{"id":"https://openalex.org/W4416747950","doi":"https://doi.org/10.1109/iros60139.2025.11247245","title":"DiffGen: Robot Demonstration Generation via Differentiable Physics Simulation, Differentiable Rendering, and Vision-Language Model","display_name":"DiffGen: Robot Demonstration Generation via Differentiable Physics Simulation, Differentiable Rendering, and Vision-Language Model","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416747950","doi":"https://doi.org/10.1109/iros60139.2025.11247245"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247245","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247245","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101574527","display_name":"Jin Yang","orcid":"https://orcid.org/0000-0003-1900-520X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Jin","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106407118","display_name":"Jun Lv","orcid":"https://orcid.org/0000-0002-0920-8444"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Lv","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043876109","display_name":"Shuqiang Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuqiang Jiang","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077494398","display_name":"Cewu Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cewu Lu","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11305","last_page":"11312"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.24690000712871552,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.24690000712871552,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.21930000185966492,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.1006999984383583,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/differentiable-function","display_name":"Differentiable function","score":0.8450999855995178},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7878999710083008},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7777000069618225},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5307000279426575},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.43529999256134033},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.35030001401901245},{"id":"https://openalex.org/keywords/robot-control","display_name":"Robot control","score":0.34369999170303345}],"concepts":[{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.8450999855995178},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7878999710083008},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7777000069618225},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.576200008392334},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5307000279426575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4602000117301941},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.43529999256134033},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.35030001401901245},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.34369999170303345},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.33799999952316284},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C74222875","wikidata":"https://www.wikidata.org/wiki/Q16000312","display_name":"Robot kinematics","level":4,"score":0.30149999260902405},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2815000116825104},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.2743000090122223},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.25619998574256897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247245","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247245","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2158782408","https://openalex.org/W2194775991","https://openalex.org/W2556096037","https://openalex.org/W2883429621","https://openalex.org/W2902812770","https://openalex.org/W2951360122","https://openalex.org/W2963150697","https://openalex.org/W2990173985","https://openalex.org/W3035624836","https://openalex.org/W3049755554","https://openalex.org/W3096831136","https://openalex.org/W3173446233","https://openalex.org/W3207758636","https://openalex.org/W3216834690","https://openalex.org/W4385245566","https://openalex.org/W4390873331","https://openalex.org/W4390874575","https://openalex.org/W4401413701","https://openalex.org/W4401414432","https://openalex.org/W4401414437","https://openalex.org/W4403129459"],"related_works":[],"abstract_inverted_index":{"Generating":[0],"robot":[1,15,43,87,92,104,168],"demonstrations":[2,44,105],"through":[3,147],"simulation":[4],"is":[5,49,140],"widely":[6],"recognized":[7],"as":[8],"an":[9],"effective":[10],"way":[11],"to":[12,24,41,80],"scale":[13],"up":[14],"data.":[16],"Previous":[17],"work":[18,38],"often":[19],"trained":[20],"reinforcement":[21],"learning":[22],"agents":[23],"generate":[25,42,102,167],"expert":[26],"policies,":[27],"but":[28,51],"this":[29,61],"approach":[30],"lacks":[31],"sample":[32],"efficiency.":[33],"Recently,":[34],"a":[35,57,66,77,90,96],"line":[36],"of":[37,86,113,120,179],"has":[39],"attempted":[40],"via":[45],"differentiable":[46,71,74,149,151],"simulation,":[47,73,150],"which":[48],"promising":[50],"heavily":[52],"relies":[53],"on":[54],"reward":[55],"design,":[56],"labor-intensive":[58],"process.":[59],"In":[60],"paper,":[62],"we":[63,162],"propose":[64],"DiffGen,":[65,161],"novel":[67],"framework":[68],"that":[69,159],"integrates":[70],"physics":[72],"rendering,":[75,152],"and":[76,83,95,117,137,144,153,165],"vision-language":[78,135,154],"model":[79,155],"enable":[81],"automatic":[82],"efficient":[84],"generation":[85],"demonstrations.":[88],"Given":[89],"simulated":[91,122],"manipulation":[93,125],"scenario":[94],"natural":[97],"language":[98,115],"instruction,":[99],"DiffGen":[100],"can":[101,182],"realistic":[103],"by":[106,142],"minimizing":[107],"the":[108,111,114,118,121,134,138,148,180],"distance":[109],"between":[110],"embedding":[112,119],"instruction":[116],"observation":[123],"after":[124],"in":[126],"representation":[127],"space.":[128],"The":[129,177],"embeddings":[130],"are":[131],"obtained":[132],"from":[133],"model,":[136],"optimization":[139],"achieved":[141],"calculating":[143],"descending":[145],"gradients":[146],"components.":[156],"Experiments":[157],"demonstrate":[158],"with":[160,170],"could":[163],"efficiently":[164],"effectively":[166],"data":[169],"minimal":[171],"human":[172],"effort":[173],"or":[174],"training":[175],"time.":[176],"videos":[178],"results":[181],"be":[183],"accessed":[184],"at":[185],"https://sites.google.com/view/diffgen.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-28T00:00:00"}