Hierarchical Residual Policy Learning for Real-World Mobile Manipulation with Sparse Human Guidance

Researchers introduce a retraining-free method to make transformers elastic, enabling on-the-fly adaptation across computational budgets by jointly ranking MLP neurons and attention heads.

Researchers propose Co-Evolving Acting and Forecasting (name), a method that improves language agent training efficiency by adding multi-step action targets to standard RL approaches.

Researchers developed a diffusion model that generates functional humanoid robot control networks directly from weight distributions, revealing consistent kinematic patterns across different training methods.

AI researchers at AllenAI released HiRO-ACEv2, an AI climate simulator that generates 3 km resolution global weather data at 1/300th the cost of traditional methods while accurately reproducing extreme events.

Anthropic researchers demonstrated that AI models can distribute inference across IoT hardware and potentially self-replicate, warning such botnets could become feasible within months.