Drone Swarms and Differentiable Programming
by Chris Dollo

Reynolds, “Flocks, Herds, and Schools” (Boids, 1987). 
Batra et al., Decentralized Quadrotor Swarms with Deep RL (2021). 
Suh et al., “Do Differentiable Simulators Give Better Policy Gradients?” (ICML 2022).
Zhang et al., “Back to Newton’s Laws” (2024).



Differentiable Trajectory Optimization
by Michael Brown

1. Differentiable Quadrotor Trajectory: https://ieeexplore.ieee.org/document/8206214
2. SDFs for Dynamic Motion Planning: https://arxiv.org/abs/2008.00969
2. CHOMP Motion Planning: https://publications.ri.cmu.edu/storage/publications/pub_files/2013/5/CHOMP_IJRR.pdf
1. LaValle Trajectory Optimization Lecture: https://lavalle.pl/planning/node795.html#eqn:gradperturb


Visual Water Quality Monitoring and Auxiliary Modality Learning for Multimodal Data: Methods, Trends, and Opportunities
by Juan Carlier Blanco

Sun, Y., Wang, D., Li, L., et al. (2024). “Application of Remote Sensing Technology in Water Quality Monitoring: From Traditional Approaches to Artificial Intelligence.” Water Research, 267, 122546. (DOI)	
(Introduction to image-based water-quality monitoring) 

Amin, G., Pourret, O., Dupin, V., Guérin-Rechdaoui, S., & Dujany, A. (2026). “Comparing AI-driven approaches for predicting river water quality: a systematic review of water quality indices and remote sensing methods.” Water Research, 301, 126047. (DOI)	(River-specific academic survey) 

Kwon, D. Y., Kim, J., Park, S., & Hong, S. (2023). “Advancements of remote data acquisition and processing in unmanned vehicle technologies for water quality monitoring: An extensive review.” Chemosphere, 343, 140198. (PubMed)	
(Connects water monitoring with drones and multimodal sensing)

Shen, Y., Wang, X., Gao, P., & Lin, M. C. (2023). “Auxiliary Modality Learning with Generalized Curriculum Distillation.” ICML 2023.	(Auxiliary Modality Learning, AML) 

Liu, R., Shen, Y., Gao, P., Tokekar, P., & Lin, M. (2025). “CAML: Collaborative Auxiliary Modality Learning for Multi-Agent Systems.” NeurIPS 2025.  (AML for multiple agents and sensors)


Differentiation of Quantum Circuit Parameters for Noise Mitigation
by Evan Chen

https://arxiv.org/pdf/2202.13414
https://arxiv.org/pdf/2407.00736v2
https://arxiv.org/pdf/2010.08561
https://arxiv.org/pdf/1710.07345


Flow Matching: Foundations and Recent Advances
by Nithin Sivakumaran

https://arxiv.org/abs/2210.02747, ICLR 2023.
https://arxiv.org/abs/2505.13447, NeurIPS 2025.
https://arxiv.org/abs/2512.02012, CVPR 2026.


What do Robots Need to Feel as They Walk
by Fatemeh Alvankarian

1) Elnoor, M., Sathyamoorthy, A.J., Weerakoon, K. and Manocha, D., 2024. Pronav: Proprioceptive traversability estimation for legged robot navigation in outdoor environments. IEEE Robotics and Automation Letters, 9(8), pp.7190-7197.

2) Chen, J., Frey, J., Zhou, R., Miki, T., Martius, G. and Hutter, M., 2024. Identifying terrain physical parameters from vision-towards physical-parameter-aware locomotion and navigation. IEEE Robotics and Automation Letters, 9(11), pp.9279-9286.

3) Chopra, S., Liang, J., Seneviratne, G. and Manocha, D., 2026. Physgs: Bayesian-inferred gaussian splatting for physical property estimation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 18980-18990).


