{"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/x-llm-bootstrapping-advanced-large-language","title":"X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages","arxiv_id":"2305.04160","date":"2023-05-07","proceeding":null,"authors":["Feilong Chen","Minglun Han","Haozhi Zhao","Qingyang Zhang","Jing Shi","Shuang Xu","Bo Xu"],"abstract":"Large language models (LLMs) have demonstrated remarkable language abilities. GPT-4, based on advanced LLMs, exhibits extraordinary multimodal capabilities beyond previous visual language models. We attribute this to the use of more advanced LLMs compared with previous multimodal models. Unfortunately, the model architecture and training strategies of GPT-4 are unknown. To endow LLMs with multimodal capabilities, we propose X-LLM, which converts Multi-modalities (images, speech, videos) into foreign languages using X2L interfaces and inputs them into a large Language model (ChatGLM). Specifically, X-LLM aligns multiple frozen single-modal encoders and a frozen LLM using X2L interfaces, where ``X'' denotes multi-modalities such as image, speech, and videos, and ``L'' denotes languages. X-LLM's training consists of three stages: (1) Converting Multimodal Information: The first stage trains each X2L interface to align with its respective single-modal encoder separately to convert multimodal information into languages. (2) Aligning X2L representations with the LLM: single-modal encoders are aligned with the LLM through X2L interfaces independently. (3) Integrating multiple modalities: all single-modal encoders are aligned with the LLM through X2L interfaces to integrate multimodal capabilities into the LLM. Our experiments show that X-LLM demonstrates impressive multimodel chat abilities, sometimes exhibiting the behaviors of multimodal GPT-4 on unseen images/instructions, and yields a 84.5\\% relative score compared with GPT-4 on a synthetic multimodal instruction-following dataset. And we also conduct quantitative tests on using LLM for ASR and multimodal ASR, hoping to promote the era of LLM-based speech recognition.","url_abs":"https://arxiv.org/abs/2305.04160v3","url_pdf":"https://arxiv.org/pdf/2305.04160v3.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":"x-llm-bootstrapping-advanced-large-language","repo_url":"https://github.com/0nutation/speechgpt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"x-llm-bootstrapping-advanced-large-language","repo_url":"https://github.com/phellonchen/x-llm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"instruction-following","task_name":"Instruction Following"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"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":"gpt-4","method_name":"GPT-4"},{"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":{"atlas_url":"https://app.syntology.ai/?focus=2305.04160","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.04160"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/0nutation/speechgpt","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/phellonchen/x-llm","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_fixture":1,"ran":4,"unverified":6},"by_repo_kind":{"listed":{"samples":11,"ran":5,"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":0,"samples":[{"code_sha256_prefix":"7d214655954e2bc6","entry":"getAttMap","repo":"phellonchen/x-llm","repo_kind":"listed","path":"xllm/common/gradcam.py","file_url":"https://github.com/phellonchen/x-llm/blob/HEAD/xllm/common/gradcam.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7d214655954e2bc6"}},{"code_sha256_prefix":"98589643273920ba","entry":"main_process","repo":"phellonchen/x-llm","repo_kind":"listed","path":"xllm/common/dist_utils.py","file_url":"https://github.com/phellonchen/x-llm/blob/HEAD/xllm/common/dist_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"98589643273920ba"}},{"code_sha256_prefix":"791c72070c0b1cfb","entry":"node_to_dict","repo":"phellonchen/x-llm","repo_kind":"listed","path":"xllm/common/config.py","file_url":"https://github.com/phellonchen/x-llm/blob/HEAD/xllm/common/config.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"791c72070c0b1cfb"}},{"code_sha256_prefix":"e4f5893b210b11f6","entry":"preprocess","repo":"phellonchen/x-llm","repo_kind":"listed","path":"demo/demo_xllm.py","file_url":"https://github.com/phellonchen/x-llm/blob/HEAD/demo/demo_xllm.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e4f5893b210b11f6"}},{"code_sha256_prefix":"cb33571427334815","entry":"tile","repo":"phellonchen/x-llm","repo_kind":"listed","path":"xllm/models/base_model.py","file_url":"https://github.com/phellonchen/x-llm/blob/HEAD/xllm/models/base_model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cb33571427334815"}},{"code_sha256_prefix":"0ec9fc2025c16f65","entry":"all_gather_with_grad","repo":"phellonchen/x-llm","repo_kind":"listed","path":"xllm/models/base_model.py","file_url":"https://github.com/phellonchen/x-llm/blob/HEAD/xllm/models/base_model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0ec9fc2025c16f65"}},{"code_sha256_prefix":"643539116e049080","entry":"download_cached_file","repo":"phellonchen/x-llm","repo_kind":"listed","path":"xllm/common/dist_utils.py","file_url":"https://github.com/phellonchen/x-llm/blob/HEAD/xllm/common/dist_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"643539116e049080"}},{"code_sha256_prefix":"77bc132c086b42cc","entry":"get_ASRFeature","repo":"phellonchen/x-llm","repo_kind":"listed","path":"gen_feats_from_service.py","file_url":"https://github.com/phellonchen/x-llm/blob/HEAD/gen_feats_from_service.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"77bc132c086b42cc"}},{"code_sha256_prefix":"35b50be2baee87cc","entry":"get_image_state_dict","repo":"phellonchen/x-llm","repo_kind":"listed","path":"xllm/checkpoints/process_checkpoint.py","file_url":"https://github.com/phellonchen/x-llm/blob/HEAD/xllm/checkpoints/process_checkpoint.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"35b50be2baee87cc"}},{"code_sha256_prefix":"d32aa22cf716217d","entry":"get_speech_state_dict","repo":"phellonchen/x-llm","repo_kind":"listed","path":"xllm/checkpoints/process_checkpoint.py","file_url":"https://github.com/phellonchen/x-llm/blob/HEAD/xllm/checkpoints/process_checkpoint.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d32aa22cf716217d"}},{"code_sha256_prefix":"6e1df60743a4db00","entry":"get_state_dict","repo":"phellonchen/x-llm","repo_kind":"listed","path":"xllm/checkpoints/process_checkpoint.py","file_url":"https://github.com/phellonchen/x-llm/blob/HEAD/xllm/checkpoints/process_checkpoint.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6e1df60743a4db00"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}