CDFG, MIT CSAILhttps://cdfg.csail.mit.edu/2026-08-10T00:00:00ZComputational Design and Fabrication GroupWith a feel for physics, AI models simulate a wider range of real-world scenariostag:cdfg.csail.mit.edu,2026-08-10:ai-models-simulate-wider-range-of-real-world-scenarios2026-08-10T00:00:00Z"GeoPT" helps AI models understand the basics of physics so they can simulate how objects respond to things like wind and water more efficiently and accurately.NeuralActuator receives the Outstanding Systems Paper in Memory of Seth Tellertag:cdfg.csail.mit.edu,2026-07-17:neuralactuator-wins-outstanding-systems-paper-in-memory-of-seth2026-07-17T00:00:00ZNeuralActuator: Neural Actuation Modeling for Robot Dynamics and External Force Perception received the Outstanding Systems Paper in Memory of Seth Teller at Robotics: Science and Systems, Sydney, 13 to 17 July 2026.Congratulations to Dr. Yifei Litag:cdfg.csail.mit.edu,2026-05-01:congratulations-to-dr-yifei-li2026-05-01T00:00:00ZYifei Li's doctoral degree was conferred in May 2026, for the thesis From Visual Computing to Physical AI: Simulation, Optimization, and Learning for Physical World.Congratulations to Dr. Liane Makaturatag:cdfg.csail.mit.edu,2026-05-01:congratulations-to-dr-liane-makatura2026-05-01T00:00:00ZLiane Makatura's doctoral degree was conferred in May 2026, for the thesis Unified Representation, Design, and Exploration of High-Performance Metamaterials.Fabrica receives the Best Paper Awardtag:cdfg.csail.mit.edu,2025-09-30:fabrica-wins-best-paper-award-conference-on-robot-learning2025-09-30T00:00:00ZFabrica: Dual-Arm Assembly of General Multi-Part Objects via Integrated Planning and Learning received the Best Paper Award at the Conference on Robot Learning, COEX Seoul, 27 to 30 September 2025.Congratulations to Dr. Yunsheng Tiantag:cdfg.csail.mit.edu,2025-09-01:congratulations-to-dr-yunsheng-tian2025-09-01T00:00:00ZYunsheng Tian's doctoral degree was conferred in September 2025, for the thesis Scalable Assembly of General Objects.AI shapes autonomous underwater 'gliders'tag:cdfg.csail.mit.edu,2025-07-09:ai-shapes-autonomous-underwater-gliders2025-07-09T00:00:00ZAn AI pipeline developed by CSAIL researchers enables unique hydrodynamic designs for bodyboard-sized vehicles that glide underwater and could help scientists gather marine data.Wojciech Matusik named Cadence Design Systems Professortag:cdfg.csail.mit.edu,2025-06-01:wojciech-matusik-named-cadence-design-systems-professor2025-06-01T00:00:00ZThe MIT Stephen A. Schwarzman College of Computing named Wojciech Matusik the Cadence Design Systems Professor, recognizing his work in machine learning and computational design. The chair began on 1 June 2025 for a five-year renewable term.System lets robots identify an object's properties through handlingtag:cdfg.csail.mit.edu,2025-05-08:system-lets-robots-identify-objects-properties-through-handling2025-05-08T00:00:00ZWith a novel simulation method, robots can guess the weight, softness, and other physical properties of an object just by picking it up.TelePulse receives the Best Paper Awardtag:cdfg.csail.mit.edu,2025-05-01:telepulse-wins-best-paper-award-acm-chi2025-05-01T00:00:00ZTelePulse: Enhancing the Teleoperation Experience through Biomechanical Simulation-Based Electrical Muscle Stimulation in Virtual Reality received the Best Paper Award at ACM CHI, Yokohama, 26 April to 1 May 2025.Could LLMs help design our next medicines and materials?tag:cdfg.csail.mit.edu,2025-04-09:could-llms-help-design-our-next-medicines-and-materials2025-04-09T00:00:00ZA new method lets users ask, in plain language, for a new molecule with certain properties, and receive a detailed description of how to synthesize it.Congratulations to Dr. Pingchuan Matag:cdfg.csail.mit.edu,2025-02-01:congratulations-to-dr-pingchuan-ma2025-02-01T00:00:00ZPingchuan Ma's doctoral degree was conferred in February 2025, for the thesis Building World Models with Neural Physics.Congratulations to Dr. Beichen Litag:cdfg.csail.mit.edu,2025-02-01:congratulations-to-dr-beichen-li2025-02-01T00:00:00ZBeichen Li's doctoral degree was conferred in February 2025, for the thesis Quality-Centric Single-Image Procedural Material Generation.Congratulations