ChartLlama: A Multimodal LLM for Chart Understanding and Generation (2023 · 99 citations)
General-purpose multimodal LLMs read everyday photos well but struggle with charts. The main cause is a shortage of suitable instruction data: existing chart datasets rely on web-crawled figures with thin annotations and rarely include the plotting code needed to teach chart generation. The authors build a synthetic…
Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search (2026)
Most LLM agents for machine learning engineering (MLE) improve solutions through tree or graph search. They reduce rich execution feedback to a scalar score and use it only to decide which candidate to keep. The authors argue that this is a gradient-free approach. It wastes diagnostic information that strong…
Rotation Control Unlearning: Quantifying and Controlling Continuous Unlearning for LLM with The Cognitive Rotation Space (2026)
This paper addresses continual machine unlearning for LLMs, where a model must remove the influence of unwanted data across a sequence of deletion requests.

Co-authors here

12 of 14 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 74 times (of the 149,439 papers whose bibliographies we read); 21 citing papers with a page here →.

Updated 2 November 2026