","mcp_get_code":{"code_sha256":"8971bec8b941516b"}},{"arxiv_id":"2502.05173","paper":"/paper/videorope-what-makes-for-good-video-rotary","title":"VideoRoPE: What Makes for Good Video Rotary Position Embedding?","date":"2025-02-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wiselnn570/videorope","path":"videorope-transformer/modeling_videorope.py","file_url":"https://github.com/wiselnn570/videorope/blob/HEAD/videorope-transformer/modeling_videorope.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":"eb4d16c3bba7cff8","mcp_get_code":{"code_sha256":"eb4d16c3bba7cff8"}},{"arxiv_id":"2412.20504","paper":"/paper/retake-reducing-temporal-and-knowledge","title":"ReTaKe: Reducing Temporal and Knowledge Redundancy for Long Video Understanding","date":"2024-12-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sczwangxiao/video-retake","path":"retake/longvideo_cache.py","file_url":"https://github.com/sczwangxiao/video-retake/blob/HEAD/retake/longvideo_cache.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8971bec8b941516b","mcp_get_code":{"code_sha256":"8971bec8b941516b"}},{"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":"eb4d16c3bba7cff8","mcp_get_code":{"code_sha256":"eb4d16c3bba7cff8"}},{"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":"eb4d16c3bba7cff8","mcp_get_code":{"code_sha256":"eb4d16c3bba7cff8"}},{"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":"eb4d16c3bba7cff8","mcp_get_code":{"code_sha256":"eb4d16c3bba7cff8"}}]}