{"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/desta2-5-audio-toward-general-purpose-large","title":"DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment","arxiv_id":"2507.02768","date":"2025-07-03","proceeding":null,"authors":["Ke-Han Lu","Zhehuai Chen","Szu-Wei Fu","Chao-Han Huck Yang","Sung-Feng Huang","Chih-Kai Yang","Chee-En Yu","Chun-Wei Chen","Wei-Chih Chen","Chien-yu Huang","Yi-Cheng Lin","Yu-Xiang Lin","Chi-An Fu","Chun-Yi Kuan","Wenze Ren","Xuanjun Chen","Wei-Ping Huang","En-Pei Hu","Tzu-Quan Lin","Yuan-Kuei Wu","Kuan-Po Huang","Hsiao-Ying Huang","Huang-Cheng Chou","Kai-Wei Chang","Cheng-Han Chiang","Boris Ginsburg","Yu-Chiang Frank Wang","Hung-Yi Lee"],"abstract":"We introduce DeSTA2.5-Audio, a general-purpose Large Audio Language Model (LALM) designed for robust auditory perception and instruction-following, without requiring task-specific audio instruction-tuning. Recent LALMs typically augment Large Language Models (LLMs) with auditory capabilities by training on large-scale, manually curated or LLM-synthesized audio-instruction datasets. However, these approaches have often suffered from the catastrophic forgetting of the LLM's original language abilities. To address this, we revisit the data construction pipeline and propose DeSTA, a self-generated cross-modal alignment strategy in which the backbone LLM generates its own training targets. This approach preserves the LLM's native language proficiency while establishing effective audio-text alignment, thereby enabling zero-shot generalization without task-specific tuning. Using DeSTA, we construct DeSTA-AQA5M, a large-scale, task-agnostic dataset containing 5 million training samples derived from 7,000 hours of audio spanning 50 diverse datasets, including speech, environmental sounds, and music. DeSTA2.5-Audio achieves state-of-the-art or competitive performance across a wide range of audio-language benchmarks, including Dynamic-SUPERB, MMAU, SAKURA, Speech-IFEval, and VoiceBench. Comprehensive comparative studies demonstrate that our self-generated strategy outperforms widely adopted data construction and training strategies in both auditory perception and instruction-following capabilities. Our findings underscore the importance of carefully designed data construction in LALM development and offer practical insights for building robust, general-purpose LALMs.","url_abs":"https://arxiv.org/abs/2507.02768v1","url_pdf":"https://arxiv.org/pdf/2507.02768v1.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":"desta2-5-audio-toward-general-purpose-large","repo_url":"https://github.com/kehanlu/desta2.5-audio","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"desta2-5-audio-toward-general-purpose-large","repo_url":"https://github.com/kehanlu/DeSTA2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"instruction-following","task_name":"Instruction Following"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"zero-shot-generalization","task_name":"Zero-shot Generalization"},{"task_slug":"cross-modal-alignment","task_name":"cross-modal alignment"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2507.02768","atlas_url":"https://app.syntology.ai/?focus=2507.02768","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.02768"}},"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/kehanlu/DeSTA2","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kehanlu/desta2.5-audio","reach":{"status":"ok"}}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"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":1,"samples":[{"code_sha256_prefix":"76f693db9eb80963","entry":"select_channels","repo":"kehanlu/desta2.5-audio","repo_kind":"official","path":"desta/utils/audio.py","file_url":"https://github.com/kehanlu/desta2.5-audio/blob/HEAD/desta/utils/audio.py","link_basis":"first_harvest_node","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":"76f693db9eb80963"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}