Picture for Nagarajan Natarajan

Nagarajan Natarajan

MASAI: Modular Architecture for Software-engineering AI Agents

Add code
Jun 17, 2024
Viaarxiv icon

Task Facet Learning: A Structured Approach to Prompt Optimization

Jun 15, 2024
Viaarxiv icon

Provably Robust DPO: Aligning Language Models with Noisy Feedback

Add code
Mar 01, 2024
Figure 1 for Provably Robust DPO: Aligning Language Models with Noisy Feedback
Figure 2 for Provably Robust DPO: Aligning Language Models with Noisy Feedback
Figure 3 for Provably Robust DPO: Aligning Language Models with Noisy Feedback
Viaarxiv icon

NoFunEval: Funny How Code LMs Falter on Requirements Beyond Functional Correctness

Add code
Feb 02, 2024
Viaarxiv icon

GAR-meets-RAG Paradigm for Zero-Shot Information Retrieval

Oct 31, 2023
Viaarxiv icon

Differentially Private Reward Estimation with Preference Feedback

Oct 30, 2023
Viaarxiv icon

Frustrated with Code Quality Issues? LLMs can Help!

Add code
Sep 22, 2023
Figure 1 for Frustrated with Code Quality Issues? LLMs can Help!
Figure 2 for Frustrated with Code Quality Issues? LLMs can Help!
Figure 3 for Frustrated with Code Quality Issues? LLMs can Help!
Figure 4 for Frustrated with Code Quality Issues? LLMs can Help!
Viaarxiv icon

Simulating Network Paths with Recurrent Buffering Units

Add code
Feb 23, 2022
Figure 1 for Simulating Network Paths with Recurrent Buffering Units
Figure 2 for Simulating Network Paths with Recurrent Buffering Units
Figure 3 for Simulating Network Paths with Recurrent Buffering Units
Figure 4 for Simulating Network Paths with Recurrent Buffering Units
Viaarxiv icon

Learning Accurate Decision Trees with Bandit Feedback via Quantized Gradient Descent

Add code
Feb 15, 2021
Figure 1 for Learning Accurate Decision Trees with Bandit Feedback via Quantized Gradient Descent
Figure 2 for Learning Accurate Decision Trees with Bandit Feedback via Quantized Gradient Descent
Figure 3 for Learning Accurate Decision Trees with Bandit Feedback via Quantized Gradient Descent
Figure 4 for Learning Accurate Decision Trees with Bandit Feedback via Quantized Gradient Descent
Viaarxiv icon

Optimal Regret Algorithm for Pseudo-1d Bandit Convex Optimization

Feb 15, 2021
Figure 1 for Optimal Regret Algorithm for Pseudo-1d Bandit Convex Optimization
Viaarxiv icon