Podcast Episodes
Back to SearchLeanMarathon: Autonomous Formalization of Math Proofs on Erdős Problems
Presents an autonomous system for formalizing mathematical proofs, specifically targeting Erdős problems. Demonstrates automated proof formalization …
4 months ago
Deep Research Agents: Survey and Roadmap for Autonomous AI Research
Provides a comprehensive taxonomy, benchmarks, and future directions for autonomous AI research agents. Examines systematic approaches to developing …
4 months ago
Cosmos 3: Omnimodal World Models for Physical AI
Omnimodal world models explicitly designed for Physical AI and robotics applications. Enables improved simulation and control for robotic systems thr…
4 months ago
Humanoid-GPT: GPT-Style Transformer for Zero-Shot Dynamic Humanoid Control
GPT-style Transformer trained on 2 billion motion frames enabling zero-shot dynamic humanoid control for tasks like soccer, dancing, and digging on r…
4 months ago
Bending Paper, Shaping Dexterity: The Robotic Origami Challenge
New IROS benchmark providing 500+ teleoperation episodes and physically accurate simulation assets for training policies that outperform human origam…
4 months ago
GraspGen-X: A Foundation Model for Zero-Shot 6-DoF Grasping
First foundation model for zero-shot grasping trained on billions of simulated grasps, enabling generalized manipulation without task-specific traini…
4 months ago
When Does Deep RL Beat Calibrated Baselines?
Benchmark study examining when deep reinforcement learning outperforms calibrated baseline methods in adaptive resource control tasks.
4 months ago
Training Deep Networks as Random Effects: An Optimization–Inference Duality
Explores training dynamics of deep neural networks through a statistical lens, examining the duality between optimization and inference perspectives.
4 months ago
Generative Depth Supervision for Embodied Vision-Language Models
Vision-language model that adds generative depth prediction during pre-training for physical grounding; achieves SOTA on embodied benchiments and tra…
4 months ago
PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation
Presents a 3D point-cloud-based world model trained on mixed real/sim data that enables zero-shot grasping and articulated object handling on real ro…
4 months, 1 week ago