{"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/perceiverattention","entry":"PerceiverAttention","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":5,"n_papers_ran":3,"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":5,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":3,"unverified":2},"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":"2505.15816","paper":"/paper/streamline-without-sacrifice-squeeze-out","title":"Streamline Without Sacrifice -- Squeeze out Computation Redundancy in LMM","date":"2025-05-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"penghao-wu/proxyv","path":"llava/model/multimodal_resampler/perceiver.py","file_url":"https://github.com/penghao-wu/proxyv/blob/HEAD/llava/model/multimodal_resampler/perceiver.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":"6a96fbd946c4017a","mcp_get_code":{"code_sha256":"6a96fbd946c4017a"}},{"arxiv_id":"2505.15755","paper":"/paper/exploring-the-visual-feature-space-for","title":"Exploring The Visual Feature Space for Multimodal Neural Decoding","date":"2025-05-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"weihaox/VINDEX","path":"src/model/model.py","file_url":"https://github.com/weihaox/VINDEX/blob/HEAD/src/model/model.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":"11192fbd2327ed4c","mcp_get_code":{"code_sha256":"11192fbd2327ed4c"}},{"arxiv_id":"2502.00791","paper":"/paper/vision-centric-token-compression-in-large","title":"Vision-centric Token Compression in Large Language Model","date":"2025-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CSU-JPG/VIST","path":"multimodal_model/model_architecture.py","file_url":"https://github.com/CSU-JPG/VIST/blob/HEAD/multimodal_model/model_architecture.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b1eb9481dae931d0","mcp_get_code":{"code_sha256":"b1eb9481dae931d0"}},{"arxiv_id":"2402.10805","paper":"/paper/generative-cross-modal-retrieval-memorizing","title":"Generative Cross-Modal Retrieval: Memorizing Images in Multimodal Language Models for Retrieval and Beyond","date":"2024-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liyongqi67/GRACE","path":"open_flamingo_deepspeed/open_flamingo/src/flamingo.py","file_url":"https://github.com/liyongqi67/GRACE/blob/HEAD/open_flamingo_deepspeed/open_flamingo/src/flamingo.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bda9925505979900","mcp_get_code":{"code_sha256":"bda9925505979900"}},{"arxiv_id":"2204.14198","paper":"/paper/flamingo-a-visual-language-model-for-few-shot-1","title":"Flamingo: a Visual Language Model for Few-Shot Learning","date":"2022-04-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mlfoundations/open_flamingo","path":"open_flamingo/src/flamingo.py","file_url":"https://github.com/mlfoundations/open_flamingo/blob/HEAD/open_flamingo/src/flamingo.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"65ec29626e592e07","mcp_get_code":{"code_sha256":"65ec29626e592e07"}}]}