Meta tags:

Headings (most frequently used words):

news, research, highlights, profile, selected, publications, professional, service, zhenfei, jeremy, yin,

Text of the page (most frequently used words):
the (80), and (70), yin (64), #zhenfei (60), pdf (59), wang (59), zhang (57), 2025 (52), 2026 (41), preprint (40), chen (39), liu (38), for (36), agents (35), multi (34), 2024 (33), agent (28), models (27), conference (26), workshop (25), systems (23), shao (22), learning (22), zhou (21), with (21), lei (21), huang (20), vision (20), bai (20), jing (19), language (19), code (17), world (17), philip (17), torr (17), embodied (16), wanli (16), ouyang (16), iclr (15), foundation (15), project (15), llm (15), neurips (14), page (14), large (14), acl (14), tang (14), reasoning (14), qiao (13), international (13), yang (13), fan (12), open (12), based (12), modal (11), sheng (11), icml (10), qin (10), computer (10), shi (10), heng (10), research (10), intelligence (10), iccv (9), annual (9), yiran (9), tao (9), model (8), report (8), kun (8), sun (8), yan (8), via (8), rui (8), lin (7), from (7), zaibin (7), association (7), computational (7), linguistics (7), has (7), organizing (7), cvpr (6), visual (6), talk (6), gao (6), towards (6), dataset (6), training (6), datasets (6), zhelun (6), zhiyong (6), framework (6), multimodal (6), ruimao (6), zheng (6), lijun (6), gui (6), meeting (6), fang (6), zhao (6), one (6), scientific (6), kang (6), yutao (6), guibin (6), agentic (6), his (6), work (6), also (6), prof (6), eccv (5), 2023 (5), song (5), building (5), machine (5), ieee (5), yao (5), benchmarks (5), information (5), processing (5), cao (5), benchmark (5), system (5), you (5), xue (5), dong (5), qian (5), shen (5), hao (5), jin (5), cheng (5), shixiang (5), are (5), generation (5), paper (5), can (5), yue (5), guo (5), scaling (5), evolving (5), university (5), our (5), organized (5), was (5), peer (4), review (4), academic (4), technical (4), junjie (4), tech (4), 2022 (4), through (4), track (4), thirty (4), neural (4), representations (4), zhen (4), comprehensive (4), beyond (4), yongting (4), findings (4), iros (4), robotic (4), xuanjing (4), main (4), jiang (4), jia (4), pang (4), siheng (4), planning (4), mas (4), hejia (4), geng (4), xiangyuan (4), self (4), reinforcement (4), shuang (4), zeng (4), yifan (4), hongru (4), guancheng (4), wan (4), post (4), spatial (4), source (4), release (4), focusing (4), intelligent (3), organizer (3), yinan (3), jianing (3), teng (3), peng (3), liang (3), new (3), yuanhan (3), ziwei (3), scale (3), european (3), representation (3), benchmarking (3), zhipin (3), hongxing (3), evaluation (3), assessment (3), recognition (3), enshen (3), advancing (3), jie (3), ren (3), generalization (3), feng (3), safety (3), aishan (3), xianglong (3), potential (3), gan (3), huchuan (3), interaction (3), xianghe (3), chai (3), llms (3), cai (3), physical (3), oral (3), presentation (3), award (3), empirical (3), xiufeng (3), xiaohong (3), compositional (3), ninth (3), simulation (3), zhiheng (3), tan (3), yijiang (3), liao (3), shuicheng (3), fourteenth (3), wenxuan (3), shaosheng (3), xiangru (3), 64th (3), time (3), zhu (3), dou (3), zeping (3), mengdi (3), first (3), mars (3), challenge (3), deepresearch (3), publications (3), indicates (3), robotics (3), scientists (3), selected (3), received (3), that (3), researcher (3), oxford (3), real (3), competition (3), excited (3), series (3), researchers (3), well (3), thrilled (3), platform (3), all (3), star (3), where (3), please (3), lab (3), email (3), your (3), about (3), multimedia (2), retrieval (2), usyd (2), spring (2), understanding (2), trustworthy (2), tifa (2), mfm (2), eai (2), echo (2), professional (2), service (2), 2021 (2), siyu (2), yangguang (2), qinghong (2), gengshi (2), huan (2), shuo (2), yujie (2), ding (2), intern (2), general (2), human (2), tasks (2), yuan (2), luo (2), xiaoshui (2), pre (2), knowledge (2), lamm (2), tuning (2), zeren (2), mllms (2), cvf (2), pattern (2), zhiyuan (2), image (2), guodong (2), jingyi (2), jinlan (2), ming (2), qibing (2), yujiong (2), gpt (2), landscape (2), trustworthiness (2), wei (2), rsj (2), robots (2), follow (2), chain (2), alignment (2), senjie (2), xiao (2), jiapeng (2), dacheng (2), haoyang (2), renqi (2), nanqing (2), two (2), better (2), forty (2), second (2), xihui (2), video (2), ziyi (2), ling (2), guohao (2), oasis (2), million (2), zhuqiang (2), jiaao (2), there (2), revealing (2), risks (2), utilizing (2), scholarly (2), build (2), yiming (2), emnlp (2), outstanding (2), top (2), driven (2), collaboration (2), constraints (2), next (2), era (2), science (2), qimin (2), xiangrui (2), jiaqi (2), maslab (2), sha (2), wangmeng (2), zuo (2), yuhao (2), wangchunshu (2), wenlong (2), long (2), honglin (2), discipline (2), tmlr (2), xiaohang (2), zelin (2), zhongzhi (2), survey (2), yufan (2), qingyu (2), xiaoman (2), text (2), behaviors (2), study (2), meng (2), latent (2), space (2), memory (2), zonghao (2), ying (2), quanchen (2), zou (2), over (2), shihan (2), jiahao (2), yixin (2), wen (2), gang (2), yixia (2), guanhua (2), efficient (2), thinking (2), hong (2), zehui (2), zehong (2), analysis (2), yiwen (2), keyang (2), guangnan (2), hongfeng (2), rethinking (2), tool (2), use (2), textual (2), market (2), cong (2), laws (2), visit (2), list (2), google (2), scholar (2), topics (2), papers (2), including (2), 000 (2), projects (2), across (2), efforts (2), nature (2), washington (2), jeremy (2), postdoctoral (2), supervised (2), visiting (2), stanford (2), princeton (2), sydney (2), not (2), but (2), discovery (2), scientist (2), both (2), virtual (2), team (2), acm (2), icpc (2), which (2), everyone (2), welcome (2), join (2), capabilities (2), announce (2), contribute (2), most (2), opportunities (2), emerging (2), rising (2), invited (2), participate (2), ideas (2), will (2), workshops (2), lifelong (2), aligning (2), 2nd (2), students (2), like (2), news (2), working (2), had (2), homepage (2), program, committee, tpami, acmmm, aaai, arr, teaching, assistant, comp, 5425, guest, lecture, signal, elec5304, meets, event, present, mengya, jihao, guanglu, yichao, yuming, fenggang, chengyu, conghui, fengwei, dahua, xiaogang, paradigm, journal, 1007, s11263, 025, 02450, yichun, zexin, bamboo, mega, continually, synergy, ijcv, learner, cross, sources, universal, omni, lens, realms, expo, jiebo, point, cloud, distilled, images, icme, seventh, jiong, jianjian, dingning, mukai, assisted, instruction, twelfth, ziqin, huayang, octavius, mitigating, task, interference, lora, moe, chef, standardized, qichang, mp5, ended, minecraft, active, perception, 18th, zheyuan, jinjin, tianfan, chao, depicting, scores, quality, chaochao, hongzhi, deng, kexin, kunchang, limin, meiqi, sirui, yali, yaru, yingchun, yixu, yurong, mou, yuxi, gemini, assessing, generalizability, causality, four, modalities, 62nd, dongrui, yong, tracing, dynamics, revisiting, period, yuzhou, minedreamer, instructions, imagination, simulated, control, values, xiaoya, lehan, sucheng, shu, cewu, rh20t, primitive, level, composable, yifeng, spa, preference, yisong, qianjia, siyuan, genderbias, gender, bias, counterfactual, probing, 