Continual learning for robot control under changing operation
by Yixuan Sun

https://proceedings.neurips.cc/paper_files/paper/2018/hash/ba6d843eb4251a4526ce65d1807a9309-Abstract.html

https://ieeexplore.ieee.org/abstract/document/11358700?casa_token=_oQRhGydG-kAAAAA:ZK0goOM9sNLcWkdUuXh7E9KjcznN-X_akIvSVkl_JGNkZ7A9G0uDZldDx1q8tkyKPgWu-DFvng

https://ieeexplore.ieee.org/abstract/document/10801427?casa_token=32M2KVYGHTkAAAAA:vf7EqopfqP0fZzMGJvIC5YQlIUkrsgxJV2t77-lAer-qMDWuoOgOhnGYbmogBdnInc6Em0g4Zg

https://ieeexplore.ieee.org/abstract/document/9560793?casa_token=6DdL0uFGs20AAAAA:JskP9CMTzFOJu0ZAXqorK_-j0-aE36l-wTh3P0HQhTKIs6WJtcaTlhaTvZmRKZJ0XtWEuND1Xw

https://ieeexplore.ieee.org/abstract/document/9968092?casa_token=yRAOu3oNVigAAAAA:fx5wJ8aDBDIFsSUZZrAEYD-mRmpHGMhaOdBELbsz87e23ODyUYAAVXRdge8ryOdPDE1NTjm4BA

https://proceedings.mlr.press/v100/williams20a.html


Learning Robot Navigation from Differentiable Planning Objectives
by Yohan Abeysinghe

Yang et al., “iPlanner: Imperative Path Planning” (2023) — learning navigation through differentiable planning costs.

Roth et al., “ViPlanner: Visual Semantic Imperative Learning for Local Navigation” — incorporating geometric and semantic traversability into differentiable planning objectives.

Amos et al., “Differentiable MPC for End-to-end Planning and Control” (2018) — differentiating through a planning and control procedure.

Andrychowicz et al., “Learning to Learn by Gradient Descent by Gradient Descent” (2016) — learning optimization update rules.

Ratliff et al., “CHOMP: Gradient Optimization Techniques for Efficient Motion Planning” (2009) — background on gradient-based trajectory refinement.


Learning to Accelerate Mathematical Algorithms Through Differentiable Programming
by Abdullah Ahmed

Learning to Learn by Gradient Descent by Gradient Descent — Andrychowicz et al. (NeurIPS 2016). https://arxiv.org/abs/1606.04474  

Learned Optimizers that Scale and Generalize — Wichrowska et al. (ICML 2017) https://arxiv.org/abs/1703.04813  

First-Order Preconditioning via Hypergradient Descent — Moskovitz et al. (2019)    https://arxiv.org/abs/1910.08461 

Meta-Curvature — Park and Oliva (NeurIPS 2019)    https://arxiv.org/abs/1902.03356 5. 

Meta-Learning with Warped Gradient Descent — Flennerhag et al. (ICLR 2020)    https://arxiv.org/abs/1909.00025 

Meta-Learning with a Geometry-Adaptive Preconditioner — Kang et al. (CVPR 2023)    https://arxiv.org/abs/2304.01552 

Greedy Learning to Optimize with Convergence Guarantees — Fahy, Golbabaee, and Ehrhardt (2024). https://arxiv.org/abs/2406.00260

Neural Fixed-Point Acceleration for Convex Optimization — Venkataraman and Amos (2021).  https://arxiv.org/abs/2107.10254 

Learning Fast Approximations of Sparse Coding — Gregor and LeCun (ICML 2010)    https://icml.cc/2010/papers/449.pdf



Learning Anticipatory Social Navigation from Human-Human Interactions Using Different Learning Methods
by Owen Hoffman 

1. HumAIN: https://arxiv.org/abs/2607.07357  
2. SocialNav: https://arxiv.org/abs/2511.21135
3. DiffStack: https://proceedings.mlr.press/v205/karkus23a.html
4. iCrowdNav: https://arxiv.org/abs/2606.26047
5. FlowPilot: https://arxiv.org/abs/2606.12603
6. Flow Matching: https://arxiv.org/abs/2210.02747


Learning to Predict the Future in Latent Space: JEPA and the LeWorldModel
by Vishesh Narayan and Arjun Mudda

