2 papers
cs.CL2026
AWARe: Mitigating Catastrophic Forgetting via Activation-Weighted Adaptive REtention
Juncheng Liao, Jinfan Lv, Guoming Wang +3
Multimodal Large Language Models (MLLMs) exhibit strong generalization and reasoning abilities due to large-scale multimodal pre-training. However, fine-tuning these models on down…
cs.AI2026
QuantWAMs: Calibrating at the Right Granularity for World Action Models
Jiacheng Zhou, Jinfan Lv, Ruixuan Li +4
World Action Models (WAMs) jointly predict future observations and actions, but their iterative denoising and closed-loop execution make efficient deployment costly. Existing post-…