Franck Dernoncourt

Franck-Dernoncourt's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper 9 days ago

MLLM as a UI Judge: Benchmarking Multimodal LLMs for Predicting Human Perception of User Interfaces

Paper • 2510.08783 • Published 14 days ago • 4

authored 6 papers 13 days ago

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

Paper • 2510.07429 • Published 16 days ago • 3

Curriculum-Guided Abstractive Summarization

Paper • 2302.01342 • Published Feb 2, 2023

Optimizing Data Delivery: Insights from User Preferences on Visuals, Tables, and Text

Paper • 2411.07451 • Published Nov 12, 2024

Steering MoE LLMs via Expert (De)Activation

Paper • 2509.09660 • Published Sep 11

MODS: Moderating a Mixture of Document Speakers to Summarize Debatable Queries in Document Collections

Paper • 2502.00322 • Published Feb 1

A Personalized Conversational Benchmark: Towards Simulating Personalized Conversations

Paper • 2505.14106 • Published May 20

authored 2 papers 23 days ago

The Photographer Eye: Teaching Multimodal Large Language Models to See and Critique like Photographers

Paper • 2509.18582 • Published Sep 23 • 2

Knowledge Homophily in Large Language Models

Paper • 2509.23773 • Published 26 days ago • 3

authored a paper 2 months ago

mSCoRe: a $M$ultilingual and Scalable Benchmark for $S$kill-based $Co$mmonsense $Re$asoning

Paper • 2508.10137 • Published Aug 13 • 2

authored 2 papers 3 months ago

Lizard: An Efficient Linearization Framework for Large Language Models

Paper • 2507.09025 • Published Jul 11 • 18

A Survey on Long-Video Storytelling Generation: Architectures, Consistency, and Cinematic Quality

Paper • 2507.07202 • Published Jul 9 • 22

authored 5 papers 4 months ago

Context-Informed Grounding Supervision

Paper • 2506.15480 • Published Jun 18

FigCaps-HF: A Figure-to-Caption Generative Framework and Benchmark with Human Feedback

Paper • 2307.10867 • Published Jul 20, 2023

Forecasting Time Series with LLMs via Patch-Based Prompting and Decomposition

Paper • 2506.12953 • Published Jun 15 • 2

MS4UI: A Dataset for Multi-modal Summarization of User Interface Instructional Videos

Paper • 2506.12623 • Published Jun 14 • 2

LaMP-Cap: Personalized Figure Caption Generation With Multimodal Figure Profiles

Paper • 2506.06561 • Published Jun 6 • 2

authored 3 papers 5 months ago

Quantitative LLM Judges

Paper • 2506.02945 • Published Jun 3 • 5

Follow the Flow: Fine-grained Flowchart Attribution with Neurosymbolic Agents

Paper • 2506.01344 • Published Jun 2 • 5

A Graph Perspective to Probe Structural Patterns of Knowledge in Large Language Models

Paper • 2505.19286 • Published May 25 • 3