
The Kempner Institute for the Study of Natural and Artificial Intelligence at @Harvard University. RTs ≠ Endorsements
Cambridge, Mass
Joined November 2022
- Tweets1K
- Following360
- Followers4K
- Likes371
What is the #KempnerInstitute? Watch a short video feature to dive deeper into our mission and meet the researchers behind it: bit.ly/49ODO2K #AI #ML #NeuroAI #neuroscience @Harvard
What do diffusion models, representation learning, reinforcement learning, and test-time reasoning have in common? Each can be seen as learning an energy function or using one to guide sampling and search.
Excited to share our tutorial on energy-based models with @daibond_alpha!
1/5 EBMs are usually taught as one model family among many. In our new tutorial with @du_yilun, we use them as a single lens on machine learning.
"An Energy-Based Perspective on Machine Learning" arxiv.org/abs/2611.14383
LLMs have slashed the costs of writing code, but not debugging it. Introducing Formal Disco, where LLMs collaborate on writing, repairing, and extending formally verified programs. By @GabrielPoesia Simon Henniger, @TzuHanH, @du_yilun, and Nada Amin. bit.ly/4zVrP15
7
505
Kempner Institute at Harvard University retweeted
Video models can generate scenes. Geometry models can reconstruct them.
What if one model did both?
UGG generates video, depth and camera motion together, as one scene. (NeurIPS 2026)
Co-first authors: @ZhiyiLi02 and @ruojin8
🌐 ugg-model.github.io
Kempner Institute at Harvard University retweeted
We’ve seen a whole wave of [X]Mimic papers lately, and I might be biased, but this one is easily my favorite 🧡
Introducing ImpedanceMimic: Learned Impedance as Action Space for Force-Accurate Motion Imitation w/ @matthiasjammot
Fixed PD gains can track a motion yet miss its contact forces. ImpedanceMimic learns per-joint stiffness and damping as 129 people walk, run, jump... 🚶🏻♀️🏃🏻♀️
TLDR:
🏆 Beats other action spaces (fixed-PD, torque, muscle) and SOTA (PHC, SimPoE) on motion and force accuracy together
🤖 Transfers without retraining to 22 unseen people and a simulated Unitree G1
🔍 Interpretable gains: stiffness scales with load, damping anticipates unloading
📝 Paper: arxiv.org/abs/2611.19153Proj…
🌐 Project page: impedancemimic.github.io/Imp…
With gracious support from the Kempner Institute at Harvard University. @KempnerInst @hseas
Congratulations to @tweetsatpreet! We appreciate the work he did at the Kempner, and we're excited to see where his research will take him next.
1/ Excited to launch my lab as a new assistant professor at UNC–Chapel Hill (@uncsdis)! 🧠🤖🐟
We'll study Natural and Engineered Intelligence through simulation, data science and theory, working closely with experimentalists.
singhlab.cc
The Kempner Institute’s research and engineering team members @NaeemKhoshnevis, @maxshadx,Timothy Ngotiaoco, and @y_mazloum are at the #SC26 supercomputing conference this week in Chicago.
Excited to share UGG, which unifies video generation and 3D reconstruction in a single generative model!
By jointly modeling video, depth and camera pose, we can infer missing parts of a scene, generate new scenes, and improve geometric predictions with inference-time search.
Video models can generate scenes. Geometry models can reconstruct them.
What if one model did both?
UGG generates video, depth and camera motion together, as one scene. (NeurIPS 2026)
Co-first authors: @ZhiyiLi02 and @ruojin8
🌐 ugg-model.github.io
Kempner Institute at Harvard University retweeted
That's a wrap on Memory for Robot Foundation Models at #CoRL2026! Thank you all for the huge interest 🙏
Here is a recap ⬇️
We had 4 invited talks from @KaterinaFragiad , @b_k_bucher, @KarlPertsch and @liu_yuejiang , 6 lightning talks, and 35 accepted papers.
The Kempner Computing Handbook has reached nearly 18,000 active users across 141 countries and territories!
If you've found the handbook useful, please consider giving it a star on GitHub bit.ly/4t1nMO6
Can AI overthink a problem? New research by @wl_tong, Ege Çakar, and @CPehlevan suggests it can.
bit.ly/4iUewXx
3
520
Thanks to @TrackingPlumes of @EFPL for delivering a fascinating talk at #KempnerInstitute about the advances in AI agents capable of performing complex motor-control tasks.
kempnerinstitute.harvard.edu…
1
6
804
Check out #KempnerInstitute Investigator @s_y_chung's work, in collaboration with @RainerFriedri12’s lab on olfactory neural manifolds in zebrafish, on the cover of
@NatureNeuro’s November issue! 🐟🐟 Congrats to Bo, Rainer, Chi-Ning & the team.
