René's URL Explorer Experiment


Title: Pulkit Agrawal

Mail addresses
pulkitag@mit.edu

direct link

Domain: people.csail.mit.edu

Nonetext/html; charset=UTF-8
authorPulkit Agrawal

Links:

MIThttps://www.mit.edu
Eka Roboticshttps://www.ekarobotics.com
CSAILhttps://www.csail.mit.edu/
LIDShttps://lids.mit.edu/
SafelyYou Inc.https://www.safely-you.com/
Tutor Intelligencehttps://www.tutorintelligence.com/
Follow @pulkitologyhttps://twitter.com/pulkitology?ref_src=twsrc%5Etfw
LinkedIn https://www.linkedin.com/in/pulkit-agrawal-967a4218/
CVhttp://people.csail.mit.edu/pulkitag/data/pulkit_CV_current.pdf
Biographyhttp://people.csail.mit.edu/pulkitag/data/pulkit-bio.txt
Google Scholarhttps://scholar.google.com/citations?user=UpZmJI0AAAAJ&hl=en
http://people.csail.mit.edu/pulkitag/images/pulkit.jpg
Ph.D. Thesis (Computational Sensorimotor Learning)http://www2.eecs.berkeley.edu/Pubs/TechRpts/2018/EECS-2018-133.pdf
Thesis Talkhttps://youtu.be/opsQndkSw5k
Bibtexhttp://people.csail.mit.edu/pulkitag/data/agrawal2018computational.bib
TEDxMIT Talk: https://www.youtube.com/watch?v=LPGGIdxOmWI
Computational Sensorimotor Learning https://pulkitag.github.io/6.8200/
FA'19http://manipulation.csail.mit.edu/Fall2019/
Summer'24 https://professional.mit.edu/course-catalog/advanced-reinforcement-learning-0
Summer'24 https://professional.mit.edu/course-catalog/reinforcement-learning
Summer'24 https://professional.mit.edu/course-catalog/ai-robotics-learning-algorithms-design-and-safety
IEEE Early Academic Career Award in Robotics and Automation https://www.ieee-ras.org/awards-recognition/society-awards/ras-early-career-award-academic
Best Paper Award https://sites.google.com/robot-learning.org/corl2021/program/awards_2021?authuser=0
in-hand object re-orientationhttps://taochenshh.github.io/projects/in-hand-reorientation#
Haoshu Fang https://fang-haoshu.github.io/
Branden Romero https://scholar.google.com/citations?user=0lns2BAAAAAJ&hl=en
Antonia Bronars https://tonibronars.github.io/
Ryan Bahlous-Boldi https://ryanboldi.github.io/
Navodita Sharma https://scholar.google.com/citations?user=hcsR-tMAAAAJ&hl=en
Gabe Margolishttps://gmargo11.github.io/about/
Nolan Fey https://www.linkedin.com/in/nolan-fey
Younghyo Park https://younghyopark.me/
Jyothish Pari https://jyopari.github.io/aboutMe.html
Idan Shenfeld https://idanshen.github.io/
Richard Li https://richardrl.github.io/
Martin Peticco https://mfpeticco.github.io/about.html
Nitish Dashora https://www.nitishdashora.com/
Seungwook Han https://scholar.google.com/citations?user=B6tpjKkAAAAJ&hl=en
Pathway to Robotic Intelligence https://www.youtube.com/watch?v=-ghQJNmStB4
Making Robots as Intelligent as ChatGPThttps://www.forbes.com/video/6335581924112/making-robots-as-intelligent-as-chatgpt/
Robot Learning for the Real World, https://www.cs.utexas.edu/~ai-lab/fai/?year=2022-2023#Pulkit%20Agrawal
Fun with Robots and Machine Learning https://www.youtube.com/watch?v=6NDWSxV7H3o
Navigating Through Contacts https://www.youtube.com/watch?v=jU7pkiv3x0E&list=PLxHmBiQi0bD34kaBxcO9ENkvL7sWafvGt&index=11
Coming of Age of Robot learning https://www.youtube.com/watch?v=ym-mrmOqOYg
Rethinking Robot Learning https://www.youtube.com/watch?v=C6LRBs27pG4&t=60s
Self-Supervised Robot Learning, Robotics Seminar,https://youtu.be/MDCkBRh0D1U
Challenges in Real-World Reinforcement Learninghttps://youtu.be/1OSaTZB3WVY?t=565
The Task Specification Problemhttps://www.youtube.com/watch?v=2el3GdwS1mg
https://arxiv.org/abs/2601.19897
Self-Distillation Enables Continual Learning https://arxiv.org/abs/2601.19897
Idan Shenfeldhttps://idanshenfeld.com
Mehul Damanihttps://damanimehul.github.io/
Jonas Hübotterhttps://jonhue.github.io/
paperhttps://arxiv.org/abs/2601.19897
project pagehttps://self-distillation.github.io/SDFT
bibtexhttp://people.csail.mit.edu/pulkitag/data/shenfeld2026self.bib
https://arxiv.org/abs/2510.17792
SoftMimic: Learning Compliant Whole-body Control from Examples https://arxiv.org/abs/2510.17792
Gabriel B. Margolis*https://gmargo11.github.io/
Michelle Wang*https://engineering.mit.edu/people/michelle-wang
Nolan Feyhttps://nolie-rolie.github.io/
paperhttps://arxiv.org/abs/2510.17792
project pagehttps://gmargo11.github.io/softmimic/
bibtexhttp://people.csail.mit.edu/pulkitag/data/margolis2025softmimic.bib
https://arxiv.org/abs/2509.04441
DEXOP: A Device for Robotic Transfer of Dexterous Human Manipulation https://arxiv.org/abs/2509.04441
paperhttps://arxiv.org/abs/2509.04441
project pagehttps://dex-op.github.io/
bibtexhttp://people.csail.mit.edu/pulkitag/data/fang2025dexop.bib
https://arxiv.org/abs/2507.01008
DexWrist: A Robotic Wrist for Constrained and Dynamic Manipulation https://arxiv.org/abs/2507.01008
paperhttps://arxiv.org/abs/2507.01008
project pagehttps://dexwrist.csail.mit.edu
bibtexhttp://people.csail.mit.edu/pulkitag/data/peticco2025dexwrist.bib
https://arxiv.org/abs/2411.00704
Learning to Look Around: Enhancing Teleoperation and Learning with a Human-like Actuated Neck https://arxiv.org/abs/2411.00704
paperhttps://arxiv.org/abs/2411.00704
bibtexhttp://people.csail.mit.edu/pulkitag/data/sen2024learning.bib
https://arxiv.org/abs/2411.02207
Collective model intelligence requires compatible specialization https://arxiv.org/abs/2411.02207
paperhttps://arxiv.org/abs/2411.02207
project pagehttps://jyopari.notion.site/compatible-specialization
codehttps://github.com/jyopari/compatible_specialization
bibtexhttp://people.csail.mit.edu/pulkitag/data/pari2024collective.bib
https://arxiv.org/abs/2411.18676
Embodied Red Teaming for Auditing Robotic Foundation Models https://arxiv.org/abs/2411.18676
paperhttps://arxiv.org/abs/2411.18676
project pagehttps://s-karnik.github.io/embodied-red-team-project-page/
codehttps://github.com/Improbable-AI/embodied-red-teaming
