Pre-training interventions, ex post facto: Grafting model beliefs across checkpoints
Research
Research News
New papers, breakthroughs and academic AI research
Localizing Transfer Between Memorization Tasks
Research
Training-Aware Target Coverage for Synthetic Data Selection
Research
Signal-Noise Factorization Isolates Nuisance Variation into Removable Subspaces
Research
FedCKA: Representation-Guided Layer Personalization for Federated 3D Perception Across Driving Domains
Research
Revisiting Cross-Reconstruction for Generalizable Deepfake Detection
Research
A Verifier Can Leak the Answer: Diagnosability Before Optimization in Closed-Loop Agent Debugging
Research
Increasing Width Allows Greedy Layer-wise Training to Rival End-to-End Backpropagation in Self-Supervised Learning
Research
Scalable Multi-Task Inverse Reinforcement Learning
Research
Learning Goal-Reaching Quasimetric Geometry From Finite-Time Reachability
Research
Hob-VL: A Benchmark for Visually Grounded Boolean Reasoning
Research
Pushing CPU Speech Synthesis to the Wall: Extreme Inference Tuning under Serverless Architecture and Billing
Research