Franck Dernoncourt

Steering MoE LLMs via Expert (De)Activation

Charts Are Not Images: On the Challenges of Scientific Chart Editing

Towards Visual Text Grounding of Multimodal Large Language Model

Quantitative LLM Judges

A Personalized Conversational Benchmark: Towards Simulating Personalized Conversations

Structured Uncertainty guided Clarification for LLM Agents

Reasoning-Based Personalized Generation for Users with Sparse Data

Learning to Route LLMs from Bandit Feedback: One Policy, Many Trade-offs

NoLiMa: Long-Context Evaluation Beyond Literal Matching

DynaSaur: Large Language Agents Beyond Predefined Actions

SV-RAG: LoRA-Contextualizing Adaptation of MLLMs for Long Document Understanding

A Large-scale Training Paradigm for Graph Generative Models

VipAct: Visual-Perception Enhancement via Specialized VLM Agent Collaboration and Tool-use

Taipan: Efficient and Expressive State Space Language Models with Selective Attention