Uploaded September 2024 | Updated September 2026, 1 week ago
Ashley Edwards, who was working at DeepMind when she co-authored the Genie paper and is now at Runway, covered several key aspects of the Genie AI system and its applications in video generation, robotics, and game creation.
MLST is sponsored by Brave:
The Brave Search API covers over 20 billion webpages, built from scratch without Big Tech biases or the recent extortionate price hikes on search API access. Perfect for AI model training and retrieval augmentated generation. Try it now - get 2,000 free queries monthly at brave.com/api.
Genie's approach to learning interactive environments, balancing compression and fidelity.
The use of latent action models and VQE models for video processing and tokenization.
Challenges in maintaining action consistency across frames and integrating text-to-image models.
Evaluation metrics for AI-generated content, such as FID and PS&R diff metrics.
The discussion also explored broader implications and applications:
The potential impact of AI video generation on content creation jobs.
Applications of Genie in game generation and robotics.
The use of foundation models in robotics and the differences between internet video data and specialized robotics data.
Challenges in mapping AI-generated actions to real-world robotic actions.
Ashley Edwards: ashedwards.github.io
TOC (*) are best bits
00:00:00 1. Intro to Genie & Brave Search API: Trade-offs & limitations *
00:02:26 2. Genie's Architecture: Latent action, VQE, video processing *
00:05:06 3. Genie's Constraints: Frame consistency & image model integration
00:07:26 4. Evaluation: FID, PS&R diff metrics & latent induction methods
00:09:44 5. AI Video Gen: Content creation impact, depth & parallax effects
00:11:39 6. Model Scaling: Training data impact & computational trade-offs
00:13:50 7. Game & Robotics Apps: Gamification & action mapping challenges *
00:16:16 8. Robotics Foundation Models: Action space & data considerations *
00:19:18 9. Mask-GPT & Video Frames: Real-time optimization, RL from videos
00:20:34 10. Research Challenges: AI value, efficiency vs. quality, safety
00:24:20 11. Future Dev: Efficiency improvements & fine-tuning strategies
Refs:
1. Genie (learning interactive environments from videos) / Ashley and DM collegues [00:01]
arxiv.org/abs/2402.15391
2. VQ-VAE (Vector Quantized Variational Autoencoder) / Aaron van den Oord, Oriol Vinyals, Koray Kavukcuoglu [02:43]
arxiv.org/abs/1711.00937
3. FID (Fréchet Inception Distance) metric / Martin Heusel et al. [07:37]
arxiv.org/abs/1706.08500
4. PS&R (Precision and Recall) metric / Mehdi S. M. Sajjadi et al. [08:02]
arxiv.org/abs/1806.00035
5. Vision Transformer (ViT) architecture / Alexey Dosovitskiy et al. [12:14]
arxiv.org/abs/2010.11929
6. Genie (robotics foundation models) / Google DeepMind [17:34]
https://deepmind.google/research/publications/60474/
7. Chelsea Finn's lab work on robotics datasets / Chelsea Finn [17:38]
https://ai.stanford.edu/~cbfinn/
8. Imitation from observation in reinforcement learning / YuXuan Liu [20:58]
arxiv.org/abs/1707.03374
9. Waymo's autonomous driving technology / Waymo [22:38]
waymo.com
10. Gen3 model release by Runway / Runway [23:48]
runwayml.com
11. Classifier-free guidance technique / Jonathan Ho and Tim Salimans [24:43]
arxiv.org/abs/2207.12598
Ashley Edwards, who was working at DeepMind when she co-authored the Genie paper and is now at Runway, covered several key aspects of the Genie AI system and its applications in video generation, robotics, and game creation.
MLST is sponsored by Brave:
The Brave Search API covers over 20 billion webpages, built from scratch without Big Tech biases or the recent extortionate price hikes on search API access. Perfect for AI model training and retrieval augmentated generation. Try it now - get 2,000 free queries monthly at brave.com/api.
Genie's approach to learning interactive environments, balancing compression and fidelity.