to Dr. Yiyue Luotag:cdfg.csail.mit.edu,2024-09-01:congratulations-to-dr-yiyue-luo2024-09-01T00:00:00ZYiyue Luo's doctoral degree was conferred in September 2024, for the thesis Intelligent Textiles for Physical Interactions.MIT CSAIL and GIST researchers develop a biomechanical dataset for badminton performance analysistag:cdfg.csail.mit.edu,2024-06-03:mit-csail-and-gist-researchers-develop-biomechanical-dataset2024-06-03T00:00:00ZCSAIL News story on the paper "MultiSenseBadminton: Wearable Sensor-Based Biomechanical Dataset for Evaluation of Badminton Performance" (Scientific Data, 2024).Congratulations to Dr. Liang Shitag:cdfg.csail.mit.edu,2024-05-01:congratulations-to-dr-liang-shi2024-05-01T00:00:00ZLiang Shi's doctoral degree was conferred in May 2024, for the thesis Towards Passing Visual Turing Test with Computational 3D Displays and Appearance Modeling.Smart glove teaches new physical skillstag:cdfg.csail.mit.edu,2024-02-20:smart-glove-teaches-new-physical-skills2024-02-20T00:00:00ZAdaptive smart glove from MIT CSAIL researchers can send tactile feedback to teach users new skills, guide robots with more precise manipulation, and help train surgeons and pilots.Using AI to discover stiff and tough microstructurestag:cdfg.csail.mit.edu,2024-02-14:using-ai-discover-stiff-tough-microstructures2024-02-14T00:00:00ZInnovative AI system from MIT CSAIL melds simulations and physical testing to forge materials with newfound durability and flexibility for diverse engineering uses.Wojciech Matusik receives the 2023 Humboldt Research Awardtag:cdfg.csail.mit.edu,2024-02-02:humboldt-research-award2024-02-02T00:00:00ZThe Alexander von Humboldt Foundation conferred the 2023 Humboldt Research Award on Feb. 2, 2024. The award recognizes a researcher's whole body of work. The foundation dates the award to 2023; the conferral followed in February 2024.Congratulations to Dr. Allan Zhaotag:cdfg.csail.mit.edu,2024-02-01:congratulations-to-dr-allan-zhao2024-02-01T00:00:00ZAllan Zhao's doctoral degree was conferred in February 2024, for the thesis Robot Graph Grammars: Towards Custom Robots for Every Task.Yiyue Luo named to the Forbes 30 under 30 listtag:cdfg.csail.mit.edu,2023-12-05:yiyue-30-under-302023-12-05T00:00:00ZCongratulations to CDFG member Yiyue Luo, who was recently named to the Forbes 30 under 30 list! Her inspiring work creates smart textiles that can add sensing and other technology into knitted fabrics. She has developed machine-knitted tactile sensing garments, like vests, socks, and gloves, that can provide real-time data on physical interactions, like a pair of socks could detect a fall or a condition like Parkinson’s non-intrusively. Congratulations, Yiyue!This 3D printer can watch itself fabricate objectstag:cdfg.csail.mit.edu,2023-11-15:3d-printer-can-watch-itself-fabricate-objects2023-11-15T00:00:00ZComputer vision enables contact-free 3D printing, letting engineers print with high-performance materials they could not use before.Seed grant for large language models in design and manufacturingtag:cdfg.csail.mit.edu,2023-09-18:mit-scholars-awarded-seed-grants-generative-ai2023-09-18T00:00:00ZOne of twenty-seven MIT projects funded to explore the impact of generative AI, spanning every school at the Institute.New method simplifies the construction process for complex materialstag:cdfg.csail.mit.edu,2023-08-02:new-method-simplifies-construction-complex-materials2023-08-02T00:00:00ZWith a new, user-friendly interface, researchers can quickly design many cellular metamaterial structures that have unique mechanical properties.Learning the language of molecules to predict their propertiestag:cdfg.csail.mit.edu,2023-07-07:learning-language-molecules-predict-properties2023-07-07T00:00:00ZThis AI system needs only a small amount of data to predict molecular properties, which could speed up drug discovery and material development.The chore of packing just got faster and easiertag:cdfg.csail.mit.edu,2023-07-06:chore-packing-just-got-faster-and-easier2023-07-06T00:00:00ZA new computational method facilitates the dense placement of objects inside a rigid container.Michael Foshey receives an MIT-Pillar AI Collective seed