DAGR: State-Conditioned Goal Representations via Difference-Aware Goal Cross-Attention
Research
Research News
New papers, breakthroughs and academic AI research
Learning to Rank Tensor Network Contraction Plans for GPU-Accelerated Quantum Circuit Simulation
Research
Weights Read and Write Features: Scalable Parameter Decomposition Grounded in Activation Space
Research
Geometric Data Perturbation with Noisy-Anchor Alignment for Privacy-Preserving Collaborative Learning
Research
Exact Risk Ratios for Weighted Data Selection in Linear Regression
Research
Steering Recurrent Reasoners at Inference Time with Readout Feedback
Research
Exact Recovery Thresholds for Weighted Data Selection in Vector-Valued Linear Regression
Research
Towards Identifying the Dataset Biases Causing Phantom Transfer
Research
Why Backdooring Neural Networks is so Easy?
Research
SCOPE: Observation-Conditioned Full-Target Prediction for Sparse PDE Inference
Research
Graph-Conditioned On-Policy Agent Distillation from Off-the-Shelf Teachers
Research
Variance-reduced accelerated methods for decentralized stochastic double-regularized nonconvex strongly-concave minimax problems
Research