63rd, xinzhe, jingzhe, heads, than, improve, idea, jiwen, xijun, worldsimbench, simulators, zirui, yuxian, ziyue, zhiyu, zijian, jinsong, martz, bowen, prateek, gupta, shuyue, bernard, ghanem, social, simulations, mengwei, zhihui, zicheng, vllm, balanced, spatio, temporal, tokens, xiang, xiaowen, yet, yaxin, xindi, baolu, liqian, jianfei, tien, tsin, wong, vlipp, physically, plausible, informed, prior, sac, highlight, candidates, methods, natural, reso, reward, robofactory, exploring, hui, automation, become, keduan, yuzhu, tian, bohan, kaiqu, rongye, wenjun, unified, codebase, heterogeneous, zixuan, wenxi, jinouwen, xuantuo, hanqing, tai, jiangmiao, duan, dongzhan, labutopia, high, fidelity, hierarchical, viki, coordinating, cooperation, shunyu, minghao, huichi, zhenyu, cui, wendong, jiajun, weihao, xuan, jiaxing, heli, qingcheng, ziqi, jialiang, jindi, aosong, wenhao, irene, qunshu, mingli, verigui, verifiable, guanyu, yufang, xiaoran, jingchao, bmmr, bilingual, transactions, zihu, songtao, mengyue, michael, littman, jun, zheyong, xie, wenbo, yuntian, junbo, shaohui, interleaving, wanghan, zijie, daniel, cixuan, lixin, hanrui, eigen, adaptive, monitor, rag, mulei, qiang, mathematical, fanci, zherui, latentevolve, test, qianshan, tengchao, yaochen, xinfeng, zhan, thorsten, holz, zhiqiang, xiaofeng, memguard, proactive, defense, comas, rewards, jianle, wenxin, junzheng, mingchuan, securewebarena, holistic, security, lvlm, web, yuchen, tiancheng, livesearchbench, automatically, constructed, dynamic, yuyang, shichun, yanwei, boyang, fangyi, jiahang, jiejun, yanbin, jiongnan, zeyu, zhongxiang, boci, zhenrong, xuanbo, jiaxin, xinlei, zhenhong, zewen, huo, junhao, yuwei, niu, xiaobin, qiankun, dawei, shirui, pan, zhicheng, rong, age, qiu, dongdong, pony, word, implicit, best, tianlin, jian, yaodong, robosafe, safeguarding, executable, logic, yuhan, lianjie, zhongbo, binghao, ran, fuxi, zhuohan, think3d, bruno, ziye, ximeng, stone, yilun, advances, innovations, zhemeng, jiahua, xincheng, xin, yuzhi, boyan, haoqin, daolin, touchguide, inference, steering, visuomotor, policies, touch, guidance, qiuchen, chu, incentivizing, capability, bolian, yijun, yiyang, weixiang, xiusi, yanfang, why, fails, plan, centric, horizon, decision, making, role, entropy, optimizing, yishuo, shiting, search, behavioral, consistency, validation, trading, style, switching, stock, xinwu, yicheng, mao, yimeng, zhiwei, yuxuan, xiangxiang, shenghua, latentchem, cot, chemical, jiaxi, yanzuo, zihan, chang, junchi, todoevolve, architect, lintao, yilin, xinzhu, charting, fine, yajie, binze, huayu, jiazheng, qiyuan, junlin, shang, jixuan, jingqi, tong, xingjun, sciagentgym, step, complete, equal, contribution, corresponding, lead, authored, preprints, published, conferences, journals, citations, contributed, github, stars, total, built, help, push, passive, assistance, toward, execution, continual, innovation, representative, include, platforms, societies, broader, academia, coverage, focuses, only, understand, generate, act, adapt, drive, spans, goal, purpose, operate, worlds, uncover, automated, highlights, profile, student, coach, led, finals, achieving, 31st, place, 2018, achieved, rank, 2265, meta, focused, identifying, videos, facial, voice, manipulations, sourced, solution, dfdc, 2020, began, weekly, inviting, young, around, who, known, their, generative, vlm, applications, hosted, evaluate, complex, egoplan, meet, supporting, interactions, among, gave, titled, society, nod, mathworks, matlab, dedicated, providing, essential, components, codebases, more, releasing, this, community, masworks, settings, aims, support, almost, approaches, attended, events, entire, challenges, futures, honored, nominee, recognizing, field, waic, yunfan, covered, piece, discusses, impact, reviewing, future, ecosystem, featured, concept, gaining, wide, attention, feature, virsci, position, systematically, define, outline, paradigms, check, out, explore, curated, find, helpful, consider, upvote, awesome, hugging, face, reliable, interactable, geometry, physics, interactivity, relevant, details, have, been, released, further, official, website, base, just, begun, warmly, innovative, sfe, panel, discussion, recursive, improvement, give, wet, modelling, icra, five, 6th, adversarial, media, scalebot, scalable, robot, mmragi, colm, looking, motivated, such, related, areas, strong, background, these, fields, plus, must, curiosity, commitment, willingness, learn, matter, interested, short, note, interests, junior, seeking, advice, early, careers, chat, career, collaborations, feel, free, schedule, happy, recommend, some, internship, job, curriculum, vitae, currently, did, previously, fellow, shanghai, collaborated, wonderful, visitor, chinese, kong, before, starting, part, sensetime, agi, group, closely, earned, bachelor, degree, hust, honor, being, captain, guided, amanda, xiaoou, orcid, dblp, linkedin, twitter, london, developing, postdoc,