bibtexhttp://people.csail.mit.edu/pulkitag/data/sathwick2024redteaming.bib
https://arxiv.org/abs/2502.10894
RL's Razor: Why Online Reinforcement Learning Forgets Less https://arxiv.org/abs/2509.04259
Idan Shenfeldhttps://www.idanshenfeld.com/
Jyothish Parihttps://jyopari.github.io/
paperhttps://arxiv.org/abs/2509.04259
project pagehttps://jyopari.github.io/posts/rl_razor
bibtexhttp://people.csail.mit.edu/pulkitag/data/shenfeldrlrazor.bib
https://openreview.net/pdf?id=JsNUE84Hxi
Self-Adapting Language Models https://openreview.net/pdf?id=JsNUE84Hxi
Adam Zweigerhttps://adamzweiger.github.io/
Jyothish Parihttps://jyopari.github.io/
Han Guohttps://han-guo.info/
Ekin Akyürekhttps://ekinakyurek.github.io/
Yoon Kimhttps://people.csail.mit.edu/yoonkim/
paperhttps://openreview.net/pdf?id=JsNUE84Hxi
project pagehttps://jyopari.github.io/posts/seal
bibtexhttp://people.csail.mit.edu/pulkitag/data/zweiger2025seal.bib
paperhttps://www.nature.com/articles/s41586-025-09640-5
bibtexhttp://people.csail.mit.edu/pulkitag/data/zhang2025multimodal.bib
https://arxiv.org/abs/2503.06358
Language Model Personalization via Reward Factorization https://arxiv.org/abs/2503.06358
Idan Shenfeld*https://idanshenfeld.com
Felix Faltings*https://www.linkedin.com/in/felix-faltings-73b886127/
Aldo Pacchianohttps://www.aldopacchiano.ai/
paperhttps://arxiv.org/abs/2503.06358
bibtexhttp://people.csail.mit.edu/pulkitag/data/shenfeld2025language.bib
https://arxiv.org/abs/2502.10894
Bridging the Sim-to-Real Gap for Athletic Loco-Manipulation https://arxiv.org/abs/2502.10894
Nolan Feyhttps://nolie-rolie.github.io/
Gabriel B. Margolishttps://gmargo11.github.io/
Martin Peticcohttps://mfpeticco.github.io/about.html
paperhttps://arxiv.org/pdf/2502.10894
project pagehttps://uan.csail.mit.edu/
bibtexhttp://people.csail.mit.edu/pulkitag/data/fey2025bridging.bib
https://arxiv.org/abs/2412.01770
Robot Learning with Super-Linear Scaling https://arxiv.org/abs/2412.01770
paperhttps://arxiv.org/abs/2412.01770
project pagehttps://casher-robot-learning.github.io/CASHER/
bibtexhttp://people.csail.mit.edu/pulkitag/data/torne2025robot.bib
https://arxiv.org/abs/2502.19402
General Intelligence Requires Reward-Based Pretraining https://arxiv.org/abs/2502.19402
paperhttps://arxiv.org/abs/2502.19402
project pagehttps://improbableai.notion.site/General-Intelligence-Requires-Reward-Based-Pretraining-2023b66e4cf580d3ab44c7860b75d25f
bibtexhttp://people.csail.mit.edu/pulkitag/data/han2025general.bib
https://openreview.net/pdf?id=0ysC6VS0y3
Emergence and Effectiveness of Task Vectors in In-Context Learning: An Encoder Decoder Perspective https://openreview.net/pdf?id=0ysC6VS0y3
paperhttps://openreview.net/pdf?id=0ysC6VS0y3
bibtexhttp://people.csail.mit.edu/pulkitag/data/han2025emergence.bib
https://residual-assembly.github.io/
paperhttps://arxiv.org/abs/2411.02214
bibtexhttp://people.csail.mit.edu/pulkitag/data/ankile2024resip.bib
https://residual-assembly.github.io/
From Imitation to Refinement – Residual RL for Precise Visual Assembly https://residual-assembly.github.io/
paperhttps://arxiv.org/abs/2407.16677
project pagehttps://residual-assembly.github.io/
codehttps://github.com/ankile/robust-rearrangement
bibtexhttp://people.csail.mit.edu/pulkitag/data/ankile2024resip.bib
https://taochenshh.github.io/projects/veg-peeling
Tao Chenhttps://taochenshh.github.io/
Eric Cousineauhttps://www.eacousineau.com/
Naveen Kuppuswamyhttps://naveenoid.wordpress.com/
paperhttps://arxiv.org/abs/2407.07884
project pagehttps://taochenshh.github.io/projects/veg-peeling
bibtexhttp://people.csail.mit.edu/pulkitag/data/chen2025vegetable.bib
paperhttps://arxiv.org/pdf/2502.12355
bibtexhttp://people.csail.mit.edu/pulkitag/data/hsuan2025hovering.bib
https://arxiv.org/abs/2502.10894
ORSO: Accelerating Reward Design via Online Reward Selection and Policy Optimization https://arxiv.org/abs/2502.10894
Chen Bo Calvin Zhanghttps://nolie-rolie.github.io/
Zhang-Wei Honghttps://gmargo11.github.io/
Aldo Pacchianohttps://mfpeticco.github.io/about.html
paperhttps://arxiv.org/pdf/2410.13837
bibtexhttp://people.csail.mit.edu/pulkitag/data/zhang2025orso.bib
https://arxiv.org/abs/2412.12953
Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning https://arxiv.org/abs/2412.12953
Moritz Reuss*https://mbreuss.github.io/
Jyo Pari*https://jyopari.github.io/
Rudolf Lioutikov https://rudolf.intuitive-robots.net/
paperhttps://arxiv.org/abs/2412.12953
bibtexhttp://people.csail.mit.edu/pulkitag/data/reuss2025efficient.bib
https://arxiv.org/abs/2409.00588
Diffusion Policy Policy Optimization https://arxiv.org/abs/2409.00588
paperhttps://arxiv.org/pdf/2409.00588
codehttps://github.com/irom-lab/dppo
bibtexhttp://people.csail.mit.edu/pulkitag/data/ren2025diffusionpolicy.bib
https://arxiv.org/abs/2502.05970
Known Unknowns: Out-of-Distribution Property Prediction in Materials and Molecules https://arxiv.org/abs/2502.05970
paperhttps://arxiv.org/abs/2502.05970
codehttps://github.com/learningmatter-mit/matex
bibtexhttp://people.csail.mit.edu/pulkitag/data/segal2024known.bib
https://www.nature.com/articles/s41746-025-01709-9
A distributional reinforcement learning model for optimal glucose control after cardiac surgery https://www.nature.com/articles/s41746-025-01709-9
paperhttps://www.nature.com/articles/s41746-025-01709-9
bibtexhttp://people.csail.mit.edu/pulkitag/data/desman2025distributional.bib
paperhttps://pubmed.ncbi.nlm.nih.gov/40420108/
bibtexhttp://people.csail.mit.edu/pulkitag/data/oh2025orakle.bib
https://eyesighthand.github.io/
EyeSight Hand: Design of a Fully-Actuated Dexterous Robot Hand with Integrated Vision-Based Tactile Sensors and Compliant Actuation https://eyesighthand.github.io/
paperhttps://arxiv.org/abs/2408.06265
project pagehttps://eyesighthand.github.io/
bibtexhttp://people.csail.mit.edu/pulkitag/data/romero2024eyesight.bib
