Dashboard

e.g. PosteriorBench: From Point Estimates to Posterior Matching in Evaluating Generative Inverse Solvers

e.g. RAFT: A Stateful Retrieval-Augmented Framework for Troubleshooting Agents

e.g. An Empirical Study of Harness Design for Coding Agents

e.g. How Does Distribution Shift Shape Pretraining Gains in Neural PDE Surrogates?

e.g. Privacy-enhanced federated learning via asynchronous aggregation and local differential perturbation

e.g. SeqMoE: Toward Full-Load Performance via Predictive and Graph-Compatible MoE Offloading

e.g. A General Kernel Framework for Non-CND Distance Measures Using |D|-Dimensional Sparse Landmark Embeddings

e.g. Coding Agents with an Obstacle-Aware Harness for Safe Robot Manipulation

e.g. StageGuard: Learning Stage Transitions for Long-Horizon Robot Tasks via Agentic Distillation