Text of the page (random words):
ed events of the entire conference 2025 04 thrilled to release mars multi agent robotics system an open source framework focusing on embodied intelligence in multi agent settings mars aims to support almost all approaches based on foundation model embodied agents spatial intelligence and compositional intelligence generalization and constraints you re welcome to follow and contribute 2025 04 excited to announce masworks maslab a nod to mathworks matlab an open source framework dedicated to multi agent systems based on llm agents providing all essential components for mas research datasets benchmarks codebases and more we ll also be releasing a series of new research projects based on this platform join us in building the community 2024 12 i gave a talk at the neurips 2024 workshop on open world agents titled building ai society with foundation model agents 2024 11 thrilled to announce oasis a simulation platform supporting interactions among over one million llm agents 2024 07 i organized the icml 2024 workshop on multi modal foundation models meet embodied ai mfm eai 2024 07 i organized the icml 2024 workshop on trustworthy multi modal foundation models and ai agents tifa 2024 05 i co hosted the egoplan challenge to evaluate embodied agents complex planning capabilities 2023 11 excited to release lamm a comprehensive framework for vlm training evaluation and applications in embodied agents 2023 08 i began organizing a weekly academic talk series echo ai talk inviting young researchers from around the world who are well known for their work in generative ai foundation models and ai agents everyone is welcome to join 2021 11 excited to release intern a series of multi modal foundation models focusing on visual representation learning 2020 07 achieved rank 4 of 2265 in meta s dfdc competition which focused on identifying videos with facial or voice manipulations our solution is open sourced 2018 05 as a student coach i led a team to the acm icpc world finals achieving 31st place research highlights profile zhenfei jeremy yin is a postdoctoral researcher at the university of oxford supervised by prof philip torr and a visiting researcher at stanford and princeton he received his ph d from the university of sydney his research focuses on advancing the next generation of ai systems that can not only understand and generate but also act adapt and drive discovery in the real world his work spans foundation model agents multi agent systems self evolving agents embodied agents and robotics and ai scientist systems with the goal of building general purpose ai agents that can operate across both physical and virtual worlds and uncover new scaling laws for agent based intelligence and automated scientific discovery dr yin has authored 90 papers including preprints with 50 papers published at top ai conferences and journals and his work has received 2 000 citations he has also contributed to open source ai projects with 20 000 github stars in total across agentic ai multi agent systems embodied intelligence and ai scientists he has built research and open source efforts that help push ai beyond passive assistance toward execution continual learning and innovation his representative efforts include open platforms and systems for multimodal foundation models large scale