[B1] LeCun, Y. (2022). A Path Towards Autonomous Machine Intelligence. OpenReview preprint.
Introduces the JEPA concept and the energy-based framing that motivates predicting in latent space.
Foundation for the entire lecture.
[B2] [B3] Assran, M., Duval, Q., Misra, I., et al. (2023). Self-Supervised Learning from Images with a Joint-Embedding
Predictive Architecture (I-JEPA). CVPR 2023. arXiv:2301.08243.
First concrete JEPA implementation. Read to understand the context/target sampling design and how
collapse is avoided without data augmentation or negative pairs.
Bardes, A., Garrido, Q., Ponce, J., et al. (2024). Revisiting Feature Prediction for Learning Visual Representations
from Video (V-JEPA). arXiv:2404.08471.
Extends I-JEPA to video with spatiotemporal masking. Bridges static image JEPA to the action-conditioned
temporal setting used in LeWM.

[C1] Maes, L., Le Lidec, Q., Scieur, D., LeCun, Y., Balestriero, R. (2026). LeWorldModel: Stable End-to-End
Joint-Embedding Predictive Architecture from Pixels. arXiv:2603.19312.
Primary reading. The full architecture, two-loss training design, stability analysis, and control bench-
marks. Re-read Section 3 (architecture) carefully before the lecture.
[C2] Assran, M., Bardes, A., Fan, D., et al. (2025). V-JEPA 2: Self-Supervised Video Models Enable Understanding,
Prediction and Planning. arXiv:2506.09985.
Demonstrates JEPA at internet scale with an action-conditioned variant for robot planning. Shows that
the same framework used in LeWM scales to real manipulation without task-specific training data.

[E1] Zhang, W., Terver, B., Zholus, A., et al. (2026). Hierarchical Planning with Latent World Models.
arXiv:2604.03208.
Multi-scale temporal hierarchy within a shared JEPA latent space. Introduces macro-action encoders and
latent subgoal matching for long-horizon tasks.
[E2] Rao, P., Zhang, W., Balestriero, R., LeCun, Y., Loianno, G. (2026). SkyJEPA: Learning Long-Horizon World
Models for Zero-Shot Sim-to-Real Control of Quadrotors. arXiv:2606.23444.
Applies JEPA dynamics to a physical system with non-trivial kinematics. The physics-inspired prober—
recovering position and velocity from frozen latents—is particularly relevant to the Diff-Kinem-WM
project.



Multisensory robot learning and the Affordance Problem
by Sidharth Mathur

https://arxiv.org/pdf/2406.13640
https://arxiv.org/pdf/2408.06265
https://arxiv.org/pdf/2312.13469
https://arxiv.org/pdf/2503.02881
https://arxiv.org/pdf/2004.07400
https://www.cs.princeton.edu/techreports/2019/013.pdf
https://arxiv.org/pdf/2510.01433
https://arxiv.org/pdf/2603.23973


Accelerating Robot Reinforcement Learning through Adaptive Rewards and Teaching Strategies”
by Che-Jung Chuang

Wang et al. (2025) — Reward Training Wheels: Adaptive Auxiliary Rewards for Robotics Reinforcement Learning
https://arxiv.org/abs/2503.15724

Zhang et al. (2025) — ReWiND: Language-Guided Rewards Teach Robot Policies without New Demonstrations
https://proceedings.mlr.press/v305/zhang25a.html

Zhang et al. (2026) — Dream2Reward: Transition-Alignment Reward Models from Positive Demonstrations for Robotic Manipulation
https://arxiv.org/abs/2608.18787

Xu et al. (2018) — Meta-Gradient Reinforcement Learning
https://arxiv.org/abs/1805.09801

Foster et al. (2021) — Deep Adaptive Design: Amortizing Sequential Bayesian Experimental Design
https://proceedings.mlr.press/v139/foster21a.html


Differentiable Learning of Adaptive Spoken Interaction
by Chau Hoang

Audio MultiChallenge: A Multi-Turn Evaluation of Spoken Dialogue Systems on Natural Human Interaction
Multi-Faceted Interactivity Alignment in Full-Duplex Speech Models
STEERDUPLEX: Steerable Duplex Speech Dialogue Models
SoulX-Duplug: Plug-and-Play Streaming State Prediction Module for Realtime Full-Duplex Speech Conversation
PERSONAPLEX: VOICE AND ROLE CONTROL FOR FULL DUPLEX CONVERSATIONAL SPEECH MODELS


Differentiable Ancient Language Reconstruction
by Davy Ling

Bouchard-Côté, A., Hall, D., Griffiths, T. L., & Klein, D. (2013). Automated reconstruction of ancient languages using probabilistic models of sound change. PNAS, 110(11), 4224–4229.
Jang, E., Gu, S., & Poole, B. (2017). Categorical reparameterization with Gumbel-Softmax. ICLR 2017.

