Interpreting and Steering a Text-to-Speech Language Model with Sparse Autoencoders Paper • 2606.10029 • Published 4 days ago • 11
Interpreting and Steering a Text-to-Speech Language Model with Sparse Autoencoders Paper • 2606.10029 • Published 4 days ago • 11
A Geometric Account of Activation Steering through Angle-Norm Decomposition Paper • 2606.06735 • Published 8 days ago • 20
Whisper Hallucination Detection and Mitigation via Hidden Representation Steering and Sparse AutoEncoders Paper • 2606.07473 • Published 7 days ago • 12
A Geometric Account of Activation Steering through Angle-Norm Decomposition Paper • 2606.06735 • Published 8 days ago • 20
Whisper Hallucination Detection and Mitigation via Hidden Representation Steering and Sparse AutoEncoders Paper • 2606.07473 • Published 7 days ago • 12
A Geometric Account of Activation Steering through Angle-Norm Decomposition Paper • 2606.06735 • Published 8 days ago • 20
Whisper Hallucination Detection and Mitigation via Hidden Representation Steering and Sparse AutoEncoders Paper • 2606.07473 • Published 7 days ago • 12