agent societies multi agent systems and embodied intelligence his work has also received broader recognition beyond academia including coverage by nature and the washington post selected publications topics foundation model agents robotics ai scientists indicates equal contribution indicates corresponding indicates project lead visit google scholar for the complete list of publications preprint sciagentgym benchmarking multi step scientific tool use in llm agents yujiong shen yajie yang zhiheng xi binze hu huayu sha jiazheng zhang qiyuan peng junlin shang jixuan huang yutao fan jingqi tong shihan dou ming zhang lei bai zhenfei yin tao gui xingjun ma qi zhang xuanjing huang yu gang jiang preprint 2026 pdf preprint charting empirical laws for llm fine tuning in scientific multi discipline learning lintao wang zhuqiang lu yilin zhu kun hu zhenfei yin shixiang tang zhiyong wang wanli ouyang xinzhu ma preprint 2026 pdf preprint todoevolve learning to architect agent planning systems jiaxi liu yanzuo jiang guibin zhang zihan zhang heng chang zhenfei yin qibing ren junchi yan preprint 2026 pdf preprint latentchem from textual cot to latent thinking in chemical reasoning xinwu ye yicheng mao jia zhang yimeng liu li hao fang wu zhiwei li yuxuan liao zehong wang zhiyuan liu zhenfei yin li yuan philip torr huan sun xiangxiang zeng mengdi wang le cong shenghua gao xiangru tang preprint 2026 pdf acl 2026 findings behavioral consistency validation for llm agents an analysis of trading style switching through stock market simulation zeping li guancheng wan keyang chen yu chen yiwen zhao philip torr guangnan ye zhenfei yin hongfeng chai findings of the association for computational linguistics acl 2026 pdf preprint vision deepresearch benchmark rethinking visual and textual search for multimodal large language models yu zeng wenxuan huang zhen fang shuang chen yufan shen yishuo cai xiaoman wang zhenfei yin lin chen zehui chen shiting huang yiming zhao xu tang yao hu philip torr wanli ouyang shaosheng cao preprint 2026 pdf acl 2026 rethinking the role of entropy in optimizing tool use behaviors for large language model agents zeping li hongru wang yiwen zhao guanhua chen yixia li keyang chen yixin cao guangnan ye hongfeng chai zhenfei yin the 64th annual meeting of the association for computational linguistics main conference acl 2026 pdf preprint why reasoning fails to plan a planning centric analysis of long horizon decision making in llm agents zehong wang fang wu hongru wang xiangru tang bolian li zhenfei yin yijun ma yiyang li weixiang sun xiusi chen yanfang ye preprint 2026 pdf preprint vision deepresearch incentivizing deepresearch capability in multimodal large language models wenxuan huang yu zeng qiuchen wang zhen fang shaosheng cao zheng chu qingyu yin shuang chen zhenfei yin lin chen zehui chen xu tang yao hu philip torr feng zhao wanli ouyang preprint 2026 pdf preprint touchguide inference time steering of visuomotor policies via touch guidance zhemeng zhang jiahua ma xincheng yang xin wen yuzhi zhang boyan li yiran qin jin liu can zhao li kang haoqin hong zhenfei yin philip torr hao su ruimao zhang daolin ma preprint 2026 pdf tech report advances and innovations in the multi agent robotic system mars challenge li kang heng zhou xiufeng song rui li bruno ny chen ziye wang ximeng meng stone tao yiran qin xiaohong liu ruimao zhang lei bai yilun du hao su philip torr zhenfei yin technical report 2026 pdf preprint think3d thinking with space for spatial reasoning zaibin zhang yuhan wu lianjie jia yifan wang zhongbo zhang yijiang li binghao ran fuxi zhang zhuohan sun zhenfei yin lijun wang huchuan lu preprint 2026 pdf iclr 2026 workshop robosafe safeguarding embodied agents via executable safety logic le wang zonghao ying xiao yang quanchen zou zhenfei yin tianlin li jian yang yaodong yang aishan liu xianglong liu the first workshop