Meloni, C., Ravfogel, S., & Goldberg, Y. (2021). Ab Antiquo: Neural proto-language reconstruction. NAACL 2021.
Campbell, L. (2013). Historical Linguistics: An Introduction (3rd ed.), chapters on sound change and the comparative method. Edinburgh University Press.
Hayes, B., & Wilson, C. (2008). A maximum entropy model of phonotactics and phonotactic learning. Linguistic Inquiry, 39(3), 379–440.
Pulleyblank, E. G. (1984). Middle Chinese: A Study in Historical Phonology. University of British Columbia Press.


Optimizing Agentic Systems: From Textual Gradients to Reflective Evolution, focusing on TextGrad and GEPA.
by Feijiang Han

TextGrad: https://arxiv.org/abs/2406.07496
GEPA: https://arxiv.org/abs/2507.19457

- Skill evolution: SkillOpt
- Policy co-evolution through RL: R-Zero
- Memory-system evolution: MemEvolve
- Policy–skill co-evolution: SkillRL
- Harness evolution: Continual Harness
- Environment evolution: EnvHarness
- Recursive self-improvement: Hyperagents
- Multi-agent evolution: CORAL



Optimizing the Workflow of Multi-Agent Systems
by Mohammad Ghaemi

Abuzakuk, S., Kermarrec, A.-M., Sharma, R., Veski, R. M., & de Vos, M. (2026). Optimizing Agentic Workflows using Meta-tools. arXiv.Org.

Zhang, Z., Shi, K., Yuan, Z., Wang, Z., Ma, T., Murugesan, K., Galassi, V., Zhang, C., & Ye, Y. (2025). AgentRouter: A Knowledge-Graph-Guided LLM Router for Collaborative Multi-Agent Question Answering. https://doi.org/10.48550/arxiv.2510.05445

Paul, R. K., & Nandy, S. (2026). AgentRouter: Heterogeneous Model Routing for Cost-Optimal Multi-Step Agentic Workflows. https://doi.org/10.48550/arxiv.2609.22951

L. Yu, Y. Qiu, Q. Wang, X. Zhang and J. Wang, "Low Entropy Communication in Multi-Agent Reinforcement Learning," ICC 2023 - IEEE International Conference on Communications, Rome, Italy, 2023, pp. 5173-5178, doi: 10.1109/ICC45041.2023.10278640. keywords: {Quantization (signal);Reinforcement learning;Reliability theory;Entropy;Multi-agent systems},

Jabbar, Samir, et al. “DocAgent-XAI: An Entropy-Guided Agentic RAG System for Adaptive and Explainable Clinical History-Taking.” Artificial Intelligence in Healthcare, edited by Hao Ni and Daniele Cafolla, vol. 16875, Springer Nature Switzerland, 2027, pp. 501–15, https://doi.org/10.1007/978-3-032-35387-0_36.
I requested it from the library

Xiong, Cheng, et al. “DelphiAgent: A Trustworthy Multi-Agent Verification Framework for Automated Fact Verification.” Information Processing & Management [London], vol. 62, no. 6, no. 104241, November 2025, https://doi.org/10.1016/j.ipm.2025.104241.



Differentiable Model Predictive Control for Autonomous Vehicles with Nonlinear Tire Dynamics
by Sherry Wang

- Differentiable Dynamics for Autonomous Micro-Mobility Navigation
- DiffStack: A Differentiable and Modular Control Stack for Autonomous Vehicles
- Differentiable MPC for End-to-end Planning and Control
- A Stochastic Nonlinear Model Predictive Control with an Uncertainty Propagation Horizon for Autonomous Vehicle Motion Control
- Proactive Local-Minima-Free Robot Navigation: Blending Motion Prediction with Safe Control
- GM3: A General Physical Model for Micro-Mobility Vehicles
- Differentiable Weights-Varying Nonlinear MPC via Gradient-Based Policy Learning: An Autonomous Vehicle Guidance Example