The use of latent action models and VQE models for video processing and tokenization.
Challenges in maintaining action consistency across frames and integrating text-to-image models.
Evaluation metrics for AI-generated content, such as FID and PS&R diff metrics.
The discussion also explored broader implications and applications:
The potential impact of AI video generation on content creation jobs.
Applications of Genie in game generation and robotics.
The use of foundation models in robotics and the differences between internet video data and specialized robotics data.
Challenges in mapping AI-generated actions to real-world robotic actions.
Ashley Edwards: ashedwards.github.io
TOC (*) are best bits
00:00:00 1. Intro to Genie & Brave Search API: Trade-offs & limitations *
00:02:26 2. Genie's Architecture: Latent action, VQE, video processing *
00:05:06 3. Genie's Constraints: Frame consistency & image model integration
00:07:26 4. Evaluation: FID, PS&R diff metrics & latent induction methods
00:09:44 5. AI Video Gen: Content creation impact, depth & parallax effects
00:11:39 6. Model Scaling: Training data impact & computational trade-offs
00:13:50 7. Game & Robotics Apps: Gamification & action mapping challenges *
00:16:16 8. Robotics Foundation Models: Action space & data considerations *
00:19:18 9. Mask-GPT & Video Frames: Real-time optimization, RL from videos
00:20:34 10. Research Challenges: AI value, efficiency vs. quality, safety
00:24:20 11. Future Dev: Efficiency improvements & fine-tuning strategies
Refs:
1. Genie (learning interactive environments from videos) / Ashley and DM collegues [00:01]
arxiv.org/abs/2402.15391
2. VQ-VAE (Vector Quantized Variational Autoencoder) / Aaron van den Oord, Oriol Vinyals, Koray Kavukcuoglu [02:43]
arxiv.org/abs/1711.00937
3. FID (Fréchet Inception Distance) metric / Martin Heusel et al. [07:37]
arxiv.org/abs/1706.08500
4. PS&R (Precision and Recall) metric / Mehdi S. M. Sajjadi et al. [08:02]
arxiv.org/abs/1806.00035
5. Vision Transformer (ViT) architecture / Alexey Dosovitskiy et al. [12:14]
arxiv.org/abs/2010.11929
6. Genie (robotics foundation models) / Google DeepMind [17:34]
https://deepmind.google/research/publications/60474/
7. Chelsea Finn's lab work on robotics datasets / Chelsea Finn [17:38]
https://ai.stanford.edu/~cbfinn/
8. Imitation from observation in reinforcement learning / YuXuan Liu [20:58]
arxiv.org/abs/1707.03374
9. Waymo's autonomous driving technology / Waymo [22:38]
waymo.com
10. Gen3 model release by Runway / Runway [23:48]
runwayml.com
11. Classifier-free guidance technique / Jonathan Ho and Tim Salimans [24:43]
arxiv.org/abs/2207.12598
![Neural Networks Are Elastic Origami! [Prof. Randall Balestriero]](https://i.ytimg.com/vi/l3O2J3LMxqI/mqdefault.jpg "Neural Networks Are Elastic Origami! [Prof. Randall Balestriero]
Professor Randall Balestriero joins us to discuss neural network geometry, spline theory, and emerging phenomena in deep learning, based on research presented at ICML. Topics include the delayed emergence of adversarial robustness in neural networks (grokking), geometric interpretations of neural networks via spline theory, and challenges in reconstruction learning. We also cover geometric analysis of Large Language Models (LLMs) for toxicity detection and the relationship between intrinsic dimensionality and model control in RLHF.
SPONSOR MESSAGES:
***
CentML offers competitive pricing for GenAI model deployment, with flexible options to suit a wide range of models, from small to large-scale deployments.
https://centml.ai/pricing/
Tufa AI Labs is a brand new research lab in Zurich started by Benjamin Crouzier focussed on o-series style reasoning and AGI. Are you interested in working on reasoning, or getting involved in their events?