on efficient spatial reasoning iclr 2026 oral presentation best paper award pdf acl 2026 from word to world can large language models be implicit text based world models yixia li hongru wang jiahao qiu zhenfei yin dongdong zhang cheng qian zeping li pony ma guanhua chen heng ji mengdi wang the 64th annual meeting of the association for computational linguistics main conference acl 2026 pdf preprint memory in the age of ai agents yuyang hu shichun liu yanwei yue guibin zhang boyang liu fangyi zhu jiahang lin honglin guo shihan dou zhiheng xi senjie jin jiejun tan yanbin yin jiongnan liu zeyu zhang zhongxiang sun yutao zhu hao sun boci peng zhenrong cheng xuanbo fan jiaxin guo xinlei yu zhenhong zhou zewen hu jiahao huo junhao wang yuwei niu yu wang zhenfei yin xiaobin hu yue liao qiankun li kun wang wangchunshu zhou yixin liu dawei cheng qi zhang tao gui shirui pan yan zhang philip torr zhicheng dou ji rong wen xuanjing huang yu gang jiang shuicheng yan preprint 2025 pdf preprint livesearchbench an automatically constructed benchmark for retrieval and reasoning over dynamic knowledge heng zhou ao yu yuchen fan jianing shi li kang hejia geng yongting zhang yutao fan yuhao wu tiancheng he yiran qin lei bai zhenfei yin preprint 2025 pdf acl 2026 securewebarena a holistic security evaluation benchmark for lvlm based web agents zonghao ying yangguang shao jianle gan gan xu junjie shen wenxin zhang quanchen zou junzheng shi zhenfei yin mingchuan zhang aishan liu xianglong liu findings of the association for computational linguistics acl 2026 pdf iclr 2026 comas co evolving multi agent systems via interaction rewards xiangyuan xue yifan zhou guibin zhang zaibin zhang yijiang li chen zhang zhenfei yin philip torr wanli ouyang lei bai the fourteenth international conference on learning representations iclr 2026 pdf preprint a memguard a proactive defense framework for llm based agent memory qianshan wei tengchao yang yaochen wang xinfeng li lijun li zhenfei yin yi zhan thorsten holz zhiqiang lin xiaofeng wang preprint 2025 pdf preprint latentevolve self evolving test time scaling in latent space guibin zhang fanci meng guancheng wan zherui li kun wang zhenfei yin lei bai shuicheng yan preprint 2025 pdf acl 2026 scaling behaviors of llm reinforcement learning post training an empirical study in mathematical reasoning zelin tan hejia geng mulei zhang xiaohang yu guancheng wan yifan zhou qiang he xiangyuan xue heng zhou yutao fan zhongzhi li zaibin zhang guibin zhang chen zhang zhenfei yin lei bai the 64th annual meeting of the association for computational linguistics main conference acl 2026 oral presentation pdf iclr 2026 eigen agent adaptive multi agent scientific reasoning with monitor based rag xiangru tang wanghan xu yujie wang zijie guo daniel shao jiapeng chen cixuan zhang ziyi wang lixin zhang guancheng wan wenlong zhang lei bai zhenfei yin philip torr hanrui wang di jin the fourteenth international conference on learning representations iclr 2026 pdf iclr 2026 interleaving reasoning for better text to image generation wenxuan huang shuang chen zheyong xie shaosheng cao shixiang tang yufan shen qingyu yin wenbo hu xiaoman wang yuntian tang junbo qiao yue guo yao hu zhenfei yin philip torr yu cheng wanli ouyang shaohui lin the fourteenth international conference on learning representations iclr 2026 pdf tmlr the landscape of agentic reinforcement learning for llms a survey guibin zhang hejia geng xiaohang yu zhenfei yin zaibin zhang zelin tan heng zhou zhongzhi li xiangyuan xue yijiang li yifan zhou yang chen chen zhang yutao fan zihu wang songtao huang yue liao hongru wang mengyue yang heng ji michael littman jun wang shuicheng yan philip torr lei bai transactions on machine learning research tmlr 2026 pdf neurips 2025 bmmr a large scale bilingual multimodal multi discipline reasoning dataset zhiheng xi guanyu li yutao fan