{"id":"https://openalex.org/W7138906627","doi":"https://doi.org/10.1609/aaai.v40i41.40804","title":"LaF-GRPO: In-Situ Navigation Instruction Generation for the Visually Impaired via GRPO with LLM-as-Follower Reward","display_name":"LaF-GRPO: In-Situ Navigation Instruction Generation for the Visually Impaired via GRPO with LLM-as-Follower Reward","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138906627","doi":"https://doi.org/10.1609/aaai.v40i41.40804"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i41.40804","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i41.40804","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40804/44765","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40804/44765","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130200159","display_name":"Yi Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Yi Zhao","raw_affiliation_strings":["The Hong Kong Polytechnic University"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129839982","display_name":"Siqi Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Siqi Wang","raw_affiliation_strings":["The Hong Kong Polytechnic University"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100775347","display_name":"Jie Li","orcid":"https://orcid.org/0000-0002-4366-7724"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jing Li","raw_affiliation_strings":["The Hong Kong Polytechnic University"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5130200159"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.79365079,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"41","first_page":"34994","last_page":"35002"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10914","display_name":"Tactile and Sensory Interactions","score":0.6085000038146973,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10914","display_name":"Tactile and Sensory Interactions","score":0.6085000038146973,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.27320000529289246,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10799","display_name":"Data Visualization and Analytics","score":0.0066999997943639755,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/usable","display_name":"USable","score":0.7688999772071838},{"id":"https://openalex.org/keywords/visually-impaired","display_name":"Visually impaired","score":0.6865000128746033},{"id":"https://openalex.org/keywords/safer","display_name":"SAFER","score":0.6751999855041504},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.6660000085830688},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.4593999981880188},{"id":"https://openalex.org/keywords/prioritization","display_name":"Prioritization","score":0.3375999927520752},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.3174999952316284},{"id":"https://openalex.org/keywords/scarcity","display_name":"Scarcity","score":0.3122999966144562}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7768999934196472},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.7688999772071838},{"id":"https://openalex.org/C3020106864","wikidata":"https://www.wikidata.org/wiki/Q737460","display_name":"Visually impaired","level":2,"score":0.6865000128746033},{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.6751999855041504},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.6660000085830688},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.6442999839782715},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.4593999981880188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4478999972343445},{"id":"https://openalex.org/C2777615720","wikidata":"https://www.wikidata.org/wiki/Q11888847","display_name":"Prioritization","level":2,"score":0.3375999927520752},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3061999976634979},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C3018587665","wikidata":"https://www.wikidata.org/wiki/Q7268696","display_name":"Qualitative analysis","level":3,"score":0.2955000102519989},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2874999940395355},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27790001034736633},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C2778761605","wikidata":"https://www.wikidata.org/wiki/Q3565782","display_name":"Navigational aid","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2547999918460846},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i41.40804","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i41.40804","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40804/44765","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i41.40804","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i41.40804","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40804/44765","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138906627.pdf","grobid_xml":"https://content.openalex.org/works/W7138906627.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Navigation":[0],"instruction":[1,62,109],"generation":[2],"for":[3,28],"visually":[4],"impaired":[5],"(VI)":[6],"individuals":[7],"(NIG-VI)":[8],"is":[9],"critical":[10],"yet":[11],"relatively":[12],"underexplored.":[13],"This":[14,60],"study":[15],"focuses":[16],"on":[17,112],"generating":[18],"precise,":[19],"in-situ,":[20],"step-by-step":[21],"navigation":[22,45,98],"instructions":[23],"that":[24,138],"are":[25],"practically":[26],"usable":[27],"VI":[29,41],"users.":[30],"Specifically,":[31],"we":[32,83],"propose":[33],"LaF-GRPO":[34,118],"(LLM-as-Follower":[35],"GRPO),":[36],"where":[37],"an":[38],"LLM":[39],"simulates":[40],"user":[42],"responses":[43],"to":[44,51,90],"instructions,":[46],"thereby":[47],"providing":[48],"feedback":[49],"rewards":[50],"guide":[52],"the":[53,75,115],"post-training":[54],"of":[55,77,117],"a":[56,86],"Vision-Language":[57],"Model":[58],"(VLM).":[59],"enhances":[61],"accuracy":[63],"and":[64,93,106,133,144],"usability":[65],"while":[66],"reducing":[67],"costly":[68],"real-world":[69],"data":[70],"collection":[71],"needs.":[72],"To":[73],"address":[74],"scarcity":[76],"dedicated":[78],"benchmarks":[79],"in":[80],"this":[81],"field,":[82],"introduce":[84],"NIG4VI,":[85],"27k-sample":[87],"open-source":[88],"dataset":[89],"facilitate":[91],"training":[92],"evaluation.":[94],"It":[95],"comprises":[96],"diverse":[97],"scenarios":[99],"with":[100],"accurate":[101],"spatial":[102],"coordinates,":[103],"supporting":[104],"detailed":[105],"open-ended":[107],"in-situ":[108],"generation.":[110],"Experiments":[111],"NIG4VI":[113],"demonstrate":[114],"effectiveness":[116],"through":[119],"quantitative":[120],"metrics":[121],"(e.g.,":[122],"Zero-(LaF-GRPO)":[123],"boosts":[124],"BLEU":[125],"14%;":[126],"SFT+(LaF-GRPO)":[127],"METEOR":[128],"0.542":[129],"vs.":[130],"GPT-4o":[131],"0.323),":[132],"qualitative":[134],"analysis":[135],"further":[136],"confirms":[137],"our":[139],"method":[140],"yields":[141],"more":[142],"intuitive":[143],"safer":[145],"instructions.":[146]},"counts_by_year":[],"updated_date":"2026-03-20T20:54:20.808490","created_date":"2026-03-20T00:00:00"}