http://arxiv.org/abs/2403.03949
Reconciling Reality through Simulation: A Real-To-Sim-to-Real Approach for Robust Manipulation http://arxiv.org/abs/2403.03949
paperhttp://arxiv.org/abs/2403.03949
project pagehttps://real-to-sim-to-real.github.io/RialTo/
bibtexhttp://people.csail.mit.edu/pulkitag/data/torne2024reconciling.bib
https://arxiv.org/abs/2411.04987
Few-Shot Task Learning through Inverse Generative Modeling https://arxiv.org/abs/2411.04987
paperhttps://arxiv.org/abs/2411.04987
project pagehttps://avivne.github.io/ftl-igm/
codehttps://github.com/avivne/ftl-igm/tree/main/code
bibtexhttp://people.csail.mit.edu/pulkitag/data/netanyahu2024few-shot.bib
https://arxiv.org/abs/2406.00681
Learning Multimodal Behaviors from Scratch with Diffusion Policy Gradient https://arxiv.org/abs/2406.00681
paperhttps://arxiv.org/abs/2406.00681
bibtexhttp://people.csail.mit.edu/pulkitag/data/li2024learning.bib
paperhttps://openreview.net/pdf?id=vBGMbFgvsX
codehttps://github.com/Improbable-AI/hepo
bibtexhttp://people.csail.mit.edu/pulkitag/data/lee2024going.bib
https://arxiv.org/abs/2407.13755
Position: Automatic Environment Shaping is the Next Frontier in RL https://arxiv.org/pdf/2407.16186
Younghyo Park*https://younghyopark.me/
Gabriel Margolis*https://gmargo11.github.io/
paperhttps://arxiv.org/pdf/2407.16186
project pagehttps://auto-env-shaping.github.io/
bibtexhttp://people.csail.mit.edu/pulkitag/data/park2024automatic.bib
https://arxiv.org/abs/2407.13755
Random Latent Exploration for Deep Reinforcement Learning https://arxiv.org/abs/2407.13755
Srinath Mahankalihttps://srinathm1359.github.io/
Zhang-Wei Honghttps://williamd4112.github.io/
Ayush Sekharihttps://ayush.sekhari.com/
Alexander Rakhlinhttps://www.mit.edu/~rakhlin/
paperhttps://arxiv.org/abs/2407.13755
project pagehttps://srinathm1359.github.io/random-latent-exploration/
codehttps://github.com/Improbable-AI/random-latent-exploration
bibtexhttp://people.csail.mit.edu/pulkitag/data/mahankali2024random.bib
https://arxiv.org/abs/2205.02824
Rapid Locomotion via Reinforcement Learning https://arxiv.org/abs/2205.02824
paperhttps://arxiv.org/abs/2205.02824
project pagehttps://agility.csail.mit.edu
codehttps://github.com/Improbable-AI/rapid-locomotion-rl
bibtexhttp://people.csail.mit.edu/pulkitag/data/margolis2024rapid.bib
https://minyoungg.github.io/LTE/
Training Neural Networks From Scratch with Parallel Low-Rank Adapters https://arxiv.org/abs/2402.16828
paperhttps://arxiv.org/abs/2402.16828
project pagehttps://minyoungg.github.io/LTE/
bibtexhttp://people.csail.mit.edu/pulkitag/data/huh2024training.bib
https://arxiv.org/abs/2405.06639
Value Augmented Sampling for Language Model Alignment and Personalization https://arxiv.org/abs/2405.06639
paperhttps://arxiv.org/abs/2405.06639
bibtexhttp://people.csail.mit.edu/pulkitag/data/han2024value.bib
https://dl.acm.org/doi/pdf/10.1145/3610977.3634987
Aligning human and robot representations https://dl.acm.org/doi/pdf/10.1145/3610977.3634987
paperhttps://dl.acm.org/doi/pdf/10.1145/3610977.3634987
bibtexhttp://people.csail.mit.edu/pulkitag/data/bobu2024aligning.bib
https://open-eqa.github.io/assets/pdfs/paper.pdf
OpenEQA: Embodied question answering in the era of foundation models https://open-eqa.github.io/assets/pdfs/paper.pdf
paperhttps://open-eqa.github.io/assets/pdfs/paper.pdf
project pagehttps://open-eqa.github.io/
bibtexhttp://people.csail.mit.edu/pulkitag/data/majumdar2024openaqa.bib
https://arxiv.org/abs/2309.14321
Lifelong Robot Learning with Human Assisted Language Planners https://arxiv.org/abs/2309.14321
paperhttps://arxiv.org/abs/2309.14321
project pagehttps://sites.google.com/mit.edu/halp-robot-learning
bibtexhttp://people.csail.mit.edu/pulkitag/data/parakh2024lifelong.bib
http://arxiv.org/abs/2405.01402.pdf
Learning Force Control for Legged Manipulation http://arxiv.org/abs/2405.01402
paperhttp://arxiv.org/abs/2405.01402.pdf
project page https://tif-twirl-13.github.io/learning-compliance
bibtexhttp://people.csail.mit.edu/pulkitag/data/portela2024learning.bib
http://arxiv.org/abs/2405.01402.pdf
Curiosity-driven Red-teaming for Large Language Models http://arxiv.org/abs/2405.01402
paperhttps://arxiv.org/pdf/2402.19464.pdf
codehttps://github.com/Improbable-AI/curiosity_redteam
bibtex http://people.csail.mit.edu/pulkitag/bibtex/hong2024curiosity.bib
https://openreview.net/pdf?id=GGuNkjQSrk
Action Space Design in Reinforcement Learning for Robot Motor Skills https://openreview.net/pdf?id=GGuNkjQSrk
paperhttps://openreview.net/pdf?id=GGuNkjQSrk
bibtexhttp://people.csail.mit.edu/pulkitag/data/esser2024action.bib
https://ieeexplore.ieee.org/abstract/document/10609983
Maximizing Quadruped Velocity by Minimizing Energy https://ieeexplore.ieee.org/abstract/document/10609983
Srinath Mahankali*https://srinathm1359.github.io/
Chi-Chang Lee*https://dblp.org/pid/258/6861.html
Gabriel B. Margolishttps://gmargo11.github.io/
Zhang-Wei Honghttps://williamd4112.github.io/
paperhttps://ieeexplore.ieee.org/abstract/document/10609983
project pagehttps://srinathm1359.github.io/eipo-locomotion/
bibtexhttp://people.csail.mit.edu/pulkitag/data/mahankali2024maximizing.bib
https://imitation-juicer.github.io/
JUICER: Data-Efficient Imitation Learning for Robotic Assembly https://imitation-juicer.github.io/
paperhttps://arxiv.org/abs/2404.03729
project pagehttps://imitation-juicer.github.io/
codehttps://github.com/ankile/imitation-juicer
bibtexhttp://people.csail.mit.edu/pulkitag/data/ankile2024juicer.bib
https://openreview.net/pdf?id=cT8oOJ6Q6F
Grid Cell-Inspired Fragmentation and Recall for Efficient Map Building https://openreview.net/pdf?id=cT8oOJ6Q6F
paperhttps://openreview.net/pdf?id=cT8oOJ6Q6F
bibtexhttp://people.csail.mit.edu/pulkitag/data/hwang2024grid.bib
https://arxiv.org/pdf/2407.03995
