…Xu Wan , , , , , , Abstract Inference-time scaling is enhanced through constrained optimization that allocates computational resources based on economic principles, improving performance in resource-constrained environments. Generated by Qwen/Qwen2.5-Coder-32B…
…Yulong Huang , Xiang Liu , , , , , , Abstract Linear attention models face challenges with information decay and convergence, which are addressed through a momentum-based approach that improves training efficiency and performance over existing models…
…Evaluation of six state-of-the-art methods shows that strong global volumetric overlap does not necessarily translate into reliable performance at clinically critical tumor-vessel interfaces. In particular, methods optimized for…
…Zewen Liu , , , , , , , , , Abstract Adaptive Auto-Harness framework addresses dynamic task streams by decomposing performance gaps into evolution and adaptation losses, utilizing a stateful multi-agent evolver and harness tree with solve-time…
…Yifeng Liu , , Yifan Zhang , Abstract A self-distilled policy-gradient framework combines on-policy self-distillation with verifier advantages and KL regularization to improve reinforcement learning stability and performance. Generated by Qwen…
…Extensive experiments and scaling analyses show that our model establishes a new performance frontier, demonstrating robust zero-shot generalization to unseen tasks while simultaneously tracking highly dynamic and complex motions. View arXiv…
…to the next? At present, addressing these questions typically requires costly training runs whose aggregate performance metrics obscure the dynamics at the level of individual tokens. We introduce a training-free diagnostic…
To show you the most relevant results, we’ve omitted some entries very similar to those already shown. Repeat the search with the omitted results included.