honglin guo yufang liu xiaoran fan jiaqi liu jingchao ding wangmeng zuo zhenfei yin lei bai tao ji tao gui qi zhang philip torr xuanjing huang the thirty ninth annual conference on neural information processing systems datasets and benchmarks track neurips 2025 pdf project page code preprint verigui verifiable long chain gui dataset shunyu liu minghao liu huichi zhou zhenyu cui yang zhou yuhao zhou wendong fan ge zhang jiajun shi weihao xuan jiaxing huang shuang luo fang wu heli qi qingcheng zeng ziqi ren jialiang gao jindi lv junjie wang aosong feng heng zhou wangchunshu zhou zhenfei yin wenlong zhang guohao li wenhao yu irene li lei ma lei bai qunshu lin mingli song dacheng tao preprint 2025 pdf code neurips 2025 viki r coordinating embodied multi agent cooperation via reinforcement learning li kang xiufeng song heng zhou yiran qin jie yang xiaohong liu philip torr lei bai zhenfei yin the thirty ninth annual conference on neural information processing systems datasets and benchmarks track neurips 2025 pdf neurips 2025 labutopia high fidelity simulation and hierarchical benchmark for scientific embodied agents rui li zixuan hu wenxi qu jinouwen zhang zhenfei yin sha zhang xuantuo huang hanqing wang tai wang jiangmiao pang wanli ouyang lei bai wangmeng zuo ling yu duan dongzhan zhou shixiang tang the thirty ninth annual conference on neural information processing systems datasets and benchmarks track neurips 2025 pdf preprint x mas towards building multi agent systems with heterogeneous llms rui ye xiangrui liu qimin wu xianghe pang zhenfei yin lei bai siheng chen preprint 2025 pdf preprint maslab a unified and comprehensive codebase for llm based multi agent systems rui ye keduan huang qimin wu yuzhu cai tian jin xianghe pang xiangrui liu jiaqi su chen qian bohan tang kaiqu liang jiaao chen yue hu zhenfei yin rongye shi bo an yang gao wenjun wu lei bai siheng chen preprint 2025 pdf preprint ai driven automation can become the foundation of next era science of science research renqi chen haoyang su shixiang tang zhenfei yin qi wu hui li ye sun nanqing dong wanli ouyang philip torr preprint 2025 pdf iccv 2025 robofactory exploring embodied agent collaboration with compositional constraints yiran qin li kang xiufeng song zhenfei yin xiaohong liu xihui liu ruimao zhang lei bai international conference on computer vision iccv 2025 pdf project page emnlp 2025 reso a reward driven self organizing llm based multi agent system for reasoning tasks heng zhou hejia geng xiangyuan xue li kang yiran qin zhiyong wang zhenfei yin lei bai empirical methods in natural language processing emnlp 2025 oral presentation sac highlight award outstanding paper candidates top 1 pdf code iccv 2025 vlipp towards physically plausible video generation with vision and language informed physical prior xindi yang baolu li yiming zhang zhenfei yin lei bai liqian ma zhiyong wang jianfei cai tien tsin wong huchuan lu xu jia international conference on computer vision iccv 2025 pdf project page icml 2025 mas gpt training llms to build llm based multi agent systems rui ye shuo tang rui ge yaxin du zhenfei yin siheng chen jing shao forty second international conference on machine learning icml 2025 iclr 2025 workshop on reasoning and planning for large language models 2025 pdf preprint are we there yet revealing the risks of utilizing large language models in scholarly peer review rui ye xianghe pang jingyi chai jiaao chen zhenfei yin zhen xiang xiaowen dong jing shao siheng chen preprint 2024 pdf project page iccv 2025 b vllm a vision large language model with balanced spatio temporal tokens zhuqiang lu zhenfei yin mengwei he zhihui wang zicheng liu zhiyong wang kun hu international conference on computer vision iccv 2025 pdf code neurips w 2024 oasis open agents social interaction simulations on one million agents ziyi yang zaibin zhang zirui zheng yuxian jian...