ROER: Regularized Optimal Experience Replay https://arxiv.org/pdf/2407.03995
paperhttps://arxiv.org/pdf/2407.03995
bibtexhttp://people.csail.mit.edu/pulkitag/data/hwang2024roer.bib
https://rank2reward.github.io/
Rank2Reward: Learning Shaped Reward Functions from Passive Video https://rank2reward.github.io/
paperhttps://arxiv.org/abs/2404.14735
project pagehttps://rank2reward.github.io/
codehttps://github.com/ankile/imitation-juicer
bibtexhttp://people.csail.mit.edu/pulkitag/data/yang2024rank.bib
https://arxiv.org/abs/2408.04142
Everyday finger: a robotic finger that meets the needs of everyday interactive manipulation https://arxiv.org/abs/2408.04142
paperhttps://arxiv.org/abs/2408.04142
project pagehttps://sites.google.com/view/everydayfinger/
bibtexhttp://people.csail.mit.edu/pulkitag/data/ornelas2024everyday.bib
https://openreview.net/forum?id=7uSBJDoP7tY
Visual Dexterity: In-Hand Reorientation of Novel and Complex Object Shapes https://taochenshh.github.io/projects/visual-dexterity
Tao Chenhttps://taochenshh.github.io/
Vikash Kumarhttps://vikashplus.github.io/
Edward Adelsonhttp://persci.mit.edu/people/adelson
paper https://arxiv.org/abs/2211.11744
project pagehttps://taochenshh.github.io/projects/visual-dexterity
bibtex http://people.csail.mit.edu/pulkitag/data/chen2023visual.bib
https://browse.arxiv.org/pdf/2309.08587.pdf
Compositional Foundation Models for Hierarchical Planning https://browse.arxiv.org/pdf/2309.08587.pdf
paperhttps://browse.arxiv.org/pdf/2309.08587.pdf
project page https://hierarchical-planning-foundation-model.github.io/
http://people.csail.mit.edu/pulkitag/
bibtexhttp://people.csail.mit.edu/pulkitag/data/ajay2023compositional.bib
https://browse.arxiv.org/pdf/2307.11049.pdf
Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-Loop Feedback https://browse.arxiv.org/pdf/2307.11049.pdf
paperhttps://browse.arxiv.org/pdf/2307.11049.pdf
project pagehttps://human-guided-exploration.github.io/HuGE/
codehttps://github.com/Improbable-AI/human-guided-exploration
bibtex http://people.csail.mit.edu/pulkitag/data/torne2023breadcrumbs.bib
https://arxiv.org/pdf/2310.04413.pdf
Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets http://people.csail.mit.edu/pulkitag/
paperhttps://arxiv.org/pdf/2310.04413.pdf
bibtexhttp://people.csail.mit.edu/pulkitag/data/hong2023beyond.bib
code https://github.com/Improbable-AI/dw-offline-rl
https://proceedings.neurips.cc/paper_files/paper/2023/hash/b048dd19ba6d85b9066aa93b4de9ad4a-Abstract-Conference.html
Self-Supervised Reinforcement Learning that Transfers using Random Features https://proceedings.neurips.cc/paper_files/paper/2023/hash/b048dd19ba6d85b9066aa93b4de9ad4a-Abstract-Conference.html
paperhttps://proceedings.neurips.cc/paper_files/paper/2023/hash/b048dd19ba6d85b9066aa93b4de9ad4a-Abstract-Conference.html
bibtexhttp://people.csail.mit.edu/pulkitag/data/chen2023self.bib
https://arxiv.org/abs/2307.04751
Shelving, Stacking, Hanging: Relational Pose Diffusion for Multi-modal Rearrangement https://arxiv.org/abs/2307.04751
paperhttps://arxiv.org/abs/2307.04751
project pagehttps://anthonysimeonov.github.io/rpdiff-multi-modal/
codehttps://github.com/anthonysimeonov/rpdiff
bibtexhttp://people.csail.mit.edu/pulkitag/data/simeonov2023shelving.bib
https://arxiv.org/abs/2311.01405
Learning to See Physical Properties with Active Sensing Motor Policies https://arxiv.org/abs/2311.01405
paperhttps://arxiv.org/abs/2311.01405
project pagehttps://gmargo11.github.io/active-sensing-loco
bibtexhttp://people.csail.mit.edu/pulkitag/
Visual Pre-training for Navigation: What Can We Learn from Noise? https://yanweiw.github.io/noise2ptz/
paperhttps://arxiv.org/abs/2207.00052
codehttps://github.com/yanweiw/noise2ptz
project pagehttps://yanweiw.github.io/noise2ptz
bibtex http://people.csail.mit.edu/pulkitag/data/wang2023visual.bib
https://openreview.net/pdf?id=z3D__-nc9y
Autonomous Robotic Reinforcement Learning with Asynchronous Human Feedback https://openreview.net/pdf?id=z3D__-nc9y
paperhttps://openreview.net/pdf?id=z3D__-nc9y
bibtexhttp://people.csail.mit.edu/pulkitag/data/pamies2023autonomous.bib
https://arxiv.org/abs/2307.03186.pdf
TGRL: An Algorithm for Teacher Guided Reinforcement Learning https://arxiv.org/abs/2307.03186
paperhttps://arxiv.org/abs/2307.03186
code https://github.com/idanshen/cleanrl/blob/master/cleanrl/tgrl_continuous_action.py
project page https://sites.google.com/view/tgrl-paper/
bibtexhttp://people.csail.mit.edu/pulkitag/data/shenfeld2023tgrl.bib
https://minyoungg.github.io/vqtorch/
Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks https://minyoungg.github.io/vqtorch/
paperhttps://arxiv.org/abs/2305.08842
website https://minyoungg.github.io/vqtorch/
code https://github.com/minyoungg/vqtorch
bibtexhttp://people.csail.mit.edu/pulkitag/data/huh2023straightening.bib
https://arxiv.org/abs/2307.12983
https://arxiv.org/abs/2307.12983
Parallel Q-Learning: Scaling Off-policy Reinforcement Learning under Massively Parallel Simulation https://arxiv.org/abs/2307.12983
Zechu Li*https://supersglzc.github.io/
Tao Chen*https://taochenshh.github.io/
Zhang-Wei Honghttps://williamd4112.github.io/
Anurag Ajayhttps://anuragajay.github.io/
paperhttps://arxiv.org/abs/2307.12983
codehttps://github.com/Improbable-AI/pql
bibtex http://people.csail.mit.edu/pulkitag/data/li2023parallel.bib
https://arxiv.org/pdf/2307.06333.pdf
Diagnosis, Feedback, Adaptation: A Human-in-the-Loop Framework for Test-Time Policy Adaptation https://arxiv.org/pdf/2307.06333.pdf
paperhttps://arxiv.org/pdf/2307.06333.pdf
project pagehttps://andipeng.com/counterfactual-adaptation/
bibtexhttp://people.csail.mit.edu/pulkitag/data/peng2023diagnosis.bib
https://browse.arxiv.org/pdf/2302.13934.pdf
Statistical Learning under Heterogenous Distribution Shift https://browse.arxiv.org/pdf/2302.13934.pdf
