2 papers
cs.LG2026
Learning to Interpret Weight Differences in Language Models
Avichal Goel, Yoon Kim, Nir Shavit +1
Finetuning (pretrained) language models is a standard approach for updating their internal parametric knowledge and specializing them to new tasks and domains. However, the corresp…
cs.LG2026
Scalable Energy-Based Models via Adversarial Training: Unifying Discrimination and Generation
Xuwang Yin, Claire Zhang, Julie Steele +2
Simultaneously achieving robust classification and high-fidelity generative modeling within a single framework presents a significant challenge. Hybrid approaches, such as Joint En…