Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
CAT-GS: Balanced Multimodal Learning via Calibrated Gating and Fusion Surgery
Mahir Shahriar Tamim, Sharjil Khan, Md. Samiul Alim +3
End-to-end training of multimodal neural networks often exhibits unstable neural dynamics characterized by three coupled failure modes that degrade learning: (i) modality imbalance…
cs.LG2026
Skip What You Can Predict: Predictive Repositioning for Policy Optimization for Efficient LLM Training
Ismam Nur Swapnil, Aranya Saha, Tanvir Ahmed Khan +3
Reinforcement learning with verifiable rewards (RLVR) can improve the reasoning ability of large language models, but repeatedly updating a policy on the same rollout batch is expe…