Meta tags:
author=Ram Ramrakhya;
keywords=yoda, ram81, ram ramrakhya, jekyll, hacker, developer, iit roorkee, deep learning, computer vision, neural networks, georgia tech, machine learning;
description=MS CS Student at Georgia Tech.;

Headings (most frequently used words):

for, embodied, and, learning, agents, benchmark, navigation, publications, scaling, with, reinforcement, multi, visual, objectnav, habitat, object, from, gui, agent, in, dataset, fabrik, ram, ramrakhya, news, bio, selected, all, projects, synthetic, task, generation, via, exploration, grounding, multimodal, llms, to, that, ask, help, goat, bench, modal, lifelong, seeing, the, unseen, common, sense, semantic, placement, pirlnav, pretraining, imitation, rl, finetuning, web, search, strategies, human, demonstrations, at, scale, ferret, ui, lite, lessons, building, small, on, device, ultracua, computer, use, through, programmatic, control, partnr, planning, reasoning, tasks, relic, recipe, 64k, steps, context, ai, hm3d, ovon, open, vocabulary, goal, matterport, 3d, semantics, ovrl, v2, simple, state, of, art, baseline, imagenav, offline, representation, an, online, collaborative, neural, network, editor, evalai,

Text of the page (most frequently used words):
and (28), paper (21), for (20), research (20), ram (19), ramrakhya (19), 2023 (17), with (15), code (14), 2022 (14), dhruv (13), batra (13), 2024 (13), the (12), cvpr (12), georgia (10), tech (10), 2025 (10), #learning (9), website (9), summer (9), accepted (9), google (8), arxiv (8), yang (8), agents (8), workshop (7), iclr (7), embodied (7), from (6), 2019 (6), zsolt (6), kira (6), alexander (6), habitat (6), intern (6), cloudcv (6), started (6), apr (6), our (6), abhishek (5), das (5), are (5), university (5), yadav (5), multi (5), 2018 (5), 2021 (5), phd (5), student (5), prof (5), oct (5), 2020 (5), jan (5), fabrik (4), that (4), have (4), challenges (4), karmesh (4), visual (4), navigation (4), chang (4), under (4), review (4), reinforcement (4), roozbeh (4), mottaghi (4), toshev (4), scaling (4), computer (4), modal (4), synthetic (4), data (4), institute (4), work (4), may (4), served (4), mentor (4), mar (4), preprint (4), out (4), models (3), using (3), web (3), gui (3), open (3), use (3), organizations (3), etc (3), submissions (3), dataset (3), benchmark (3), gunjan (3), chhablani (3), andrew (3), szot (3), matthew (3), yuhao (3), anh (3), nguyen (3), omar (3), attia (3), you (3), feng (3), zhe (3), gan (3), publications (3), presentation (3), pirlnav (3), seeing (3), unseen (3), generation (3), apple (3), spring (3), post (3), meta (3), allen (3), ai2 (3), aug (3), released (3), autoplay (3), online (2), collaborative (2), platform (2), train (2), via (2), simple (2), like (2), source (2), more (2), hosting (2), their (2), also (2), large (2), organization (2), stanford (2), 000 (2), systems (2), sosp (2), harsh (2), rrl (2), arjun (2), majumdar (2), aleksei (2), baevski (2), oleksandr (2), offline (2), representation (2), naoki (2), yokoyama (2), objectnav (2), highlight (2), top (2), gervet (2), john (2), turner (2), clegg (2), devendra (2), singh (2), chaplot (2), matterport (2), semantics (2), iros (2), hm3d (2), ovon (2), object (2), relic (2), ruta (2), desai (2), xavier (2), puig (2), eric (2), undersander (2), partnr (2), reasoning (2), agent (2), tasks (2), zhen (2), dou (2), tuan (2), keen (2), michael (2), chao (2), huang (2), yinfei (2), ferret (2), building (2), erik (2), wijmans (2), kuo (2), hao (2), luca (2), weihs (2), common (2), sense (2), semantic (2), goat (2), bench (2), llms (2), ask (2), selected (2), gatech (2), edu (2), training (2), interned (2), working (2), mitsubishi (2), electric (2), technology (2), mistral (2), llm (2), act (2), science (2), advised (2), masters (2), bio (2), jul (2), software (2), development (2), engineer (2), nov (2), jun (2), joined (2), runners (2), organized (2), available (2), here (2), challenge (2), awarded (2), college (2), computing (2), award (2), feb (2), papers (2), hm3dsem (2), program (2), sep (2), scholar (2), courtesy, build, visualize, deep, drag, drop, interface, allows, researchers, collectively, develop, debug, supports, importing, editing, exporting, networks, popular, frameworks, caffe, keras, tensorflow, leading, evaluating, benchmarking, hosted, who, created, than, industry, academia, project, some, labs, host, forked, versions, used, such, instead, reinventing, wheel, one, largest, interdisciplinary, centres, europe, forschungszentrum, jülich, world, health, alexaprize, mit, carnegie, mellon, virginia, umbc, pittsburg, draper, adelaide, iit, madras, nankai, facebook, deepmind, amazon, ebay, mapillary, yearly, pageviews, 130, contributors, 180, users, 200, evalai, projects, utsav, garg, viraj, prabhu, deshraj, agarwal, neural, network, editor, vincent, pierre, berges, sachit, kuhar, makysmet, makysmets, ovrl, state, art, baseline, imagenav, santhosh, kumar, ramakrishnan, theo, aaron, gokaslan, noah, maestre, angel, xuan, manolis, savva, william, sehoon, vocabulary, goal, ahmad, elawady, recipe, 64k, steps, context, mikael, dallaire, cote, michal, hlavac, vladimir, karashchuk, jacob, krantz, priyam, parashar, siddharth, patki, ishita, prasad, akshara, rai, daniel, tran, joanne, truong, tsung, yen, planning, ultracua, through, programmatic, control, forrest, haotian, zhang, jia, jeffrey, nichols, lite, lessons, small, device, all, video, embodiedai, overlooked, aspects, rss, spotlight, search, strategies, human, demonstrations, scale, pretraining, imitation, finetuning, vlmnm, icra, aniruddha, kembhavi, zeng, placement, mukul, khanna, sriram, yenamandra, theophile, lifelong, grounding, multimodal, help, 2026, bogdan, mazoure, agrawal, task, exploration, any, questions, want, collaborate, discuss, feel, free, send, email, been, fortunate, mlr, mllm, fair, vla, policies, was, laborateries, merl, scene, representations, anoop, cherian, zheng, pune, 2015, insitute, current, interested, general, purpose, can, reason, solve, complex, long, horizon, require, few, hours, days, currently, infrastructure, interaction, environments, required, capable, area, expertise, curation, simulation, scientist, final, year, department, prior, this, completed, closely, collaborated, during, time, read, inmobi, glance, conference, administrator, devi, parikh, machine, perception, lab, represented, summit, outstanding, interning, laboratories, recived, admits, austin, simon, fraser, offer, serving, reviewer, icml, rising, star, doctoral, news, dot, linkedin, twitter, github,

Text of the page (random words):
ram ramrakhya ram ramrakhya bio cv publications github google scholar semantic scholar twitter linkedin phd student georgia institute of technology ram ramrakhya at gatech dot edu news jan 2025 autoplay accepted to iclr 26 jan 2025 autoplay accepted to iclr 26 sep 2025 autoplay and ferret ui are released on arxiv apr 2025 ask to act is released on arxiv jan 2025 started as a research intern at apple ml research oct 2024 relic and partnr are released on arxiv jul 2024 hm3d ovon accepted at iros 2024 may 2024 started as a research intern at meta ai research mar 2024 awarded the college of computing rising star doctoral student research award 2023 feb 2024 2 papers seeing the unseen and goat bench accepted at cvpr 2024 jan 2024 preprint of our paper seeing the unseen is out on arxiv sep 2023 serving as a reviewer for iclr and icml 2024 aug 2023 started phd in cs at georgia tech may 2023 started as a research intern at allen institute of ai ai2 apr 2023 accepted georgia tech cs phd program offer mar 2023 recived cs phd program admits from stanford georgia tech ut austin and simon fraser university mar 2023 our work hm3dsem is accepted as highlight paper top 2 5 of submissions at cvpr 2023 feb 2023 2 papers pirlnav and hm3dsem accepted at cvpr 2023 jan 2023 preprint of our paper