Podcast Episodes
Back to SearchRobix: A Unified Model for Robot Interaction, Reasoning and Planning
A single vision-language model that unifies reasoning, task planning, and human-robot interaction for complex instructions and long-horizon tasks.
3 months, 3 weeks ago
Robotic World Model: Learning to Simulate for Robust Robot Control
Presents a neural network-based world model for model-based reinforcement learning in robotics, focusing on sim-to-real transfer for quadrupedal and …
3 months, 3 weeks ago
AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization
Embodied egocentric simulation framework that controls first-person worlds with 3D human motion and customizes evolving scenes via pose-anchored view…
3 months, 3 weeks ago
ArtiFixer: Few-Step Diffusion for 3D Scene Reconstruction
Few-step auto-regressive diffusion model that converts broken 3D reconstructions into fully realized scenes, outperforming prior methods by 1-3 dB PS…
3 months, 3 weeks ago
Deployment-Time Memorization in Foundation-Model Agents
Examines memorization phenomena that occur during deployment of foundation model agents in practical applications.
3 months, 3 weeks ago
Adversarial Machine Learning: Taxonomy, Threat Models, and Mitigation Strategies in Deep Neural Networks
Focuses on security aspects of deep neural networks, providing taxonomy and mitigation strategies for adversarial attacks.
3 months, 4 weeks ago
SoCRATES: Evaluating LLM Mediators in Conflict Scenarios
First comprehensive framework for evaluating LLM mediators in real-time, emotional, socio-cognitive scenarios.
3 months, 4 weeks ago
Unembedding Matrix as a Feature Lens: Unlocking Better Text Embeddings
Improves embedding quality without extra training by using the unembedding matrix as a feature lens for text embeddings.
3 months, 4 weeks ago
LeanMarathon: Autonomous Formalization of Math Proofs on Erdős Problems
Presents an autonomous system for formalizing mathematical proofs, specifically targeting Erdős problems. Demonstrates automated proof formalization …
3 months, 4 weeks 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 …
3 months, 4 weeks ago