Prioritizing the Best: Incentivizing Reliable Multimodal Reasoning by Rewarding Beyond Answer Correctness
Paper • 2604.18892 • Published
AI & ML interests
We develop data-driven computational methods and intelligent systems to facilitate decision making.
Recent Activity
View all activity
Papers
Uncovering Cross-Objective Interference in Multi-Objective Alignment
A Decentralized Retrieval Augmented Generation System with Source Reliabilities Secured on Blockchain
JillJiaÂ
authored 17
papers 2 days ago
CRC-Router: Risk-Constrained Routing for Medical Agentic AI Systems
Paper • 2609.30714 • Published
AT-CXR: Uncertainty-Aware Agentic Triage for Chest X-rays
Paper • 2508.19322 • Published
AutoRubric: Rubric-Based Generative Rewards for Faithful Multimodal Reasoning
Paper • 2510.14738 • Published
Knowledge-enhanced Memory Model for Emotional Support Conversation
Paper • 2310.07700 • Published
Debiasing Multimodal Sarcasm Detection with Contrastive Learning
Paper • 2312.10493 • Published
Agent as Policy for Robotic Manipulation
Paper • 2609.12541 • Published • 17
FAITHSCORE: Evaluating Hallucinations in Large Vision-Language Models
Paper • 2311.01477 • Published • 1
PLUG: Leveraging Pivot Language in Cross-Lingual Instruction Tuning
Paper • 2311.08711 • Published
Multi-source Semantic Graph-based Multimodal Sarcasm Explanation Generation
Paper • 2306.16650 • Published
Protecting Privacy in Multimodal Large Language Models with MLLMU-Bench
Paper • 2410.22108 • Published • 1
RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph
Paper • 2410.14684 • Published • 1
MultiChartQA: Benchmarking Vision-Language Models on Multi-Chart Problems
Paper • 2410.14179 • Published
Learn Beyond The Answer: Training Language Models with Reflection for Mathematical Reasoning
Paper • 2406.12050 • Published • 19
Describe-then-Reason: Improving Multimodal Mathematical Reasoning through Visual Comprehension Training
Paper • 2404.14604 • Published
MMTutorBench: The First Multimodal Benchmark for AI Math Tutoring
Paper • 2510.23477 • Published • 1
BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution
Paper • 2510.08697 • Published • 41
franciscoliuÂ
submitted a
paper to Daily Papers 5 days ago
JillJiaÂ
submitted a
paper to Daily Papers 26 days ago
franciscoliuÂ
submitted a
paper to Daily Papers 5 months ago