pirlnav is out on arxiv oct 2022 preprint of our paper habitat matterport 3d semantics dataset is out on arxiv oct 2022 runners up of the habitat challenge 2022 organized at cvpr 2022 presentation available here may 2022 interning at mitsubishi electric research laboratories apr 2022 preprint of our paper offline visual representation learning for embodied navigation is out on arxiv apr 2022 awarded the college of computing outstanding ms research award 2022 mar 2022 our paper habitat web accepted at cvpr 2022 aug 2021 joined georgia tech for masters in computer science jun 2021 runners up of the habitat challenge 2021 organized at cvpr 2021 presentation available here oct 2020 represented cloudcv at google summer of code mentor summit 2020 jun 2020 joined as a research intern at machine learning and perception lab at georgia tech to work with prof dhruv batra prof devi parikh apr 2020 served as a google summer of code 2020 mentor with cloudcv nov 2019 served as a google code in 2019 organization administrator with cloudcv oct 2019 fabrik accepted at ai systems workshop at sosp conference aug 2019 started as a software development engineer 2 at glance apr 2019 served as a google summer of code mentor with cloudcv nov 2018 served as a google code in 2018 mentor with cloudcv jul 2018 started as a software development engineer at inmobi may 2018 selected as a google summer of code student with cloudcv read more bio i am a research scientist at mistral ai and final year phd student in the department of computer science at georgia tech advised by prof dhruv batra and prof zsolt kira prior to this i completed my masters in cs at georgia tech advised by prof dhruv batra and abhishek das i also closely collaborated with erik wijmans during my time as a ms student i am interested in building general purpose multi modal llm agents that can reason and act to solve complex long horizon tasks that require few hours to days of work currently i work on scaling reinforcement learning rl infrastructure interaction data and environments required to post train capable multi modal llms agents my area of expertise are rl multi modal llm agents synthetic data curation and simulation mistral ai spring 2025 current apple ml research spring 2025 meta ai research summer 2024 allen insitute of ai ai2 summer 2023 georgia tech 2021 2025 pune institute of computer technology 2015 2018 i have been fortunate to intern at apple mlr with alexander toshev from spring to summer 2025 on scaling synthetic data generation for post training mllm agents in summer 2024 i interned at meta fair working with roozbeh mottaghi on post training vla policies using reinforcement learning in summer 2023 i interned at allen institute of ai ai2 with luca weihs and kuo hao zheng on synthetic data generation for visual common sense reasoning in 2022 i was an intern at mitsubishi electric research laborateries merl with anoop cherian working on scene representations for embodied agents if you have any questions want to collaborate discuss research feel free to send me an email at ram ramrakhya gatech edu selected publications scaling synthetic task generation for agents via exploration ram ramrakhya andrew szot omar attia yuhao yang anh nguyen bogdan mazoure zhe gan harsh agrawal alexander toshev iclr 2026 paper website grounding multimodal llms to embodied agents that ask for help with reinforcement learning ram ramrakhya matthew chang xavier puig ruta desai zsolt kira roozbeh mottaghi under review paper website goat bench a benchmark for multi modal lifelong navigation mukul khanna ram ramrakhya gunjan chhablani sriram yenamandra theophile gervet matthew chang zsolt kira devendra singh chaplot dhruv batra roozbeh mottaghi cvpr 2024 paper code website seeing the unseen visual common sense for semantic placement ram ramrakhya aniruddha kembhavi dhruv batra zsolt kira kuo hao zeng luca weihs cvpr 2024 vlmnm workshop at icra 24 paper code