Research

Validate Self-Imitation Learning recovery evidence for source boundaries, executable metrics, and mechanism-faithful proxy checks.

Execute one deterministic reduced Soft Actor-Critic critic actor and target update for recovery evidence.

Validate reduced PPO recovery evidence with mechanism checks, source-boundary checks, and pass-rate metrics.

Evaluate Go-Explore archived trajectories with deterministic replay and bounded perturbation checks for recovery evidence.

Build deterministic periodic PDE benchmarks for PINN failure-mode recovery experiments.

Detect induction-head copying behavior on repeated token sequences with explicit mechanism checks.

Run a bounded mechanism-faithful proxy experiment for FFN value-vector concept promotion using generated skills.

Run a bounded mechanism-faithful proxy experiment for maximum softmax OOD detection recovery artifacts.

Decide whether a declared soft-mode proxy exercises the Accuracy on the Line mechanism.

Run a bounded mechanism-faithful proxy experiment for probabilistic bilevel coreset selection with executable evidence.

Validate paper-target metadata, aggregate influence tolerance, and observed pruning metric gaps for generalization-influence pruning.

Compute EL2N and GraNd example-importance scores for supervised classification pruning experiments.

Compute reduced NLE task rewards and clipping for symbolic recovery experiments.

Validate OPAL recovery evidence, mechanism checks, source boundaries, and proxy metric comparison.

Train or check an OPAL-style primitive autoencoding objective with reconstruction loss and KL-style prior matching.

Run a bounded soft-mode reduced recovery experiment for forward-backward representations with executable evidence.

Execute a bounded D4RL-style offline recovery proxy with fixed-dataset training and normalized-score evidence.

Classify offline RL datasets by D4RL challenge properties and explain benchmark implications from metadata.

Apply noisy classifier log-probability gradients to reverse diffusion steps with explicit guidance-scale checks.

Run a bounded DDPM-PA proxy optimizer step and emit mechanism-faithful recovery traces and metrics.

Run a bounded soft-mode proxy DDPM recovery experiment using generated module skills.

Build DDPM beta schedules and closed-form forward noising coefficients for recovery experiments.

Compute diversity and correspondence diagnostics for few-shot image generation recovery experiments.

Compute cross-domain distance consistency softmax-KL losses for few-shot generator adaptation experiments.