Kullback-Leibler divergence-based knowledge distillation, a technique for transferring knowledge from teacher models to student models
| Name | Categories | Topics | References | Credibility | CreateDate | UpdateDate | Title | RelatedNotes | NavigationOrder | Created |
|---|---|---|---|---|---|---|---|---|---|---|
| 20260608_handoff_humanoid_agentic_whole_body_control | paper_analysis | embodied_ai, robotics, agent_architecture, multimodal, sim_to_real | caltech, ihmc, unitree, mixture_of_experts, kl_distillation | 100 | HANDOFF: Humanoid Agentic Task-Space Whole-Body Control via Distilled Complementary Teachers | Agent Memory: Characterization and System Implications of Stateful Long-Horizon Workloads, Navigating to objects in the real world | [object Object] | |||
| 20260706_demopsd_disagreement_modulated_policy_self_distillation | paper_analysis | reinforce_learning, reasoning, llm, self_evolving_agents | grpo, sciknoweval, kl_distillation, gpqa | 100 | DemoPSD: Disagreement-Modulated Policy Self-Distillation | rl_long_horizon_reasoning, vector_policy_optimization | [object Object] |