Automatic Prompt Optimization for LLM Agents 
by Yi Zuo

Yuksekgonul et al., Optimizing generative AI by backpropagating language model feedback (Nature, 2025).
https://www.nature.com/articles/s41586-025-08661-4

Agrawal et al., GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning (ICLR, 2026).
https://proceedings.iclr.cc/paper_files/paper/2026/hash/0e9e708b6f48e14fd0ac29e167413f76-Abstract-Conference.html

Schneider et al., Hyperband-based Bayesian Optimization for Black-box Prompt Selection (ICML, 2025).
https://proceedings.mlr.press/v267/schneider25b.html

Zhao et al., Gradient-Guided Multi-Judge Prompt Optimization (ACL, 2026).
https://aclanthology.org/2026.acl-long.1089/


Differentiable Meshing
by Richard Chen & Yucheng Zhu

- DMesh 
- DMesh++ 
- MeshSplatting: Differentiable Rendering with Opaque Meshes 



Understanding Catastrophic Forgetting during Sequential Fine-Tuning
by Semih Akkoc

• Lee, Goldt, and Saxe, Continual Learning in the Teacher-Student Setup: Impact of Task Similarity, ICML 2021.
• Kirkpatrick et al., Overcoming Catastrophic Forgetting in Neural Networks, PNAS 2017.
• Hu et al., LoRA: Low-Rank Adaptation of Large Language Models, 2021.
• Koubbi, Hernandez, and Boussard, Understanding Catastrophic Forgetting in LoRA via Mean-Field Attention Dynamics, ICML 2026.
• Yang et al., Learning the Mechanism of Catastrophic Forgetting: A Perspective from Gradient Similarity, 2026.



Can visual representation understand acoustic information?
by Kan-Jen Cheng

REPRESENTATION LEARNING:
Xiaohua Zhai, Basil Mustafa, Alexander Kolesnikov, and Lucas Beyer. Sigmoid Loss for Language Image Pre-Training. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 11975–11986, 2023.

Daniel Bolya, Po-Yao Huang, Peize Sun, Jang Hyun Cho, Andrea Madotto, Chen Wei, Tengyu Ma, Jiale Zhi, Jathushan Rajasegaran, Hanoona Bangalath, Junke Wang, Marco Monteiro, Hu Xu, Shiyu Dong, Nikhila Ravi, Shang-Wen Li, Piotr Dollar, and Christoph Feichtenhofer. Perception ´ Encoder: The Best Visual Embeddings Are Not at the Output of the Network. In Advances in Neural Information Processing Systems (NeurIPS), pp. 60884–60937, 2025.

Sreyan Ghosh, Arushi Goel, Jaehyeon Kim, Sonal Kumar, Zhifeng Kong, Sang-gil Lee, ChaoHan Huck Yang, Ramani Duraiswami, Dinesh Manocha, Rafael Valle, and Bryan Catanzaro. Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models. In Advances in Neural Information Processing Systems (NeurIPS), pp. 41819–41886, 2025.

Wei-Cheng Tseng, Xuanru Zhou, Mingyue Huo, Yiwen Shao, Hao Zhang, and Dong Yu. Revisiting Audio-Language Pretraining for Learning General-Purpose Audio Representation. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL), pp. 34244–34263, 2026.

Kaiming He, Xinlei Chen, Saining Xie, Yanghao Li, Piotr Dollar, and Ross Girshick. Masked ´ Autoencoders Are Scalable Vision Learners. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16000–16009, 2022.

Adrien Bardes, Quentin Garrido, Jean Ponce, Xinlei Chen, Michael Rabbat, Yann LeCun, Mido
Assran, and Nicolas Ballas. Revisiting Feature Prediction for Learning Visual Representations
from Video. Transactions on Machine Learning Research, 2024.

Jiuhai Chen, Zhiyang Xu, Xichen Pan, Yushi Hu, Can Qin, Tom Goldstein, Lifu Huang, Tianyi
Zhou, Saining Xie, Silvio Savarese, Le Xue, Caiming Xiong, and Ran Xu. BLIP3-o: A Family
of Fully Open Unified Multimodal Models-Architecture, Training and Dataset. Computer Vision
in the Wild Workshop at the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025a.