2
450
⚡NEW: Unlocking lossless speedups in LLMs via discrete diffusion. A new diffusion-augmented model, Uno, combines autoregressive and diffusion weights in one network to generate multiple tokens per forward pass. More in today’s Deeper Learning blog post: bit.ly/4AmooR0
Work by @JonathanGeuter, @ssahoo_, @LingjieChen127, Khiem Pham, @DwChaitanya, @varad0309, @yashakha, Alexander Moreno, @Yurochkin_M, @wang1999_zt, @m_elhoushi, @DeyNolan, @ShaneBergsma, Joel Hestness, @jwthickstun, @ericxing and @waterluffy
1
202
A team led by #KempnerInstitute Associate Faculty @marinkazitnik has recieved a Cancer Grand Challenges grant to create AI “co-scientists” that help researchers analyze data, generate hypotheses, and suggest new experiments, speeding new knowledge and therapies. Learn more:
Our cancer researchers are putting AI to the test.
Three Cancer Grand Challenges teams have been selected as part of a $10M project to explore how AI co-scientists could accelerate cancer research 🚀
Led by @marinkazitnik (@harvardmed), Project AURORA is developing AI co-scientists to work alongside researchers, helping them generate scientific hypotheses and prioritise experiments.
Following a competitive application and selection process, researchers from three currently funded Cancer Grand Challenges teams have been selected as our AURORA pioneer teams. They will be led by:
🔹@NickyMcGranahan (team NexTGen)
🔹Welles Robinson and @squezadd (team MATCHMAKERS)
🔹@nlbigas (team PROMINENT)
We’re excited to see how this project can help our scientists make faster progress against cancer’s toughest challenges!
Learn more about AURORA and the pioneer teams ➡️ bit.ly/4yXS4Tz
AURORA is funded by @CR_UK through Cancer Grand Challenges.
1
3
399
Kempner Institute at Harvard University retweeted
Happy to join Harvard University’s @KempnerInst as a Research Fellow!
I’ll continue to explore energy-based models for generation and reasoning. Excited about the future of the field!
If you work on similar questions, let’s connect here or at NeurIPS in Sydney (presenting GEM).
Excited to share our work on Energy-Based Policy Orchestration that we will be presenting at CoRL!
We present a simple framework to orchestrate different humanoid skills together through an energy value.
yewr.github.io/epo/
Planners operate on task timescales. Feasibility changes on control timescales.
Bridging that gap takes a high-frequency mid-level layer. Introducing EPO: Energy-Based Policy Orchestration #CoRL2026
EPO gives each low-level policy an energy: how feasible a goal is, and how well the policy will reach it. Energies are differentiable and comparable across policies, so EPO optimizes the policy–goal pair at control rate.
Unlike a learned MoE router, EPO is compositional: adding a skill means training one new energy, nothing else. It's also more precise and switches policies 7× less often, pushing the precision–robustness frontier.
📄 Paper: arxiv.org/abs/2611.02546
🌐 Project: yewr.github.io/epo
💻 Code: github.com/YeWR/EPO
@wangyenjen @elvis_hsieh77 @frankzydou @ShiboZhaoSLAM @pabbeel @du_yilun @MIT_LISLab
At #CoRL this week? Check out the workshop on Memory for Robot Foundation Models with #KempnerInstitute panelist @du_yilun! @pgozdil
Heading to Austin for my FIRST #CoRL! 🙂 Excited to meet fellow robotics researchers, DM me if you'd like to chat! We're organizing a workshop on Memory for Robot Foundation Models. All accepted papers and the workshop program are now online 👉 corl2026-memory.github.io #CoRL2026
2
290
🔍What if we could anticipate which scenarios LLMs will fail on and focus on those? Adversarial Concept Search predicts when a model might make a mistake using representational geometry. More in today's Deeper Learning blog post from the #KempnerInstitute: bit.ly/4ePWsfW
Adversarial Concept Search: Predicting Compositional Errors From Feature Geometry by @nsaphra, @jenniferlumeng, @ruochenz_, @wordscompute, @elmelis and Ellie Pavlick
1
1
544




















