Picture for Sarath Chandar

Sarath Chandar

A Generalist Hanabi Agent

Add code
Mar 17, 2025
Viaarxiv icon

Do Large Language Models Know How Much They Know?

Add code
Feb 26, 2025
Viaarxiv icon

NeoBERT: A Next-Generation BERT

Add code
Feb 26, 2025
Viaarxiv icon

Torque-Aware Momentum

Add code
Dec 25, 2024
Viaarxiv icon

Too Big to Fool: Resisting Deception in Language Models

Add code
Dec 13, 2024
Viaarxiv icon

Combining Domain and Alignment Vectors to Achieve Better Knowledge-Safety Trade-offs in LLMs

Add code
Nov 11, 2024
Figure 1 for Combining Domain and Alignment Vectors to Achieve Better Knowledge-Safety Trade-offs in LLMs
Figure 2 for Combining Domain and Alignment Vectors to Achieve Better Knowledge-Safety Trade-offs in LLMs
Figure 3 for Combining Domain and Alignment Vectors to Achieve Better Knowledge-Safety Trade-offs in LLMs
Figure 4 for Combining Domain and Alignment Vectors to Achieve Better Knowledge-Safety Trade-offs in LLMs
Viaarxiv icon

Do Robot Snakes Dream like Electric Sheep? Investigating the Effects of Architectural Inductive Biases on Hallucination

Add code
Oct 22, 2024
Figure 1 for Do Robot Snakes Dream like Electric Sheep? Investigating the Effects of Architectural Inductive Biases on Hallucination
Figure 2 for Do Robot Snakes Dream like Electric Sheep? Investigating the Effects of Architectural Inductive Biases on Hallucination
Figure 3 for Do Robot Snakes Dream like Electric Sheep? Investigating the Effects of Architectural Inductive Biases on Hallucination
Figure 4 for Do Robot Snakes Dream like Electric Sheep? Investigating the Effects of Architectural Inductive Biases on Hallucination
Viaarxiv icon

Toward Debugging Deep Reinforcement Learning Programs with RLExplorer

Add code
Oct 06, 2024
Figure 1 for Toward Debugging Deep Reinforcement Learning Programs with RLExplorer
Figure 2 for Toward Debugging Deep Reinforcement Learning Programs with RLExplorer
Figure 3 for Toward Debugging Deep Reinforcement Learning Programs with RLExplorer
Figure 4 for Toward Debugging Deep Reinforcement Learning Programs with RLExplorer
Viaarxiv icon

Context-Aware Assistant Selection for Improved Inference Acceleration with Large Language Models

Add code
Aug 16, 2024
Viaarxiv icon

Exploring Quantization for Efficient Pre-Training of Transformer Language Models

Add code
Jul 16, 2024
Figure 1 for Exploring Quantization for Efficient Pre-Training of Transformer Language Models
Figure 2 for Exploring Quantization for Efficient Pre-Training of Transformer Language Models
Figure 3 for Exploring Quantization for Efficient Pre-Training of Transformer Language Models
Figure 4 for Exploring Quantization for Efficient Pre-Training of Transformer Language Models
Viaarxiv icon