VIDEO (+ TEXT) TO AUDIO GENERATION:
Ho Kei Cheng, Masato Ishii, Akio Hayakawa, Takashi Shibuya, Alexander Schwing, and Yuki Mitsufuji. MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 28901–28911, 2025.

Huadai Liu, Kaicheng Luo, Jialei Wang, Wen Wang, Qian Chen, Zhou Zhao, and Wei Xue.
ThinkSound: Chain-of-Thought Reasoning in Multimodal LLMs for Audio Generation and Editing. In Advances in Neural Information Processing Systems (NeurIPS), pp. 78526–78552, 2025a.

Huadai Liu, Kaicheng Luo, Wen Wang, Qian Chen, Peiwen Sun, Rongjie Huang, Xiangang Li,
Jieping Ye, and Wei Xue. PrismAudio: Decomposed Chain-of-Thought and Multi-Dimensional
Rewards for Video-to-Audio Generation. In International Conference on Learning Representations (ICLR), pp. 25176–25204, 2026a.

Yusheng Dai, Zehua Chen, Yuxuan Jiang, Qiuhong Ke, Jianfei Cai, and Jun Zhu. Omni2Sound:
Towards Unified Video-Text-to-Audio Generation. In Proceedings of the IEEE/CVF Conference
on Computer Vision and Pattern Recognition (CVPR), pp. 1661–1671, 2026.

Tingle Li, Siddharth Gururani, Kevin J. Shih, Gantavya Bhatt, Sang-gil Lee, Zhifeng Kong, Arushi Goel, Gopala Anumanchipalli, and Ming-Yu Liu. Benchmarking Single-Factor Physical Videoto-Audio Generation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1939–1949, 2026a.



Gradients Through Discrete Decisions
by Shanmuka Sadhu

Estimators for discrete variables
1. Bengio, Léonard, Courville, "Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation," 2013
2. Jang, Gu, Poole, "Categorical Reparameterization with Gumbel-Softmax," ICLR 2017
3. Maddison, Mnih, Teh, "The Concrete Distribution," ICLR 2017
4. Yin et al., "Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets," ICLR 2019

Structured and combinatorial decisions
5. Berthet et al., "Learning with Differentiable Perturbed Optimizers," NeurIPS 2020
6. Vlastelica et al., "Differentiation of Blackbox Combinatorial Solvers," ICLR 2020

Discrete decisions in fabrication and topology optimization
7. Bendsøe & Sigmund, Topology Optimization: Theory, Methods and Applications (SIMP chapter)
8. Wang, Lazarov, Sigmund, "On Projection Methods, Convergence and Robust Formulations in Topology Optimization," 2011
9. Stegmann & Lund, "Discrete Material Optimization of General Composite Shell Structures," 2005
10. Nindel et al., "A Gradient-Based Framework for 3D Print Appearance Optimization," SIGGRAPH 2021


Differentiation of Circuits 
by Ryan Whittaker

“Deep Differentiable Logic Gate Networks”, https://arxiv.org/pdf/2210.08277
“Evaluating analytic gradients on quantum hardware”, https://arxiv.org/pdf/1811.11184


Human Detection and Object Categorization based on WIFI CSI
by George Miao
 
1. G. Zhu et al. Wi-MoID: Human and Nonhuman Motion Discrimination Using WiFi With Edge Computing. IEEE Internet of Things Journal, 2024.
2. W. Wang et al. Understanding and Modeling of WiFi Signal Based Human Activity Recognition. ACM MobiCom, 2015.
3. G. Dong, K. Yang, and M. Srivastava. FuseFi: Combining Irregularly Sampled CSI from Diverse Communication Packets and Frequency Bands for Wi-Fi Sensing. IEEE Internet of Things Journal, 2026.
4. C. Feng et al. WiMi: Target Material Identification with Commodity Wi-Fi Devices. IEEE ICDCS, 2019.


