Picture for Sham Kakade

Sham Kakade

Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems

Feb 27, 2024
Viaarxiv icon

Q-Probe: A Lightweight Approach to Reward Maximization for Language Models

Add code
Feb 22, 2024
Viaarxiv icon

A Study on the Calibration of In-context Learning

Add code
Dec 11, 2023
Figure 1 for A Study on the Calibration of In-context Learning
Figure 2 for A Study on the Calibration of In-context Learning
Figure 3 for A Study on the Calibration of In-context Learning
Figure 4 for A Study on the Calibration of In-context Learning
Viaarxiv icon

Feature emergence via margin maximization: case studies in algebraic tasks

Nov 13, 2023
Figure 1 for Feature emergence via margin maximization: case studies in algebraic tasks
Figure 2 for Feature emergence via margin maximization: case studies in algebraic tasks
Figure 3 for Feature emergence via margin maximization: case studies in algebraic tasks
Figure 4 for Feature emergence via margin maximization: case studies in algebraic tasks
Viaarxiv icon

Learning an Inventory Control Policy with General Inventory Arrival Dynamics

Oct 26, 2023
Figure 1 for Learning an Inventory Control Policy with General Inventory Arrival Dynamics
Figure 2 for Learning an Inventory Control Policy with General Inventory Arrival Dynamics
Figure 3 for Learning an Inventory Control Policy with General Inventory Arrival Dynamics
Figure 4 for Learning an Inventory Control Policy with General Inventory Arrival Dynamics
Viaarxiv icon

MatFormer: Nested Transformer for Elastic Inference

Oct 11, 2023
Figure 1 for MatFormer: Nested Transformer for Elastic Inference
Figure 2 for MatFormer: Nested Transformer for Elastic Inference
Figure 3 for MatFormer: Nested Transformer for Elastic Inference
Figure 4 for MatFormer: Nested Transformer for Elastic Inference
Viaarxiv icon

Pareto Frontiers in Neural Feature Learning: Data, Compute, Width, and Luck

Sep 07, 2023
Figure 1 for Pareto Frontiers in Neural Feature Learning: Data, Compute, Width, and Luck
Figure 2 for Pareto Frontiers in Neural Feature Learning: Data, Compute, Width, and Luck
Figure 3 for Pareto Frontiers in Neural Feature Learning: Data, Compute, Width, and Luck
Figure 4 for Pareto Frontiers in Neural Feature Learning: Data, Compute, Width, and Luck
Viaarxiv icon

Scaling Laws for Imitation Learning in NetHack

Add code
Jul 18, 2023
Figure 1 for Scaling Laws for Imitation Learning in NetHack
Figure 2 for Scaling Laws for Imitation Learning in NetHack
Figure 3 for Scaling Laws for Imitation Learning in NetHack
Figure 4 for Scaling Laws for Imitation Learning in NetHack
Viaarxiv icon

Beyond Implicit Bias: The Insignificance of SGD Noise in Online Learning

Add code
Jun 14, 2023
Figure 1 for Beyond Implicit Bias: The Insignificance of SGD Noise in Online Learning
Figure 2 for Beyond Implicit Bias: The Insignificance of SGD Noise in Online Learning
Figure 3 for Beyond Implicit Bias: The Insignificance of SGD Noise in Online Learning
Figure 4 for Beyond Implicit Bias: The Insignificance of SGD Noise in Online Learning
Viaarxiv icon

AdANNS: A Framework for Adaptive Semantic Search

Add code
May 30, 2023
Figure 1 for AdANNS: A Framework for Adaptive Semantic Search
Figure 2 for AdANNS: A Framework for Adaptive Semantic Search
Figure 3 for AdANNS: A Framework for Adaptive Semantic Search
Figure 4 for AdANNS: A Framework for Adaptive Semantic Search
Viaarxiv icon