Why Do More Experts Fail? A Theoretical Analysis of Model Merging (2026 · 2 citations)
Merging several fine-tuned expert models into one multi-task model saves storage and compute. However, adding more experts stops helping quickly: state-of-the-art methods such as GENOME level off at around six merged models on most datasets. This paper asks why that ceiling exists. Using high-dimensional geometry…
PlaM: Training-Free Plateau-Guided Model Merging for Better Visual Grounding in MLLMs (2026 · 1 citation)
Multimodal instruction fine-tuning tends to weaken the text reasoning that MLLMs inherit from their base language models.
Look Within or Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning (2026)
Parameter-efficient fine-tuning (PEFT) methods such as LoRA often match full fine-tuning (FFT) on standard benchmarks. It is less clear whether they hold up on harder tasks like reasoning and instruction-following, or under adversarial inputs. The authors address this with a theoretical analysis backed by experiments.

Co-authors here

12 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 3 times (of the 149,439 papers whose bibliographies we read); 1 citing paper with a page here →.

Updated 1 November 2026