Podcast Episodes
Back to SearchThe Llama 3 Herd of Models
Comprehensive technical report on the Llama 3 family, covering architecture, training at scale, multimodal extensions, and real-world impact. Details…
4 months, 2 weeks ago
LATENT: Learning Athletic Humanoid Tennis Skills from Imperfect Human Motion Data
Introduces a three-stage pipeline that extracts a latent action space from low-quality human tennis demonstrations, then trains a high-level policy i…
4 months, 2 weeks ago
AnyFlow: Any-Step Video Diffusion for Predictive World Modeling
First any-step video diffusion framework using flow maps, allowing a single model to adapt to arbitrary inference budgets for scalable high-quality v…
4 months, 3 weeks ago
# Robotics: The Endgame
Technical roadmap mirroring LLM scaling: critiques VLAs, advocates video world models as second pretraining phase, introduces World Action Models (WA…
4 months, 3 weeks ago
Claw-Eval: Toward Trustworthy and Transparent Evaluation of Autonomous Agents
Benchmark with 2,159 rubric items across 300 tasks using trajectory-aware grading and 3-trial Pass^3 scoring to mitigate luck. Evaluates agent reliab…
5 months, 3 weeks ago
LIBERO-Para: Paraphrase Robustness in Robotic Manipulation
Reveals paraphrase fragility in VLAs causing 22-52% success drops due to task misidentification. Introduces PRIDE metric weighting success by paraphr…
5 months, 3 weeks ago
YOR: Your Own Mobile Manipulator for Generalizable Robotics
Low-cost mobile manipulator design and training strategies for broad generalization in real-world tasks.
5 months, 4 weeks ago
EgoSim: Egocentric World Simulator for Embodied Interaction Generation
Closed-loop egocentric video simulator maintaining persistent 3D scene state for consistent interactions, enabling cross-embodiment transfer from hum…
5 months, 4 weeks ago
Accelerating Video World Models: From Generative Videos to Real-Time Simulators
Comprehensive survey taxonomizing efficient architectures/algorithms for video world models as simulators, targeting compute bottlenecks in embodied …
5 months, 4 weeks ago
From Tokens to Thoughts: Continuous Latent Reasoning in Large Models and Robot Control
Curated collection of 100+ works surveying shift to continuous latent spaces in LLMs/VLMs/VLAs for improved reasoning over discrete tokens, with rele…
5 months, 4 weeks ago