granttag:cdfg.csail.mit.edu,2023-06-22:foshey-mit-pillar-ai-collective-seed-grant2023-06-22T00:00:00ZThe grant supports autonomous manufacturing assembly with human-like tactile perception. Six teams were funded for AI, data science and machine learning work with potential commercial applications.Two papers to be presented at SIGGRAPH 2023tag:cdfg.csail.mit.edu,2023-05-22:two-papers-to-be-presented-at-siggraph-20232023-05-22T00:00:00ZTwo CDFG papers appear at SIGGRAPH 2023. Beichen Li presents “End-to-End Procedural Material Capture with Proxy-Free Mixed-Integer Optimization”, with Liang Shi and Wojciech Matusik. Liane Makatura presents “Procedural Metamaterials: A Unified Procedural Graph for Metamaterial Design”, with Bohan Wang, Bolei Deng, Wojciech Matusik, and collaborators at IST Austria.Liane Makatura wins Design Fellowship from the MIT Morningside Academy for Designtag:cdfg.csail.mit.edu,2023-05-22:liane-makatura-wins-mad-design-fellowship2023-05-22T00:00:00ZOur lab member, Liane Makatura, has been named as a MAD Design Fellow , as part of the MIT Morningside Academy for Design. Congratulations, Liane!MIT and GIST researchers develop a natural and comfortable Seamless-walk VR locomotion systemtag:cdfg.csail.mit.edu,2023-04-11:mit-and-gist-researchers-develop-natural-and-comfortable-sea2023-04-11T00:00:00ZCSAIL News story on the paper "Seamless-walk: natural and comfortable virtual reality locomotion method with a high-resolution tactile sensor" (Virtual Reality, 2023).Computational system streamlines the design of fluidic devicestag:cdfg.csail.mit.edu,2022-12-09:computational-tool-fluidic-devices2022-12-09T00:00:00ZThis computational tool can generate an optimal design for a complex fluidic device such as a combustion engine or a hydraulic pump.An automated way to assemble thousands of objectstag:cdfg.csail.mit.edu,2022-12-07:automated-way-assemble-thousands-objects2022-12-07T00:00:00ZA new algorithm for automatic assembly of products is accurate, efficient, and generalizable to a wide range of complex real-world assemblies.Liang Shi awarded Snap Fellowshiptag:cdfg.csail.mit.edu,2022-12-05:liang-shi-won-snap-fellowship2022-12-05T00:00:00ZOur group member Liang Shi has been award the Snap Fellowship 2022 . Congratulations!VoRF receives a Best Paper Honorable Mentiontag:cdfg.csail.mit.edu,2022-11-24:vorf-best-paper-honorable-mention-bmvc2022-11-24T00:00:00ZVoRF: Volumetric Relightable Faces received a Best Paper Honorable Mention at the British Machine Vision Conference, London, 21 to 24 November 2022.Liang Shi is elected as the Rising Star of Light by Nature Light Science & Applicationstag:cdfg.csail.mit.edu,2022-10-26:liang-shi-won-rising-star-of-light-by-nature-light2022-10-26T00:00:00ZOur group member Liang Shi has been elected as the Rising Star of Light by Nature Light Science & Applications . Congratulations!Wenqiang Winston Chen wins Best Paper award at ACM MobiCom 2022tag:cdfg.csail.mit.edu,2022-10-20:winston-chen-wins-best-paper-award2022-10-20T00:00:00ZOur lab member, Wenqiang Winston Chen, received the Best Paper award at the 2022 ACM Wireless of the Students, by the Students, and for the Students Workshop (S^3) co-located with ACM MobiCom 2022. This award recognizes Winston’s work on the paper entitled, “ViWatch: Harness Vibrations for Finger Interactions with Commodity Smartwatches.” Congratulations, Winston!Two papers accepted to SIGGRAPH Asia 2022tag:cdfg.csail.mit.edu,2022-10-03:two-papers-accepted-to-siggraph-asia-20222022-10-03T00:00:00ZTwo papers authored by CDFG members have been accepted to SIGGRAPH Asia 2022 (journal track). Yifei Li and Tao Du will present “Fluidic Topology Optimization with an Anisotropic Mixture Model”. Yunsheng Tian, Jie Xu and Yichen Li will present “Assemble Them All: Physics-Based Planning for Generalizable Assembly by Disassembly.Congratulations to Dr. Xutag:cdfg.csail.mit.edu,2022-08-17:congratulations-to-dr-xu2022-08-17T00:00:00ZOur PhD student Jie Xu is now Dr. XU. Dr. Xu successfully defended his thesis, “Towards Computational Design of Shape and Control for Rigid Robots” last week. Congratulations!Paper accepted to Light: Science & Applicationstag:cdfg.csail.mit.edu,2022-08-10:paper-accepted-light-science-applications2022-08-10T00:00:00ZWe