{"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":"/paper/making-llama-see-and-draw-with-seed-tokenizer","title":"Making LLaMA SEE and Draw with SEED Tokenizer","arxiv_id":"2310.01218","date":"2023-10-02","proceeding":null,"authors":["Yuying Ge","Sijie Zhao","Ziyun Zeng","Yixiao Ge","Chen Li","Xintao Wang","Ying Shan"],"abstract":"The great success of Large Language Models (LLMs) has expanded the potential of multimodality, contributing to the gradual evolution of General Artificial Intelligence (AGI). A true AGI agent should not only possess the capability to perform predefined multi-tasks but also exhibit emergent abilities in an open-world context. However, despite the considerable advancements made by recent multimodal LLMs, they still fall short in effectively unifying comprehension and generation tasks, let alone open-world emergent abilities. We contend that the key to overcoming the present impasse lies in enabling text and images to be represented and processed interchangeably within a unified autoregressive Transformer. To this end, we introduce SEED, an elaborate image tokenizer that empowers LLMs with the ability to SEE and Draw at the same time. We identify two crucial design principles: (1) Image tokens should be independent of 2D physical patch positions and instead be produced with a 1D causal dependency, exhibiting intrinsic interdependence that aligns with the left-to-right autoregressive prediction mechanism in LLMs. (2) Image tokens should capture high-level semantics consistent with the degree of semantic abstraction in words, and be optimized for both discriminativeness and reconstruction during the tokenizer training phase. With SEED tokens, LLM is able to perform scalable multimodal autoregression under its original training recipe, i.e., next-word prediction. SEED-LLaMA is therefore produced by large-scale pretraining and instruction tuning on the interleaved textual and visual data, demonstrating impressive performance on a broad range of multimodal comprehension and generation tasks. More importantly, SEED-LLaMA has exhibited compositional emergent abilities such as multi-turn in-context multimodal generation, acting like your AI assistant.","url_abs":"https://arxiv.org/abs/2310.01218v1","url_pdf":"https://arxiv.org/pdf/2310.01218v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"making-llama-see-and-draw-with-seed-tokenizer","repo_url":"https://github.com/ailab-cvc/seed","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"multimodal-generation","task_name":"multimodal generation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2310.01218","atlas_url":"https://app.syntology.ai/?focus=2310.01218","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.01218"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ailab-cvc/seed","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":4,"ran_violates":2,"ran_draft_wrong":2,"unverified":3},"by_repo_kind":{"official":{"samples":11,"ran":8,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":11,"samples":[{"code_sha256_prefix":"bd6de531c5313312","entry":"decode_image","repo":"ailab-cvc/seed","repo_kind":"official","path":"gradio_demo/seed_llama_flask.py","file_url":"https://github.com/ailab-cvc/seed/blob/HEAD/gradio_demo/seed_llama_flask.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"bd6de531c5313312"}},{"code_sha256_prefix":"4cb732f513d69dfd","entry":"disabled_train","repo":"ailab-cvc/seed","repo_kind":"official","path":"models/seed_qformer/blip2.py","file_url":"https://github.com/ailab-cvc/seed/blob/HEAD/models/seed_qformer/blip2.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4cb732f513d69dfd"}},{"code_sha256_prefix":"65dbe48364c80cba","entry":"encode_image","repo":"ailab-cvc/seed","repo_kind":"official","path":"gradio_demo/seed_llama_flask.py","file_url":"https://github.com/ailab-cvc/seed/blob/HEAD/gradio_demo/seed_llama_flask.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"65dbe48364c80cba"}},{"code_sha256_prefix":"d25aa46a7e2f707f","entry":"encode_image","repo":"ailab-cvc/seed","repo_kind":"official","path":"gradio_demo/seed_llama_gradio.py","file_url":"https://github.com/ailab-cvc/seed/blob/HEAD/gradio_demo/seed_llama_gradio.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"d25aa46a7e2f707f"}},{"code_sha256_prefix":"c1307f2aca21ab37","entry":"get_image_name","repo":"ailab-cvc/seed","repo_kind":"official","path":"gradio_demo/seed_llama_gradio.py","file_url":"https://github.com/ailab-cvc/seed/blob/HEAD/gradio_demo/seed_llama_gradio.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"c1307f2aca21ab37"}},{"code_sha256_prefix":"c6ec173f19f5c34d","entry":"interpolate_pos_embed","repo":"ailab-cvc/seed","repo_kind":"official","path":"models/seed_qformer/vit.py","file_url":"https://github.com/ailab-cvc/seed/blob/HEAD/models/seed_qformer/vit.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c6ec173f19f5c34d"}},{"code_sha256_prefix":"4d1d9c47619920ba","entry":"is_url","repo":"ailab-cvc/seed","repo_kind":"official","path":"models/seed_qformer/utils.py","file_url":"https://github.com/ailab-cvc/seed/blob/HEAD/models/seed_qformer/utils.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4d1d9c47619920ba"}},{"code_sha256_prefix":"98589643273920ba","entry":"main_process","repo":"ailab-cvc/seed","repo_kind":"official","path":"models/seed_qformer/utils.py","file_url":"https://github.com/ailab-cvc/seed/blob/HEAD/models/seed_qformer/utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"98589643273920ba"}},{"code_sha256_prefix":"41fbc8a2fbffad5a","entry":"create_clip_vit_L","repo":"ailab-cvc/seed","repo_kind":"official","path":"models/seed_qformer/clip_vit.py","file_url":"https://github.com/ailab-cvc/seed/blob/HEAD/models/seed_qformer/clip_vit.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"41fbc8a2fbffad5a"}},{"code_sha256_prefix":"cd33fb877f45ca78","entry":"create_eva_vit_g","repo":"ailab-cvc/seed","repo_kind":"official","path":"models/seed_qformer/eva_vit.py","file_url":"https://github.com/ailab-cvc/seed/blob/HEAD/models/seed_qformer/eva_vit.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"cd33fb877f45ca78"}},{"code_sha256_prefix":"643539116e049080","entry":"download_cached_file","repo":"ailab-cvc/seed","repo_kind":"official","path":"models/seed_qformer/utils.py","file_url":"https://github.com/ailab-cvc/seed/blob/HEAD/models/seed_qformer/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"643539116e049080"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}