Picture for Vedant Nanda

Vedant Nanda

Understanding Memorisation in LLMs: Dynamics, Influencing Factors, and Implications

Add code
Jul 27, 2024
Viaarxiv icon

Lawma: The Power of Specialization for Legal Tasks

Add code
Jul 23, 2024
Viaarxiv icon

Understanding the Role of Invariance in Transfer Learning

Add code
Jul 05, 2024
Viaarxiv icon

Towards Reliable Latent Knowledge Estimation in LLMs: In-Context Learning vs. Prompting Based Factual Knowledge Extraction

Add code
Apr 19, 2024
Viaarxiv icon

What Happens During Finetuning of Vision Transformers: An Invariance Based Investigation

Add code
Jul 12, 2023
Viaarxiv icon

Diffused Redundancy in Pre-trained Representations

Add code
May 31, 2023
Viaarxiv icon

Pointwise Representational Similarity

Add code
May 30, 2023
Viaarxiv icon

Measuring Representational Robustness of Neural Networks Through Shared Invariances

Add code
Jun 23, 2022
Figure 1 for Measuring Representational Robustness of Neural Networks Through Shared Invariances
Figure 2 for Measuring Representational Robustness of Neural Networks Through Shared Invariances
Figure 3 for Measuring Representational Robustness of Neural Networks Through Shared Invariances
Figure 4 for Measuring Representational Robustness of Neural Networks Through Shared Invariances
Viaarxiv icon

Rawlsian Fairness in Online Bipartite Matching: Two-sided, Group, and Individual

Add code
Jan 16, 2022
Figure 1 for Rawlsian Fairness in Online Bipartite Matching: Two-sided, Group, and Individual
Figure 2 for Rawlsian Fairness in Online Bipartite Matching: Two-sided, Group, and Individual
Viaarxiv icon

Exploring Alignment of Representations with Human Perception

Add code
Nov 29, 2021
Figure 1 for Exploring Alignment of Representations with Human Perception
Figure 2 for Exploring Alignment of Representations with Human Perception
Figure 3 for Exploring Alignment of Representations with Human Perception
Figure 4 for Exploring Alignment of Representations with Human Perception
Viaarxiv icon