Picture for Ali Payani

Ali Payani

Polo

InfantAgent-Next: A Multimodal Generalist Agent for Automated Computer Interaction

Add code
May 16, 2025
Viaarxiv icon

Program Semantic Inequivalence Game with Large Language Models

Add code
May 02, 2025
Viaarxiv icon

Personalized Federated Fine-tuning for Heterogeneous Data: An Automatic Rank Learning Approach via Two-Level LoRA

Add code
Mar 05, 2025
Figure 1 for Personalized Federated Fine-tuning for Heterogeneous Data: An Automatic Rank Learning Approach via Two-Level LoRA
Figure 2 for Personalized Federated Fine-tuning for Heterogeneous Data: An Automatic Rank Learning Approach via Two-Level LoRA
Figure 3 for Personalized Federated Fine-tuning for Heterogeneous Data: An Automatic Rank Learning Approach via Two-Level LoRA
Figure 4 for Personalized Federated Fine-tuning for Heterogeneous Data: An Automatic Rank Learning Approach via Two-Level LoRA
Viaarxiv icon

Benchmarking LLMs for Political Science: A United Nations Perspective

Add code
Feb 19, 2025
Viaarxiv icon

SAIF: A Sparse Autoencoder Framework for Interpreting and Steering Instruction Following of Language Models

Add code
Feb 17, 2025
Viaarxiv icon

Investigating the Shortcomings of LLMs in Step-by-Step Legal Reasoning

Add code
Feb 08, 2025
Figure 1 for Investigating the Shortcomings of LLMs in Step-by-Step Legal Reasoning
Figure 2 for Investigating the Shortcomings of LLMs in Step-by-Step Legal Reasoning
Figure 3 for Investigating the Shortcomings of LLMs in Step-by-Step Legal Reasoning
Figure 4 for Investigating the Shortcomings of LLMs in Step-by-Step Legal Reasoning
Viaarxiv icon

Effective Guidance for Model Attention with Simple Yes-no Annotations

Add code
Oct 29, 2024
Figure 1 for Effective Guidance for Model Attention with Simple Yes-no Annotations
Figure 2 for Effective Guidance for Model Attention with Simple Yes-no Annotations
Figure 3 for Effective Guidance for Model Attention with Simple Yes-no Annotations
Figure 4 for Effective Guidance for Model Attention with Simple Yes-no Annotations
Viaarxiv icon

ProFL: Performative Robust Optimal Federated Learning

Add code
Oct 23, 2024
Viaarxiv icon

Can Knowledge Editing Really Correct Hallucinations?

Add code
Oct 21, 2024
Figure 1 for Can Knowledge Editing Really Correct Hallucinations?
Figure 2 for Can Knowledge Editing Really Correct Hallucinations?
Figure 3 for Can Knowledge Editing Really Correct Hallucinations?
Figure 4 for Can Knowledge Editing Really Correct Hallucinations?
Viaarxiv icon

Deliberate Reasoning for LLMs as Structure-aware Planning with Accurate World Model

Add code
Oct 04, 2024
Viaarxiv icon