propose a end-to-end learning pipeline for sythesizing phase-only 3D holograms in real-time.Using artificial intelligence to control digital manufacturingtag:cdfg.csail.mit.edu,2022-08-02:artificial-intelligence-3-d-printing2022-08-02T00:00:00ZResearchers train a machine-learning model to monitor and adjust the 3D printing process to correct errors in real time.Design your own robotic handtag:cdfg.csail.mit.edu,2022-07-14:design-your-own-robotic-hand2022-07-14T00:00:00ZMIT researchers have created an integrated design pipeline that enables a user with no specialized knowledge to quickly craft a customized 3D-printable robotic hand.Beichen Li Recipient of the 2022 Ernst A. Guillemin Thesis Award in Artificial Intelligence and Decision Makingtag:cdfg.csail.mit.edu,2022-07-14:beichen-li-recipient-of-the-2022-ernst-a-guillemin-thesis-award-in-artificial-intelligence-and-decision-making2022-07-14T00:00:00ZBeichen Li, a PhD student in CDFG, has been chosen as the recipient of the 2022 MIT EECS Ernst A. Guillemin Thesis Award in Artificial Intelligence and Decision Making for his master’s thesis entitled “Computational Discovery of Microstructured Composites with Optimized Trade-Off between Strength and Toughness,” supervised by Professor Wojciech Matusik.A helping hand for robotic manipulator designtag:cdfg.csail.mit.edu,2022-06-06:helping-hand-robotic-manipulator-design2022-06-06T00:00:00ZCSAIL News story on the paper "An Integrated Design Pipeline for Tactile Sensing Robotic Manipulators" (ICRA 2022).A one-up on motion capturetag:cdfg.csail.mit.edu,2022-04-29:one-motion-capture-neural-network2022-04-29T00:00:00ZA new neural network approach captures the characteristics of a physical system's dynamic motion from video, regardless of rendering configuration or image differences.Digital Fabrication of Pneumatic Actuators with Integrated Sensing by Machine Knittingtag:cdfg.csail.mit.edu,2022-04-18:digital-fabrication-of-pneumatic-actuators-with-integrated-sensing-by-machine-knitting2022-04-18T00:00:00ZWe propose a rapid design and fabrication workflow for pneumatic actuators with integrated sensing using digital machine knitting.Paper accepted to CVPR 2022tag:cdfg.csail.mit.edu,2022-04-14:paper-accepted-to-cvpr-20222022-04-14T00:00:00ZCDFG members Yunsheng Tian and Yifei Li’s paper “JoinABLe: Learning Bottom-up Assembly of Parametric CAD Joints” has been accepted to CVPR 2022. In this paper, we propose a learning-based method that assembles parts together to form joints without the help of object class labels or human guidance, and a large dataset containing CAD assemblies with rich information.Three papers accepted to ICLR, with two oral presentations!tag:cdfg.csail.mit.edu,2022-04-13:three-papers-accepted-to-iclr-with-two-oral-presentations2022-04-13T00:00:00ZThree papers authored by CDFG members have been accepted to ICLR 2022, and two have been selected for an oral presentation! Pingchuan Ma and Tao Du will present their work “RISP: Rendering-Invariant State Predictor with Differentiable Simulation and Rendering for Cross-Domain Parameter Estimation.” Minghao Guo and Beichen Li will also present their paper, “Data-Efficient Graph Grammar Learning for Molecular Generation”. The third accepted paper, authored by CDFG member Jie Xu, is titled “Accelerated Policy Learning with Parallel Differentiable Simulation”. Congratulations to all the paper authors!Generating new molecules with graph grammartag:cdfg.csail.mit.edu,2022-04-01:generating-new-molecules-with-graph-grammar2022-04-01T00:00:00ZAn efficient machine-learning method uses chemical knowledge to create a learnable grammar with production rules to build synthesizable monomers and polymers.Mina Konakovic Lukovic joins the MIT facultytag:cdfg.csail.mit.edu,2022-02-28:school-engineering-welcomes-new-faculty2022-02-28T00:00:00ZMina Konakovic Lukovic, a Schmidt Science Postdoctoral Fellow in the group, joins the Department of Electrical Engineering and Computer Science as an assistant professor. She now leads the Algorithmic Design Group at CSAIL.Paper accepted to NeurIPS 2021tag:cdfg.csail.mit.edu,2021-12-14:paper-accepted-to-neurips2021-12-14T00:00:00ZCDFG UROPs