Picture for Saravan Rajmohan

Saravan Rajmohan

Distill Not Only Data but Also Rewards: Can Smaller Language Models Surpass Larger Ones?

Add code
Feb 26, 2025
Viaarxiv icon

VEM: Environment-Free Exploration for Training GUI Agent with Value Environment Model

Add code
Feb 26, 2025
Viaarxiv icon

AMPO: Active Multi-Preference Optimization

Add code
Feb 25, 2025
Viaarxiv icon

Lean and Mean: Decoupled Value Policy Optimization with Global Value Guidance

Add code
Feb 24, 2025
Viaarxiv icon

Minerva: A Programmable Memory Test Benchmark for Language Models

Add code
Feb 05, 2025
Viaarxiv icon

MEETING DELEGATE: Benchmarking LLMs on Attending Meetings on Our Behalf

Add code
Feb 05, 2025
Viaarxiv icon

Enabling Autonomic Microservice Management through Self-Learning Agents

Add code
Jan 31, 2025
Figure 1 for Enabling Autonomic Microservice Management through Self-Learning Agents
Figure 2 for Enabling Autonomic Microservice Management through Self-Learning Agents
Figure 3 for Enabling Autonomic Microservice Management through Self-Learning Agents
Figure 4 for Enabling Autonomic Microservice Management through Self-Learning Agents
Viaarxiv icon

Skeleton-Guided-Translation: A Benchmarking Framework for Code Repository Translation with Fine-Grained Quality Evaluation

Add code
Jan 27, 2025
Figure 1 for Skeleton-Guided-Translation: A Benchmarking Framework for Code Repository Translation with Fine-Grained Quality Evaluation
Figure 2 for Skeleton-Guided-Translation: A Benchmarking Framework for Code Repository Translation with Fine-Grained Quality Evaluation
Figure 3 for Skeleton-Guided-Translation: A Benchmarking Framework for Code Repository Translation with Fine-Grained Quality Evaluation
Figure 4 for Skeleton-Guided-Translation: A Benchmarking Framework for Code Repository Translation with Fine-Grained Quality Evaluation
Viaarxiv icon

DI-BENCH: Benchmarking Large Language Models on Dependency Inference with Testable Repositories at Scale

Add code
Jan 23, 2025
Viaarxiv icon

AIOpsLab: A Holistic Framework to Evaluate AI Agents for Enabling Autonomous Clouds

Add code
Jan 12, 2025
Figure 1 for AIOpsLab: A Holistic Framework to Evaluate AI Agents for Enabling Autonomous Clouds
Figure 2 for AIOpsLab: A Holistic Framework to Evaluate AI Agents for Enabling Autonomous Clouds
Figure 3 for AIOpsLab: A Holistic Framework to Evaluate AI Agents for Enabling Autonomous Clouds
Figure 4 for AIOpsLab: A Holistic Framework to Evaluate AI Agents for Enabling Autonomous Clouds
Viaarxiv icon