Forgetting That Sticks: Quantization-Permanent Unlearning via Circuit Attribution
Paper • 2605.15138 • Published • 3
AI & ML interests
Frontier research around Safe and aligned intelligence
Recent Activity
View all activity
Papers
Forgetting That Sticks: Quantization-Permanent Unlearning via Circuit Attribution
$C$-$ΔΘ$: Circuit-Restricted Weight Arithmetic for Selective Refusal
pratinavsetharyaÂ
submitted a
paper to Daily Papers about 22 hours ago
pratinavsetharyaÂ
authored 2
papers 3 months ago
pratinavsetharyaÂ
submitted a
paper to Daily Papers 3 months ago
pratinavsetharyaÂ
authored 3
papers 6 months ago
Orion-MSP: Multi-Scale Sparse Attention for Tabular In-Context Learning
Paper • 2511.02818 • Published • 15
TabTune: A Unified Library for Inference and Fine-Tuning Tabular Foundation Models
Paper • 2511.02802 • Published • 16
Interpretability-Aware Pruning for Efficient Medical Image Analysis
Paper • 2507.08330 • Published
pratinavsetharyaÂ
authored 5
papers 7 months ago
Alberta Wells Dataset: Pinpointing Oil and Gas Wells from Satellite Imagery
Paper • 2410.09032 • Published
Interpretability as Alignment: Making Internal Understanding a Design Principle
Paper • 2509.08592 • Published
SELF-PERCEPT: Introspection Improves Large Language Models' Detection of Multi-Person Mental Manipulation in Conversations
Paper • 2505.20679 • Published
xai_evals : A Framework for Evaluating Post-Hoc Local Explanation Methods
Paper • 2502.03014 • Published
DLBacktrace: A Model Agnostic Explainability for any Deep Learning Models
Paper • 2411.12643 • Published
pratinavsetharyaÂ
updated a
Space 7 months ago
pratinavsetharyaÂ
published a
Space 7 months ago