Jagdeep Singh Bhatia , Holly Jackson , and PhD students Yunsheng Tian , Jie Xu ’s paper Evolution Gym: A Large-Scale Benchmark for Evolving Soft Robots has been accepted to NeurIPS 2021. In this paper, we propose Evolution Gym, the first large-scale benchmark for co-optimizing the design and control of soft robots.Paper accepted to Science Advancestag:cdfg.csail.mit.edu,2021-10-15:paper-accepted-to-science-advances2021-10-15T00:00:00ZCDFG member Michael Foshey , and Mina Konaković Luković ’s paper Accelerated discovery of 3D printing materials using data-driven multiobjective optimization has been accepted to Science Advances. In this paper, we present how machine learning can aid the discovery of useful 3D printing material formulations.Alyssa Luo awarded Mathworks Fellowshiptag:cdfg.csail.mit.edu,2021-08-26:fellowship2021-08-26T00:00:00ZWe are pleased to announce that CDFG member and 3rd year graduate student Alyssa Luo has been awarded a MathWorks Engineering Fellowship for AY 21-22. Her current research interests involve working on tactile sensing and smart textiles. Congratulations to Alyssa on her fellowship.Liang Shi awarded Facebook Fellowshiptag:cdfg.csail.mit.edu,2021-08-26:cdfg-member-awarded-fellowship2021-08-26T00:00:00ZCDFG member Liang Shi has been awarded a 2021 Facebook Fellowship in the area of AR/VR computer graphics. Additionally, he has just completed a Summer internship (5/28-8/20) at Facebook Reality Lab Display System Research group. Congratulations to Liang on his fellowship as well as involvement in this Summer internship.Paper accepted to RSS 2021tag:cdfg.csail.mit.edu,2021-06-25:paper-accepted-to-rss-20212021-06-25T00:00:00ZCDFG member Jie Xu , Lara Zlokapa , and Michael Foshey ’s paper An End-to-End Differentiable Framework for Contact-Aware Robot Design has been accepted to RSS 2021. In this paper, we present an efficient differentiable pipeline to co-optimize the morphology and control of articulated robots.Intelligent carpet gives insight into human posestag:cdfg.csail.mit.edu,2021-06-24:intelligent-carpet-gives-insight-human-poses2021-06-24T00:00:00ZTactical sensing carpet estimates 3D human poses without the use of cameras, and could improve health monitoring and smart homes.KnitUI receives a Best Paper Honorable Mentiontag:cdfg.csail.mit.edu,2021-05-13:knitui-best-paper-honorable-mention-chi2021-05-13T00:00:00ZKnitUI: Fabricating Interactive and Sensing Textiles with Machine Knitting received a Best Paper Honorable Mention at ACM CHI, held online 8 to 13 May 2021.Robo-starfish aims to enable closer study of aquatic lifetag:cdfg.csail.mit.edu,2021-04-08:robo-starfish-aims-enable-closer-study-aquatic-life2021-04-08T00:00:00ZCSAIL News story on the paper "Underwater Soft Robot Modeling and Control With Differentiable Simulation" (IEEE Robotics and Automation Letters, 2021).Five papers conditionally accepted to SIGGRAPH 2021tag:cdfg.csail.mit.edu,2021-04-02:five-papers-conditionally-accepted-to-siggraph-20212021-04-02T00:00:00ZFive papers authored by CDFG members have been conditionally accepted to SIGGRAPH 2021! We are excited to share these works, and hope you’ll stay tuned for their official releases over the coming months.Paper accepted to CVPR 2021tag:cdfg.csail.mit.edu,2021-04-01:paper-accepted-to-cvpr-20212021-04-01T00:00:00ZCDFG member Yiyue Luo , Michael Foshey , and Wan Shou’s paper Intelligent Carpet: Inferring 3D Human Pose from Tactile Signals has been accepted to CVPR 2021. In this paper, we present a 3D human pose estimation approach using vision as supersion and the pressure maps recorded by a large-scale tactile carpet as input. This work is in collobaration with Professor Antonio Torralba ’s group.Papers accepted to ICRA and RAL 2021tag:cdfg.csail.mit.edu,2021-03-30:papers-accepted-to-icra-and-ral-20212021-03-30T00:00:00ZJie Xu’s “Multi-Objective Graph Heuristic Search for Terrestrial Robot Design”, with Andrew Spielberg and Allan Zhao, is accepted to ICRA 2021: co-designing a rigid robot’s control and morphology under multiple objectives. Tao Du’s “Underwater Soft Robot Modeling and Control with Differentiable Simulation”, with Josie Hughes and UROP student Sebastien Wah, is accepted to IEEE RA-L.