Goto https://tufalabs.ai/
***
Show notes and transcript: https://www.dropbox.com/scl/fi/3lufge4upq5gy0ug75j4a/RANDALLSHOW.pdf?rlkey=nbemgpa0jhawt1e86rx7372e4&dl=0
TOC:
[00:00:00] Introduction
1. Neural Network Geometry and Spline Theory
[00:01:41] 1.1 Neural Network Geometry and Spline Theory
[00:07:41] 1.2 Deep Networks Always Grok
[00:11:39] 1.3 Grokking and Adversarial Robustness
[00:16:09] 1.4 Double Descent and Catastrophic Forgetting
2. Reconstruction Learning
[00:18:49] 2.1 Reconstruction Learning
[00:24:15] 2.2 Frequency Bias in Neural Networks
3. Geometric Analysis of Neural Networks
[00:29:02] 3.1 Geometric Analysis of Neural Networks
[00:34:41] 3.2 Adversarial Examples and Region Concentration
4. LLM Safety and Geometric Analysis
[00:40:05] 4.1 LLM Safety and Geometric Analysis
[00:46:11] 4.2 Toxicity Detection in LLMs
[00:52:24] 4.3 Intrinsic Dimensionality and Model Control
[00:58:07] 4.4 RLHF and High-Dimensional Spaces
5. Conclusion
[01:02:13] 5.1 Neural Tangent Kernel
[01:08:07] 5.2 Conclusion
REFS:
[00:01:35] Balestriero/Humayun – Deep network geometry & input space partitioning
https://arxiv.org/html/2408.04809v1
[00:03:55] Balestriero & Paris – Linking deep networks to adaptive spline operators
https://proceedings.mlr.press/v80/balestriero18b/balestriero18b.pdf
[00:13:55] Song et al. – Gradient-based white-box adversarial attacks
https://arxiv.org/abs/2012.14965
[00:16:05] Humayun, Balestriero & Baraniuk – Grokking phenomenon & emergent robustness
https://arxiv.org/abs/2402.15555
[00:18:25] Humayun – Training dynamics & double descent via linear region evolution
https://arxiv.org/abs/2310.12977
[00:20:15] Balestriero – Power diagram partitions in DNN decision boundaries
https://arxiv.org/abs/1905.08443
[00:23:00] Frankle & Carbin – Lottery Ticket Hypothesis for network pruning
https://arxiv.org/abs/1803.03635
[00:24:00] Belkin et al. – Double descent phenomenon in modern ML
https://arxiv.org/abs/1812.11118
[00:25:55] Balestriero et al. – Batch normalization’s regularization effects
https://arxiv.org/pdf/2209.14778
[00:29:35] EU – EU AI Act 2024 with compute restrictions
https://www.lw.com/admin/upload/SiteAttachments/EU-AI-Act-Navigating-a-Brave-New-World.pdf
[00:39:30] Humayun, Balestriero & Baraniuk – SplineCam: Visualizing deep network geometry
https://openaccess.thecvf.com/content/CVPR2023/papers/Humayun_SplineCam_Exact_Visualization_and_Characterization_of_Deep_Network_Geometry_and_CVPR_2023_paper.pdf
[00:40:40] Carlini – Trade-offs between adversarial robustness and accuracy
https://arxiv.org/abs/1902.06705
[00:44:55] Balestriero & LeCun – Limitations of reconstruction-based learning methods
https://raw.githubusercontent.com/mlresearch/v235/main/assets/balestriero24b/balestriero24b.pdf
[00:47:20] Balestriero & LeCun – Spectral analysis of neural network learning
https://proceedings.neurips.cc/paper_files/paper/2022/file/aa56c74513a5e35768a11f4e82dd7ffb-Paper-Conference.pdf
[00:49:45] He et al. – MAE: Masked Autoencoders for self-supervised learning
https://arxiv.org/abs/2111.06377
[00:54:50] Balestriero et al. – Geometric analysis of LLM layers for toxicity detection
https://arxiv.org/abs/2309.12312
[00:59:35] Balestriero et al. – Superior toxicity detection via geometric features
https://arxiv.org/html/2312.01648v2
[01:04:45] UofT ML – Self-attention control & context length effects
https://arxiv.org/abs/2310.04444
[01:11:55] Roberts – Foundations of deep learning theory
https://arxiv.org/abs/2106.10165
[01:15:40] Balestriero & Cha – Kolmogorov GAM Networks via spline partition theory
https://arxiv.org/pdf/2501.00704
[01:16:40] Various – Graph Kolmogorov-Arnold Networks (GKAN) extension
https://www.nature.com/articles/s41598-024-85083-8")
![The ARC Prize 2024 Winning Algorithm [Daniel Franzen and Jan Disselhoff]](https://i.ytimg.com/vi/mTX_sAq--zY/mqdefault.jpg "The ARC Prize 2024 Winning Algorithm [Daniel Franzen and Jan Disselhoff]
SPONSOR MESSAGES:
***
CentML offers competitive pricing for GenAI model deployment, with flexible options to suit a wide range of models, from small to large-scale deployments. Check out their super fast DeepSeek R1 hosting!