paperhttps://browse.arxiv.org/pdf/2302.13934.pdf
bibtexhttp://people.csail.mit.edu/pulkitag/data/simchowitz2023statistical.bib
https://gmargo11.github.io/dribblebot
DribbleBot: Dynamic Legged Manipulation in the Wild https://gmargo11.github.io/dribblebot
Yandong Ji*https://yandongji.github.io/
Gabriel B. Margolis*https://gmargo11.github.io/
paperhttps://arxiv.org/abs/2304.01159
project pagehttps://gmargo11.github.io/dribblebot
bibtexhttp://people.csail.mit.edu/pulkitag/data/ji2023dribblebot.bib
TechCrunchhttps://techcrunch.com/2023/04/03/this-robot-dog-can-play-soccer-and-grass-mud-and-sand/
IEEE Spectrumhttps://spectrum.ieee.org/quadrupedal-robot
NBC Bostonhttps://archive.tveyes.com/7313/meltwater/3fa732c9-740b-4602-a9e6-f9b44988c02b/WBTS_04-04-2023_04.55.00.mp4
Insiderhttps://www.businessinsider.com/mit-robot-that-can-play-soccer-dribble-ball-video-2023-4
Yahoo!Newshttps://www.yahoo.com/lifestyle/robots-getting-good-dribbling-soccer-163646616.html
MIT Newshttps://news.mit.edu/2023/legged-robotic-system-playing-soccer-various-terrains-0403
https://taochenshh.github.io/projects/tactofind
TactoFind: A Tactile Only System for Object Retrieval https://taochenshh.github.io/projects/tactofind
Edward Adelsonhttp://persci.mit.edu/people/adelson
Abhishek Gupta†https://homes.cs.washington.edu/~abhgupta/
paperhttps://arxiv.org/abs/2303.13482
project pagehttps://taochenshh.github.io/projects/tactofind
bibtexhttp://people.csail.mit.edu/pulkitag/data/pai2023tactofind.bib
Is Conditional Generative Modeling all you need for Decision Making? https://arxiv.org/pdf/2211.15657.pdf
paperhttps://arxiv.org/pdf/2211.15657.pdf
project pagehttps://anuragajay.github.io/decision-diffuser/
bibtexhttp://people.csail.mit.edu/pulkitag/data/ajay2023is.bib
https://arxiv.org/abs/2304.14329
Learning to Extrapolate: A Transductive Approach https://arxiv.org/abs/2304.14329
paperhttps://arxiv.org/abs/2304.14329
bibtexhttp://people.csail.mit.edu/pulkitag/data/netanyahu2023learning.bib
https://openreview.net/forum?id=OhUAblg27z
Harnessing Mixed Offline Reinforcement Learning Datasets via Trajectory Weighting https://openreview.net/forum?id=OhUAblg27z
paperhttps://openreview.net/forum?id=OhUAblg27z
bibtexhttp://people.csail.mit.edu/pulkitag/data/hong2023harness.bib
https://minyoungg.github.io/overparam/
The Low-Rank Simplicity Bias in Deep Networks https://minyoungg.github.io/overparam/
paperhttps://minyoungg.github.io/overparam/resources/overparam-v3.pdf
website https://minyoungg.github.io/overparam/
bibtexhttp://people.csail.mit.edu/pulkitag/data/huh2023low.bib
https://sites.google.com/view/neurips22-eipo/
Redeeming Intrinsic Rewards via Constrained Optimization https://sites.google.com/view/neurips22-eipo/
paperhttps://arxiv.org/abs/2211.07627
project pagehttps://sites.google.com/view/neurips22-eipo/
bibtexhttp://people.csail.mit.edu/pulkitag/data/chen2022redeeming.bib
MIT Newshttps://news.mit.edu/2022/ensuring-ai-works-with-right-dose-curiosity-1110
SE(3)-Equivariant Relational Rearrangement with Neural Descriptor Fields https://arxiv.org/abs/2211.09786
Anthony Simeonov*https://anthonysimeonov.github.io/
Yilun Du*https://yilundu.github.io/
Lin Yen-Chenhttps://yenchenlin.me/
Alberto Rodriguezhttp://meche.mit.edu/people/faculty/ALBERTOR@MIT.EDU
Leslie P. Kaelblinghttps://people.csail.mit.edu/lpk/
Tomás Lozano-Perézhttps://people.csail.mit.edu/tlp/
paperhttps://arxiv.org/abs/2211.09786
project pagehttps://anthonysimeonov.github.io/r-ndf/
codehttps://github.com/anthonysimeonov/relational_ndf
bibtexhttp://people.csail.mit.edu/pulkitag/data/simeonov2022se.bib
https://sites.google.com/view/gait-conditioned-rl/
Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behavior https://sites.google.com/view/gait-conditioned-rl/
Gabriel B. Margolishttps://gmargo11.github.io/about/
paperhttps://openreview.net/pdf?id=52c5e73SlS2
codehttps://github.com/Improbable-AI/walk-these-ways
project pagehttps://sites.google.com/view/gait-conditioned-rl/
bibtexhttp://people.csail.mit.edu/pulkitag/data/margolis2022walk.bib
Distributionally Adaptive Meta Reinforcement Learning https://openreview.net/pdf?id=2ovFjGGDFjc
paperhttps://openreview.net/forum?id=2ovFjGGDFjc
project pagehttps://anuragajay.github.io/diametr/
bibtexhttp://people.csail.mit.edu/pulkitag/data/ajay2022distributionally.bib
http://tactilesim.csail.mit.edu/
Efficient Tactile Simulation with Differentiability for Robotic Manipulation http://tactilesim.csail.mit.edu/
Jie Xuhttps://people.csail.mit.edu/jiex
Sangwoon Kimhttps://sangwkim.github.io/
Tao Chenhttps://taochenshh.github.io/
Alberto Rodriguezhttps://meche.mit.edu/people/faculty/ALBERTOR@MIT.EDU
Wojciech Matusikhttps://people.csail.mit.edu/wojciech/
Shinjiro Suedahttp://faculty.cs.tamu.edu/sueda/
paperhttps://people.csail.mit.edu/jiex/papers/TactileSim/paper.pdf
Code coming soonhttp://people.csail.mit.edu/pulkitag/
project pagehttp://tactilesim.csail.mit.edu/
bibtexhttp://people.csail.mit.edu/pulkitag/data/xu2022efficient.bib
https://arxiv.org/pdf/2203.07359.pdf
Stubborn: A Strong Baseline for Indoor Object Navigation https://arxiv.org/pdf/2203.07359.pdf
paperhttps://arxiv.org/pdf/2203.07359.pdf
codehttps://github.com/Improbable-AI/Stubborn
bibtexhttp://people.csail.mit.edu/pulkitag/data/luo2022stubborn.bib
https://arxiv.org/abs/2112.05124
Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation https://arxiv.org/abs/2112.05124
paperhttps://arxiv.org/abs/2112.05124
website and code https://yilundu.github.io/ndf/
bibtexhttp://people.csail.mit.edu/pulkitag/data/simeonov2021neural.bib
https://arxiv.org/pdf/2204.07149.pdf
An Integrated Design Pipeline for Tactile Sensing Robotic Manipulators https://arxiv.org/pdf/2204.07149.pdf
paperhttps://arxiv.org/pdf/2204.07149.pdf
website http://robohands.csail.mit.edu/