website pirlnav pretraining with imitation and rl finetuning for objectnav ram ramrakhya dhruv batra erik wijmans abhishek das cvpr 2023 rrl workshop at iclr 2023 paper code website habitat web learning embodied object search strategies from human demonstrations at scale ram ramrakhya eric undersander dhruv batra abhishek das cvpr 2022 embodiedai workshop at cvpr 2022 overlooked aspects of il workshop at rss 2022 spotlight paper code website presentation video all publications ferret ui lite lessons from building small on device gui agents zhen yang zi yi dou di feng forrest huang anh tuan nguyen keen you omar attia yuhao yang michael feng haotian zhang ram ramrakhya chao jia jeffrey nichols alexander toshev yinfei yang zhe gan under review paper ultracua scaling computer use agent through gui and programmatic control yuhao yang zhen yang zi yi dou anh tuan nguyen omar attia andrew szot keen you michael feng ram ramrakhya alexander toshev chao huang yinfei yang zhe gan under review paper partnr a benchmark for planning and reasoning in embodied multi agent tasks matthew chang gunjan chhablani alexander clegg mikael dallaire cote ruta desai michal hlavac vladimir karashchuk jacob krantz roozbeh mottaghi priyam parashar siddharth patki ishita prasad xavier puig akshara rai ram ramrakhya daniel tran joanne truong john m turner eric undersander tsung yen yang iclr 2025 website paper code relic a recipe for 64k steps in context reinforcement learning for embodied ai ahmad elawady gunjan chhablani ram ramrakhya karmesh yadav dhruv batra zsolt kira andrew szot under review paper code hm3d ovon a dataset and benchmark for open vocabulary object goal navigation naoki yokoyama ram ramrakhya abhishek das dhruv batra sehoon ha iros 24 paper code website habitat matterport 3d semantics dataset karmesh yadav ram ramrakhya santhosh kumar ramakrishnan theo gervet john turner aaron gokaslan noah maestre angel xuan chang dhruv batra manolis savva alexander william clegg devendra singh chaplot cvpr 2023 highlight top 2 5 of submissions paper website ovrl v2 a simple state of art baseline for imagenav and objectnav karmesh yadav arjun majumdar ram ramrakhya naoki yokoyama aleksei baevski zsolt kira oleksandr makysmets dhruv batra arxiv paper offline visual representation learning for embodied navigation karmesh yadav ram ramrakhya arjun majumdar vincent pierre berges sachit kuhar dhruv batra aleksei baevski oleksandr makysmet rrl workshop at iclr 2023 paper fabrik an online collaborative neural network editor utsav garg viraj prabhu deshraj yadav ram ramrakhya harsh agarwal dhruv batra workshop on ai systems sosp 2019 paper code projects evalai leading open source platform for evaluating and benchmarking ai models we have hosted 200 ai challenges with 18 000 users who have created 180 000 submissions more than 30 organizations from industry and academia use it for hosting their ai challenges the project is open source with 130 contributors and 2m yearly pageviews some of the organizations using it are google research facebook ai research deepmind amazon ebay research mapillary research etc and research labs from mit stanford carnegie mellon university georgia tech virginia tech umbc university of pittsburg draper university of adelaide iit madras nankai university etc also use it to host large ai challenges like alexaprize on it it s forked versions are used by large organizations such as world health organization forschungszentrum jülich one of the largest interdisciplinary research centres in europe etc for hosting their challenges instead of reinventing the wheel fabrik fabrik is an online collaborative platform to build visualize and train deep learning models via a simple drag and drop interface it allows researchers to collectively develop and debug models using a web gui that supports importing editing and exporting networks to popular frameworks like caffe keras and tensorflow courtesy abhishek das