2 papers
cs.LG2026
LoRA's Second Descent Extends Beyond Parameter Parity
Yueran Ma
Double descent has sparked considerable interest, with recent work relating it to the data, the model and the learning configuration. Practical fine-tuning commonly involves traini…
cs.CV2026
Seeing What Should Be Heard: Diagnosing and Repairing Cross-Modal Shortcuts in Omni-Modal LLMs
Yueran Ma, Ronghao Lin
Omni-modal large language models (LLMs) are expected to answer a question using the modality it explicitly refers to. However, existing training paradigms rarely verify whether mod…