{"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/deepresonance-enhancing-multimodal-music","title":"DeepResonance: Enhancing Multimodal Music Understanding via Music-centric Multi-way Instruction Tuning","arxiv_id":"2502.12623","date":"2025-02-18","proceeding":null,"authors":["Zhuoyuan Mao","Mengjie Zhao","Qiyu Wu","Hiromi Wakaki","Yuki Mitsufuji"],"abstract":"Recent advancements in music large language models (LLMs) have significantly improved music understanding tasks, which involve the model's ability to analyze and interpret various musical elements. These improvements primarily focused on integrating both music and text inputs. However, the potential of incorporating additional modalities such as images, videos and textual music features to enhance music understanding remains unexplored. To bridge this gap, we propose DeepResonance, a multimodal music understanding LLM fine-tuned via multi-way instruction tuning with multi-way aligned music, text, image, and video data. To this end, we construct Music4way-MI2T, Music4way-MV2T, and Music4way-Any2T, three 4-way training and evaluation datasets designed to enable DeepResonance to integrate both visual and textual music feature content. We also introduce multi-sampled ImageBind embeddings and a pre-LLM fusion Transformer to enhance modality fusion prior to input into text LLMs, tailoring DeepResonance for multi-way instruction tuning. Our model achieves state-of-the-art performances across six music understanding tasks, highlighting the benefits of the auxiliary modalities and the structural superiority of DeepResonance. We plan to open-source the models and the newly constructed datasets.","url_abs":"https://arxiv.org/abs/2502.12623v2","url_pdf":"https://arxiv.org/pdf/2502.12623v2.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":[],"tasks":[],"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/2502.12623","atlas_url":"https://app.syntology.ai/?focus=2502.12623","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.12623"}},"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":"deterministic:regex_extraction","url":"https://github.com/sony/DeepResonance","reach":null}],"summary":{"ran":4,"ran_draft_wrong":1,"ran_fixture":2,"unverified":5},"by_repo_kind":{"found_in_text":{"samples":12,"ran":7,"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":"4105ecc8df8a8154","entry":"LlamaMLP","repo":"sony/DeepResonance","repo_kind":"found_in_text","path":"code/model/deepresonance.py","file_url":"https://github.com/sony/DeepResonance/blob/HEAD/code/model/deepresonance.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4105ecc8df8a8154"}},{"code_sha256_prefix":"ef0f3d688eac1213","entry":"LlamaRMSNorm","repo":"sony/DeepResonance","repo_kind":"found_in_text","path":"code/model/deepresonance.py","file_url":"https://github.com/sony/DeepResonance/blob/HEAD/code/model/deepresonance.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ef0f3d688eac1213"}},{"code_sha256_prefix":"5f256ecadc2081af","entry":"LlamaRotaryEmbedding","repo":"sony/DeepResonance","repo_kind":"found_in_text","path":"code/model/deepresonance.py","file_url":"https://github.com/sony/DeepResonance/blob/HEAD/code/model/deepresonance.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5f256ecadc2081af"}},{"code_sha256_prefix":"4cdc48d738bd28c0","entry":"StoppingCriteriaSub","repo":"sony/DeepResonance","repo_kind":"found_in_text","path":"code/model/deepresonance.py","file_url":"https://github.com/sony/DeepResonance/blob/HEAD/code/model/deepresonance.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4cdc48d738bd28c0"}},{"code_sha256_prefix":"61ecf291f8900bce","entry":"_expand_mask","repo":"sony/DeepResonance","repo_kind":"found_in_text","path":"code/model/deepresonance.py","file_url":"https://github.com/sony/DeepResonance/blob/HEAD/code/model/deepresonance.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"61ecf291f8900bce"}},{"code_sha256_prefix":"c5c590da5a7c2a3f","entry":"_make_causal_mask","repo":"sony/DeepResonance","repo_kind":"found_in_text","path":"code/model/deepresonance.py","file_url":"https://github.com/sony/DeepResonance/blob/HEAD/code/model/deepresonance.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c5c590da5a7c2a3f"}},{"code_sha256_prefix":"dffca8afadd5d56c","entry":"apply_rotary_pos_emb","repo":"sony/DeepResonance","repo_kind":"found_in_text","path":"code/model/deepresonance.py","file_url":"https://github.com/sony/DeepResonance/blob/HEAD/code/model/deepresonance.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dffca8afadd5d56c"}},{"code_sha256_prefix":"2dd71742c7d0c8e5","entry":"DeepResonanceModel","repo":"sony/DeepResonance","repo_kind":"found_in_text","path":"code/model/deepresonance.py","file_url":"https://github.com/sony/DeepResonance/blob/HEAD/code/model/deepresonance.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2dd71742c7d0c8e5"}},{"code_sha256_prefix":"586f7e54af865636","entry":"LlamaAttention","repo":"sony/DeepResonance","repo_kind":"found_in_text","path":"code/model/deepresonance.py","file_url":"https://github.com/sony/DeepResonance/blob/HEAD/code/model/deepresonance.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"586f7e54af865636"}},{"code_sha256_prefix":"40826a087f0fbbed","entry":"LlamaDecoderLayer","repo":"sony/DeepResonance","repo_kind":"found_in_text","path":"code/model/deepresonance.py","file_url":"https://github.com/sony/DeepResonance/blob/HEAD/code/model/deepresonance.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"40826a087f0fbbed"}},{"code_sha256_prefix":"b386ff5ca1779cbf","entry":"LlamaForCausalLM","repo":"sony/DeepResonance","repo_kind":"found_in_text","path":"code/model/deepresonance.py","file_url":"https://github.com/sony/DeepResonance/blob/HEAD/code/model/deepresonance.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b386ff5ca1779cbf"}},{"code_sha256_prefix":"5c2dbf28bfa2c492","entry":"LlamaModel","repo":"sony/DeepResonance","repo_kind":"found_in_text","path":"code/model/deepresonance.py","file_url":"https://github.com/sony/DeepResonance/blob/HEAD/code/model/deepresonance.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5c2dbf28bfa2c492"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}