Y. Wu

SketchVL: Policy Optimization via Fine-Grained Credit Assignment for Chart Understanding and More

m.-huang
•
阅读更多

PhysPRM: A Generative Process Reward Model with Fine-grained Diagnosis for Physics Problem Solving

y.-dong
•
阅读更多

OptiVerse: A Comprehensive Benchmark towards Optimization Problem Solving

x.-zhang
•
阅读更多

Memory-Enriched Thought-by-Thought Framework for Complex Diagram Question Answering

x.-zhang
•
阅读更多

Beyond Layer-Wise Merging: Chain-of-Merging for Vision-Language Models

x.-zhang
•
阅读更多

AGT^AO: Robust and Stabilized LLM Unlearning via Adversarial Gating Training with Adaptive Orthogonality

p.-li
•
阅读更多

PhysReason: A Comprehensive Benchmark towards Physics-Based Reasoning

x.-zhang
•
阅读更多

LFSRM: Few-Shot Diagram-Sentence Matching via Local-Feedback Self-Regulating Memory

l.-zhang
•
阅读更多

Diagram-driven course questions generation

x.-zhang
•
阅读更多

Cognitive Predictive Coding Network: Rethinking the Generalization in Raven Progressive Matrices

x.-zhang
•
阅读更多