bibtexhttp://people.csail.mit.edu/pulkitag/data/zlokapa2022integrated.bib
https://richardrl.github.io/stable-reorientation/resources/ICRA_2022__Stable_Object_Reorientation_using_Contact_Plane_Registration.pdf
Stable Object Reorientation using Contact Plane Registration https://richardrl.github.io/stable-reorientation/resources/ICRA_2022__Stable_Object_Reorientation_using_Contact_Plane_Registration.pdf
paperhttps://arxiv.org/abs/2208.08962
bibtexhttp://people.csail.mit.edu/pulkitag/data/li2022stable.bib
https://proceedings.mlr.press/v162/netanyahu22a.html
Discovering Generalizable Spatial Goal Representations via Graph-based Active Reward Learning https://proceedings.mlr.press/v162/netanyahu22a.html
paperhttp://people.csail.mit.edu/pulkitag/
bibtexhttp://people.csail.mit.edu/pulkitag/data/netanyahu2022discovering.bib
https://arxiv.org/pdf/2207.02200.pdf
Offline RL Policies Should be Trained to be Adaptive https://arxiv.org/pdf/2207.02200.pdf
paperhttps://arxiv.org/pdf/2207.02200.pdf
bibtexhttp://people.csail.mit.edu/pulkitag/data/ghosh2022offline.bib
https://openreview.net/forum?id=OXRZeMmOI7a
Topological Experience Replay https://openreview.net/forum?id=OXRZeMmOI7a
paperhttps://openreview.net/forum?id=OXRZeMmOI7a
bibtexhttp://people.csail.mit.edu/pulkitag/data/hong2022topological.bib
https://openreview.net/forum?id=LedObtLmCjS
Bilinear Value Networks for Multi-goal Reinforcement Learning https://openreview.net/forum?id=LedObtLmCjS
paperhttps://openreview.net/forum?id=LedObtLmCjS
bibtexhttp://people.csail.mit.edu/pulkitag/data/hong2022bilinear.bib
https://arxiv.org/pdf/2111.00899.pdf
Equivariant Contrastive Learning https://arxiv.org/pdf/2111.00899.pdf
paperhttps://arxiv.org/pdf/2111.00899.pdf
bibtexhttp://people.csail.mit.edu/pulkitag/data/dangovski2021equivariant.bib
https://people.csail.mit.edu/pulkitag/
Overcoming The Spectral Bias of Neural Value Approximation https://people.csail.mit.edu/pulkitag/
paper https://arxiv.org/abs/2206.04672
bibtexhttp://people.csail.mit.edu/pulkitag/data/yang2022overcoming.bib
https://openreview.net/forum?id=7uSBJDoP7tY
A System for General In-Hand Object Re-Orientation https://taochenshh.github.io/projects/in-hand-reorientation
Tao Chenhttps://taochenshh.github.io/
Jie Xuhttp://people.csail.mit.edu/jiex
paperhttps://openreview.net/forum?id=7uSBJDoP7tY
bibtexhttp://people.csail.mit.edu/pulkitag/data/chen2021system.bib
project pagehttps://taochenshh.github.io/projects/in-hand-reorientation
MIT Newshttps://news.mit.edu/2021/dexterous-robotic-hands-manipulate-thousands-objects-1112
https://openreview.net/pdf?id=R4E8wTUtxdl
Learning to Jump from Pixels https://openreview.net/pdf?id=R4E8wTUtxdl
Gabriel Margolishttp://people.csail.mit.edu/gmargo/
Tao Chenhttps://taochenshh.github.io/
Kartik Paigwarhttps://kartikpaigwar.github.io/
Xiang Fuhttps://xiangfu.co/
Donghyun Kimhttps://dhkim0821.github.io/
Sangbae Kimhttp://meche.mit.edu/people/faculty/sangbae@mit.edu
paperhttps://openreview.net/pdf?id=R4E8wTUtxdl
bibtexhttp://people.csail.mit.edu/pulkitag/data/margolis2021jumping.bib
project pagehttps://sites.google.com/view/jumpingfrompixels
MIT Newshttps://news.mit.edu/2021/one-giant-leap-mini-cheetah-1020
https://3d-representation-learning.github.io/nerf-dy/
3D Neural Scene Representations for Visuomotor Control https://3d-representation-learning.github.io/nerf-dy/
paperhttps://arxiv.org/abs/2107.04004
website https://3d-representation-learning.github.io/nerf-dy/
bibtexhttp://people.csail.mit.edu/pulkitag/data/li20213d.bib
https://arxiv.org/abs/2107.07501
An End-to-End Differentiable Framework for Contact-Aware Robot Design https://arxiv.org/abs/2107.07501.pdf
paperhttps://arxiv.org/abs/2107.07501.pdf
websitehttp://diffhand.csail.mit.edu/
bibtexhttp://people.csail.mit.edu/pulkitag/data/xu2021end.bib
videohttps://youtu.be/0CQoFaRaz7U
MIT Newshttps://news.mit.edu/2021/contact-aware-robot-design-0719
https://arxiv.org/pdf/2106.15612.pdf
Learning Task Informed Abstractions https://arxiv.org/pdf/2106.15612.pdf
paperhttps://arxiv.org/pdf/2106.15612.pdf
websitehttps://xiangfu.co/tia
bibtexhttp://people.csail.mit.edu/pulkitag/data/fu2021learning.bib
https://arxiv.org/pdf/2104.00631.pdf
Residual Model Learning for Microrobot Control https://arxiv.org/pdf/2104.00631.pdf
paperhttps://arxiv.org/pdf/2104.00631.pdf
bibtexhttp://people.csail.mit.edu/pulkitag/data/gruenstein2021residual.bib
http://people.csail.mit.edu/pulkitag/href="https:/sites.google.com/view/opal-iclr"
OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning https://sites.google.com/view/opal-iclr
Anurag Ajayhttps://anuragajay.github.io/
paperhttps://arxiv.org/pdf/2010.13611.pdf
websitehttps://sites.google.com/view/opal-iclr
bibtexhttp://people.csail.mit.edu/pulkitag/data/ajay2021opal.bib
http://people.csail.mit.edu/pulkitag/href="https:/anthonysimeonov.github.io/rpo-planning-framework/"
A Long Horizon Planning Framework for Manipulating Rigid Pointcloud Objects https://anthonysimeonov.github.io/rpo-planning-framework/
Anthony Simeonovhttps://anthonysimeonov.github.io/
paperhttps://arxiv.org/pdf/2011.08177.pdf
websitehttps://anthonysimeonov.github.io/rpo-planning-framework/
bibtexhttp://people.csail.mit.edu/pulkitag/data/simeonov2020learning.bib
https://richardrl.github.io/relational-rl/
Towards Practical Multi-object Manipulation using Relational Reinforcement Learning https://richardrl.github.io/relational-rl/
Richard Lihttps://richardrl.github.io/
Allan Jabrihttps://ajabri.github.io/
Trevor Darrellhttps://people.eecs.berkeley.edu/~trevor/
paperhttps://arxiv.org/pdf/1912.11032.pdf
websitehttps://richardrl.github.io/relational-rl/
codehttps://github.com/richardrl/rlkit-relational
bibtexhttp://people.csail.mit.edu/pulkitag/data/li2019towards.bib
https://arxiv.org/abs/1902.05522
Superposition of Many Models into One https://arxiv.org/abs/1902.05522
