Picture for Jin Peng Zhou

Jin Peng Zhou

INPROVF: Leveraging Large Language Models to Repair High-level Robot Controllers from Assumption Violations

Add code
Mar 17, 2025
Viaarxiv icon

$Q\sharp$: Provably Optimal Distributional RL for LLM Post-Training

Add code
Feb 27, 2025
Viaarxiv icon

Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond

Add code
Feb 26, 2025
Viaarxiv icon

Enhancing Cognitive Diagnosis by Modeling Learner Cognitive Structure State

Add code
Dec 27, 2024
Viaarxiv icon

Towards More Robust Retrieval-Augmented Generation: Evaluating RAG Under Adversarial Poisoning Attacks

Add code
Dec 21, 2024
Viaarxiv icon

Gemma 2: Improving Open Language Models at a Practical Size

Add code
Aug 02, 2024
Figure 1 for Gemma 2: Improving Open Language Models at a Practical Size
Figure 2 for Gemma 2: Improving Open Language Models at a Practical Size
Figure 3 for Gemma 2: Improving Open Language Models at a Practical Size
Figure 4 for Gemma 2: Improving Open Language Models at a Practical Size
Viaarxiv icon

On Speeding Up Language Model Evaluation

Add code
Jul 08, 2024
Viaarxiv icon

Orchestrating LLMs with Different Personalizations

Add code
Jul 04, 2024
Viaarxiv icon

Code Repair with LLMs gives an Exploration-Exploitation Tradeoff

Add code
May 26, 2024
Viaarxiv icon

Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization

Add code
Mar 26, 2024
Viaarxiv icon