Ali Payani

Command-V: Training-Free Representation Finetuning Transfer

Utilizing LLM Robustness for LVLM Safety via Reducing the Pretraining Modality Gap

MemLens: Uncovering Memorization in LLMs with Activation Trajectories

LLMs as Rules Oracles: Exploring Real-World Multimodal Reasoning in Tabletop Strategy Game Environments

Enhancing Language Model Reasoning with Structured Multi-Level Modeling

SPARC-RTL: Stochastic Prompt-Assisted RTL Code Synthesis

GUI-Spotlight: Adaptive Iterative Focus Refinement for Enhanced GUI Visual Grounding

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

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

Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution

A Generic Framework for Conformal Fairness

Can Knowledge Editing Really Correct Hallucinations?

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

Personalized Federated Fine-tuning for Heterogeneous Data: a Two-Level Low Rank Adaptation Approach

Enhancing Group Fairness in Federated Learning through Personalization

MDBench: A Synthetic Multi-Document Reasoning Benchmark Generated with Knowledge Guidance