Brian Cheunghttps://redwood.berkeley.edu/people/brian-cheung/
Alex Terekhovhttps://redwood.berkeley.edu/people/alex-terekhov/
Yubei Chenhttps://redwood.berkeley.edu/people/yubei-chen/
Bruno Olshausenhttp://www.rctn.org/bruno/
arxivhttps://arxiv.org/abs/1902.05522
video tutorialhttps://www.youtube.com/watch?v=1WopZJ4WrX0
codehttps://github.com/briancheung/superposition
bibtexhttp://people.csail.mit.edu/pulkitag/data/cheung2019superposition.bib
https://www.ncbi.nlm.nih.gov/pubmed/31318502
Real-time Video Detection of Falls in Dementia Care Facility and Reduced Emergency Care https://ajmc.s3.amazonaws.com/_media/_pdf/AJMC_07_2019_Xiong%20final.pdf
paperhttps://ajmc.s3.amazonaws.com/_media/_pdf/AJMC_07_2019_Xiong%20final.pdf
SafelyYouhttps://www.safely-you.com/
bibtexhttp://people.csail.mit.edu/pulkitag/data/xiong2019real.bib
https://openreview.net/pdf?id=BkisuzWRW
Zero Shot Visual Imitation https://openreview.net/pdf?id=BkisuzWRW
Deepak Pathak*https://people.eecs.berkeley.edu/~pathak/
Parsa Mahmoudieh*https://people.eecs.berkeley.edu/~parsa.m/
Evan Shelhamerhttps://people.eecs.berkeley.edu/~shelhamer/
Alexei A. Efroshttps://people.eecs.berkeley.edu/~efros/
Trevor Darrellhttps://people.eecs.berkeley.edu/~trevor/
paperhttps://openreview.net/forum?id=BkisuzWRW
websitehttps://pathak22.github.io/zeroshot-imitation/
codehttps://github.com/pathak22/zeroshot-imitation
slideshttps://www.dropbox.com/s/36efg1t3qn6i495/2018_04_ZeroShotImitation.pptx
bibtexhttp://people.csail.mit.edu/pulkitag/data/pathak2018zero.bib
https://rach0012.github.io/humanRL_website/
Investigating Human Priors for Playing Video Games https://rach0012.github.io/humanRL_website/
Rachit Dubeyhttp://cocosci.princeton.edu/rachit/
Deepak Pathakhttps://people.eecs.berkeley.edu/~pathak/
Alexei A. Efroshttps://people.eecs.berkeley.edu/~efros/
Tom Griffithshttp://cocosci.princeton.edu/tom/
paperhttps://arxiv.org/pdf/1802.10217.pdf
websitehttps://rach0012.github.io/humanRL_website/
youtube coverhttps://youtu.be/Ol0-c9OE3VQ
mediahttps://rach0012.github.io/humanRL_website/#media
bibtexhttp://people.csail.mit.edu/pulkitag/data/dubey2018investigating.bib
https://pathak22.github.io/seg-by-interaction/
Learning Instance Segmentation by Interaction https://pathak22.github.io/seg-by-interaction/
Deepak Pathak*https://people.eecs.berkeley.edu/~pathak/
Dian Chen*http://www.cs.utexas.edu/~dchen/
Trevor Darrellhttps://people.eecs.berkeley.edu/~trevor/
Sergey Levinehttps://people.eecs.berkeley.edu/~svlevine/
Jitendra Malikhttps://people.eecs.berkeley.edu/~malik/
paperhttps://arxiv.org/pdf/1806.08354.pdf
websitehttps://pathak22.github.io/seg-by-interaction/
bibtexhttp://people.csail.mit.edu/pulkitag/data/pathak2018learning.bib
https://www.ahajournals.org/doi/full/10.1161/CIRCULATIONAHA.118.034338
Fully Automated Echocardiogram Interpretation in Clinical Practice: Feasibility and Diagnostic Accuracy https://www.ahajournals.org/doi/full/10.1161/CIRCULATIONAHA.118.034338
paperhttps://www.ahajournals.org/doi/full/10.1161/CIRCULATIONAHA.118.034338
arxivhttps://arxiv.org/abs/1706.07342
bibtexhttp://people.csail.mit.edu/pulkitag/data/zhang2018fully.bib
http://pathak22.github.io/noreward-rl/
Curiosity Driven Exploration by Self-Supervised Prediction http://people.csail.mit.edu/pulkitag/TODO
Deepak Pathakhttps://people.eecs.berkeley.edu/~pathak/
Alexei A. Efroshttps://people.eecs.berkeley.edu/~efros/
Trevor Darrellhttps://people.eecs.berkeley.edu/~trevor/
arxivhttps://arxiv.org/abs/1705.05363
videohttps://www.youtube.com/watch?v=J3FHOyhUn3A
talkhttps://vimeo.com/237270588
codehttps://github.com/pathak22/noreward-rl
project website https://pathak22.github.io/noreward-rl/
bibtexhttp://people.csail.mit.edu/pulkitag/data/pathak2017curiosity.bib
http://openaccess.thecvf.com/content_iccv_2017/html/Felsen_What_Will_Happen_ICCV_2017_paper.html
What Will Happen Next?: Forecasting Player Moves in Sports Videos http://openaccess.thecvf.com/content_iccv_2017/html/Felsen_What_Will_Happen_ICCV_2017_paper.html
Panna Felsenhttps://www.linkedin.com/in/panna-felsen-030a3964
Jitendra Malikhttps://people.eecs.berkeley.edu/~malik/
paper http://openaccess.thecvf.com/content_ICCV_2017/papers/Felsen_What_Will_Happen_ICCV_2017_paper.pdf
bibtexhttp://people.csail.mit.edu/pulkitag/data/felsen2017iccv.bib
Combining Self-Supervised Learning and Imitation for Vision-based Rope Manipulation https://ropemanipulation.github.io/
Ashvin Nair*http://ashvin.me/
Dian Chen*http://www.cs.utexas.edu/~dchen/
Phillip Isolahttp://web.mit.edu/phillipi/
Pieter Abbeelhttps://people.eecs.berkeley.edu/~pabbeel/
Jitendra Malikhttps://people.eecs.berkeley.edu/~malik/
Sergey Levinehttps://people.eecs.berkeley.edu/~svlevine/
arxivhttps://arxiv.org/abs/1703.02018
websitehttps://ropemanipulation.github.io/
video https://youtu.be/ofNQh5ELrOw
bibtexhttp://people.csail.mit.edu/pulkitag/data/nair2017combining.bib
Learning to Perform Physics Experiments via Deep Reinforcement Learning https://arxiv.org/abs/1611.01843
Misha Denilhttp://mdenil.com/
Tejas D Kulkarnihttps://tejasdkulkarni.github.io/
Tom Erezhttps://scholar.google.com/citations?user=gVFnjOcAAAAJ&hl=en
Peter Battagliahttps://scholar.google.com/citations?user=nQ7Ij30AAAAJ&hl=en
Nando de Freitashttps://www.cs.ubc.ca/~nando/
arxivhttps://arxiv.org/abs/1611.01843
mediahttps://www.newscientist.com/article/2112455-google-deepminds-ai-learns-to-play-with-physical-objects/
video https://www.youtube.com/watch?time_continue=1&v=gs7mWG2sjUU&feature=emb_logo
bibtexhttp://people.csail.mit.edu/pulkitag/data/denil2017learning.bib
https://www.ncbi.nlm.nih.gov/pubmed/29042342
Reduction in Fall Rate in Dementia Managed Care through Video Incident Review: Pilot Study https://www.ncbi.nlm.nih.gov/pubmed/29042342
paper https://www.jmir.org/2017/10/e339/pdf