https://centml.ai/pricing/
Daniel Franzen and Jan Disselhoff the ARChitects won the ARC Prize 2024 with co-researcher David Hartmann, achieving a remarkable 53.5% accuracy on the ARC challenge using a 12-billion parameter language model. Filmed at Tufa Labs in Zurich, they walk through their solution architecture in detail: how they tokenized grid-based visual puzzles as text and fed them directly into an LLM, why test-time training on evaluation examples gave a major score boost, and how depth-first search over token probabilities outperformed greedy and beam search for solution generation.
The conversation gets into the surprising computational capabilities of language models on spatial reasoning tasks. The team found that LLMs could handle 2D grid reasoning without explicit positional encodings, that symmetry augmentations served as a powerful validation mechanism rather than a training aid, and that the models second-best solutions were often conceptually correct just wrong in a specific detail like rotation direction. They also discuss why their fine-tuned 12B model outperformed much larger foundation models, the role of LoRA in preventing catastrophic forgetting during test-time training, and what the entropy distribution of their search trees reveals about how the model represents uncertainty across different task types.
REFERENCES:
Paper:
[00:01:00] The ARChitects: Winning ARC Prize 2024 Solution
https://github.com/da-fr/arc-prize-2024/blob/main/the_architects.pdf
[00:03:38] Robustness of Analogical Reasoning in LLMs
https://arxiv.org/html/2411.14215
[00:14:58] Search Methods in Language Models
https://arxiv.org/html/2408.00724v2
[00:22:28] GPT-4 Code Solutions for ARC (50% SOTA)
https://redwoodresearch.substack.com/p/getting-50-sota-on-arc-agi-with-gpt
[00:53:08] Overcoming Catastrophic Forgetting
https://www.pnas.org/doi/10.1073/pnas.1611835114
[00:53:58] LoRA: Low-Rank Adaptation of Large Language Models
https://arxiv.org/abs/2106.09685
Tool:
[00:07:48] Re-ARC Dataset Generator
https://github.com/michaelhodel/re-arc
LINKS:
Full Transcript: https://app.rescript.info/share/57e5d773f2d0b195cbce7eee1f53aef2
Download PDF transcript: https://app.rescript.info/api/public/sessions/7772acbf1f11f44b/pdf
Daniel Franzen
https://github.com/da-fr
REFS
[00:01:05] Winning ARC 2024 solution using 12B param model, Franzen, Disselhoff, Hartmann
https://github.com/da-fr/arc-prize-2024/blob/main/the_architects.pdf
[00:07:50] Re-ARC dataset generator for ARC task variations, Michael Hodel
https://github.com/michaelhodel/re-arc
[00:22:30] GPT-4 guided code solutions for ARC tasks, Ryan Greenblatt
https://redwoodresearch.substack.com/p/getting-50-sota-on-arc-agi-with-gpt")