Differentiable Programming for Genomics: Learning Cell Dynamics with Neural SDEs (scDiffEq)
by Dongkun Lee

- Required: Vinyard, Rasmussen, Li, Klein, Getz, Pinello. `Learning cell dynamics with neural differential equations.` Nature Machine Intelligence 7, 1969–1984 (2025). (https://doi.org/10.1038/s42256-025-01150-3)
- Recommended: Chen, Rubanova, Bettencourt, Duvenaud. `Neural Ordinary Differential Equations.` NeurIPS 2018. (https://arxiv.org/abs/1806.07366)
- Optional background:
  - Li, Wong, Chen, Duvenaud. `Scalable Gradients for Stochastic Differential Equations.` AISTATS 2020. (https://arxiv.org/abs/2001.01328)
  - Cuturi. `Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances.` NeurIPS 2013. (https://arxiv.org/abs/1306.0895)
  - Yeo, Saksena, Gifford. `Generative modeling of single-cell time series with PRESCIENT enables prediction of cell trajectories with interventions.` Nature Communications 12, 3222 (2021). (https://doi.org/10.1038/s41467-021-23518-w)


Reconstruction of Human-Object Interaction from Monocular Video
by Xiyi Chen

1. Do as I Do: Dexterous Manipulation Data from Everyday Human Videos
https://arxiv.org/abs/2606.19333
Main paper. Read in full, including Appendix A (reconstruction) and B (retargeting).
2. SAM 3D: 3Dfy Anything in Images
https://arxiv.org/abs/2511.16624
Object shape and pose backbone. Focus on the joint shape-pose generative formulation
and how occlusion is handled in training.
3. HaWoR: World-Space Hand Motion Reconstruction from Egocentric Videos
https://arxiv.org/abs/2501.02973
Hand tracking component. Focus on how world-space hand motion is recovered under
camera motion and out-of-view hands.
4. SPIDER: Scalable Physics-Informed Dexterous Retargeting
https://arxiv.org/abs/2511.09484
Retargeting framework. Focus on the sampling-based optimization formulation and
contact guidance.
5. FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects
https://arxiv.org/abs/2312.08344
The standard object tracker that Do as I Do replaces. Read to understand why
model-based tracking fails under occlusion and motion blur.


Neural SDEs
by Nishad Wajge

- https://arxiv.org/pdf/2202.02435
- https://arxiv.org/abs/1806.07366 (optional)
- https://arxiv.org/abs/2001.01328 (optional)


Towards Differentiable Phenomenological Modeling: Applications in Automated Analysis of Semiconductor Quantum Dot Qubit Measurements
by Daniel Schug

1. QD Autotuning:
J. P. Zwolak and J. M. Taylor, Colloquium: Advances in automation of quantum dot devices
control, Reviews of Modern Physics 95, 011006 (2023).
DOI: 10.1103/RevModPhys.95.011006
2. Explainable QD Analysis:
D. Schug et al., Automation of quantum dot measurement analysis via explainable machine
learning, Machine Learning: Science and Technology 6, 015024 (2025).
DOI: 10.1088/2632-2153/ada087
3. Industrially Fabricated QD Scaling:
HRL Quantum, A digitally controlled silicon quantum processing unit, arXiv:2604.16216 (2026).
URL: arXiv:2604.16216


Differentiable Real-to-Sim Reconstruction
by Andrew Wang

PAC-NeRF: Physics Augmented Continuum Neural Radiance Fields for Geometry-Agnostic System Identification — ICLR 2023
3D Gaussian Splatting for Real-Time Radiance Field Rendering — SIGGRAPH 2023
PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics — CVPR 2024
PhyRecon: Physically Plausible Neural Scene Reconstruction — NeurIPS 2024
PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videos — ICCV 2025
D-REX: Differentiable Real-to-Sim-to-Real Engine for Learning Dexterous Grasping — ICLR 2026


Exploring Role of Active-Gaze in Heterogeneous Agent Collaboration
by Atharvan Dogra

EyeRobot 2.0: Active Gaze for Precise Manipulation without Wrist Cameras 
https://eyerobot2.github.io/

HALO: Learning Human-Robot Collaboration via Heterogeneous-Agent Lyapunov Policy Optimization 
https://haozhang-thu.github.io/HALO/

EgoScale: Scaling Human Video to Unlock Dexterous Robot Intelligence
https://research.nvidia.com/labs/gear/egoscale/