3 papers
cs.LG2026
Aligning by Misaligning: Boundary-aware Curriculum Learning for Multimodal Alignment
Hua Ye, Hang Ding, Siyuan Chen +3
Most multimodal models treat every negative pair alike, ignoring the ambiguous negatives that differ from the positive by only a small detail. We propose Boundary-Aware Curriculum…
cs.LG2026
Synergy over Discrepancy: A Partition-Based Approach to Multi-Domain LLM Fine-Tuning
Hua Ye, Siyuan Chen, Haoliang Zhang +3
Large language models (LLMs) demonstrate impressive generalization abilities, yet adapting them effectively across multiple heterogeneous domains remains challenging due to inter-d…
cs.AI2026
Seeing through the Conflict: Transparent Knowledge Conflict Handling in Retrieval-Augmented Generation
Hua Ye, Siyuan Chen, Ziqi Zhong +4
Large language models (LLMs) equipped with retrieval--the Retrieval-Augmented Generation (RAG) paradigm--should combine their parametric knowledge with external evidence, yet in pr…