bibtexhttp://people.csail.mit.edu/pulkitag/data/bayen2017reduction.bib
Human Pose Estimation with Iterative Error Feedback https://arxiv.org/pdf/1507.06550
Joao Carreirahttps://uk.linkedin.com/in/jo%C3%A3o-carreira-56238a7
Katerina Fragkiadakihttps://www.cs.cmu.edu/~katef/
Jitendra Malikhttps://people.eecs.berkeley.edu/~malik/
arxivhttps://arxiv.org/pdf/1507.06550
codehttps://github.com/pulkitag/ief
bibtexhttp://people.csail.mit.edu/pulkitag/data/carreira2016human.bib
Learning to Poke by Poking: Experiential Learning of Intuitive Physics http://ashvin.me/pokebot-website/
Ashvin Nair*http://ashvin.me/
Pieter Abbeelhttps://people.eecs.berkeley.edu/~pabbeel/
Jitendra Malikhttps://people.eecs.berkeley.edu/~malik/
Sergey Levinehttps://people.eecs.berkeley.edu/~svlevine/
arxivhttps://arxiv.org/abs/1505.01596
talkhttps://channel9.msdn.com/Events/Neural-Information-Processing-Systems-Conference/Neural-Information-Processing-Systems-Conference-NIPS-2016/Learning-to-Poke-by-Poking-Experiential-Learning-of-Intuitive-Physics
project websitehttp://ashvin.me/pokebot-website/
datahttps://drive.google.com/file/d/0B3xZefNMOTwuTUwtU0ZnaDhGVUE/view?usp=sharing
bibtexhttp://people.csail.mit.edu/pulkitag/data/agrawal2016learning.bib
What makes Imagenet Good for Transfer Learning? https://arxiv.org/pdf/1608.08614v2.pdf
Jacob Huh http://minyounghuh.com/
Alexei A. Efroshttps://people.eecs.berkeley.edu/~efros/
arxivhttps://arxiv.org/pdf/1608.08614
project websitehttp://minyounghuh.com/papers/analysis/
codehttps://github.com/minyoungg/WMIGFT
bibtexhttp://people.csail.mit.edu/pulkitag/data/huh2016what.bib
Learning Visual Predictive Models of Physics for Playing Billiards https://arxiv.org/abs/1511.07404
Katerina Fragkiadaki*https://www.cs.cmu.edu/~katef/
Sergey Levinehttps://people.eecs.berkeley.edu/~svlevine/
Jitendra Malikhttps://people.eecs.berkeley.edu/~malik/
arxivhttps://arxiv.org/abs/1511.07404
codehttps://github.com/pulkitag/pyphy-engine
bibtexhttp://people.csail.mit.edu/pulkitag/data/fragkiadaki2016learning.bib
Generic 3d Representation via Pose Estimation and Matching http://3drepresentation.stanford.edu/
Amir R. Zamirhttps://cs.stanford.edu/~amirz/
Tilman Wekelhttps://www.researchgate.net/profile/Tilman_Wekel
Jitendra Malikhttps://people.eecs.berkeley.edu/~malik/
Silvio Savaresehttp://cvgl.stanford.edu/silvio/
arxivhttps://arxiv.org/abs/1710.08247
website http://3drepresentation.stanford.edu/
dataset https://github.com/amir32002/3D_Street_View
codehttps://github.com/pulkitag/learning-to-see-by-moving
bibtexhttp://people.csail.mit.edu/pulkitag/data/zamir2016generic.bib
Learning to See by Moving https://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Agrawal_Learning_to_See_ICCV_2015_paper.pdf
Joao Carreirahttps://uk.linkedin.com/in/jo%C3%A3o-carreira-56238a7
Jitendra Malikhttps://people.eecs.berkeley.edu/~malik/
arxivhttps://arxiv.org/abs/1505.01596
codehttps://github.com/pulkitag/learning-to-see-by-moving
bibtexhttp://people.csail.mit.edu/pulkitag/data/agrawal2015learning.bib
Analyzing the Performance of Multilayer Neural Networks for Object Recognition https://www2.eecs.berkeley.edu/Research/Projects/CS/vision/papers/PulkitECCV2014.pdf
Ross Girshickhttps://www.rossgirshick.info/
Jitendra Malikhttps://people.eecs.berkeley.edu/~malik/
arxivhttps://arxiv.org/abs/1407.1610
bibtexhttp://people.csail.mit.edu/pulkitag/data/carreira2016human.bib
Pixels to Voxels: Modeling Visual Representation in the Human Brain https://arxiv.org/pdf/1407.5104
Dustin Stansburyhttps://people.eecs.berkeley.edu/~malik/
Jitendra Malikhttps://people.eecs.berkeley.edu/~malik/
Jack Gallanthttps://people.eecs.berkeley.edu/~malik/
arxivhttps://arxiv.org/pdf/1407.5104
unpublished resultshttp://people.csail.mit.edu/pulkitag/data/cnn_mimics_brain.pdf
bibtexhttp://people.csail.mit.edu/pulkitag/data/agrawal2014pixels.bib
The Automatic Assessment of Knowledge Integration Processes in Project Teams https://pdfs.semanticscholar.org/0242/a90f7a269ef2d185ca59ada28e4160b638a6.pdf
arxivhttps://pdfs.semanticscholar.org/0242/a90f7a269ef2d185ca59ada28e4160b638a6.pdf
bibtexhttp://people.csail.mit.edu/pulkitag/data/gweon2011automatic.bib
System and Method for Detecting, Recording and Communicating Events in the Care and Treatment of Cognitively Impaired Persons https://patentimages.storage.googleapis.com/5d/98/08/56f1af274703b6/US20190287376A1.pdf
Invariant Object Representation of Images Using Spiking Neural Networks https://patentimages.storage.googleapis.com/51/c6/fa/ce05ea8879dd68/US20150278628A1.pdf
Invariant Object Representation of Images Using Spiking Neural Networks https://patentimages.storage.googleapis.com/cb/1f/cf/5d728862f69828/US20150278641A1.pdf
Laurence Willement https://dutchsoftrobotics.nl/people/laurence-willemet
Zhang-wei Hong https://williamd4112.github.io/
Aviv Netanyahu https://avivne.github.io/
Tao Chenhttps://taochenshh.github.io/
Anurag Ajay https://anuragajay.github.io/
Ruben Castro https://rcastro.mit.edu/
Jacob Huh http://minyounghuh.com/
Anthony Simeonov https://anthonysimeonov.github.io/
Xiang Fu http://xiangfu.co/
Bipasha Sen https://bipashasen.github.io/
Brian Cheung https://scholar.google.com/citations?user=7N-ethYAAAAJ&hl=en
Srinath Mahankalihttps://srinathm1359.github.io/
Jagdeep Bhatiahttps://jagdeepsb.github.io/
Lars Ankilehttps://ankile.com/
Tifanny Portelahttps://ch.linkedin.com/in/tifanny-pereira-portela-97868521a
Marcel Tornehttps://marceltorne.github.io/
Steven Li https://supersglzc.github.io/
Abhishek Guptahttps://abhishekunique.github.io/
Lara Zlokapahttps://lara-z.github.io/
Avery Lamp https://averylamp.me/
templatehttps://github.com/jonbarron/jonbarron_website
accessibility https://accessibility.mit.edu/

Viewport: width=device-width, initial-scale=1

URLs of crawlers that visited me.