Papers

Filtered to sequence-to-sequence models · clear filter

Browse by term

continual learning 89reinforcement learning 43vision-language models 19benchmarking 12benchmarks 12robotics 12language models 9world models 9large language models 8video generation 7multimodal models 5recursive self-improvement 5video world models 5agents 4diffusion models 4embodied AI 4foundation models 4generative models 4human-computer interaction 4multimodal large language models 4natural language processing 4policy optimization 4reasoning 4self-supervised learning 4spatial reasoning 4agentic models 3conversational AI 3dialogue systems 3evaluation benchmarks 3LLMs 3

Matching papers

PAR: Progress-Aligned Recurrence for Length Generalization in State Tracking

146 upvotes · 20 OCT 2026 · Pan Wang, Yihao Hu, Guangyuan Dong et al.

This paper proposes a new training method called Progress-Aligned Recurrence (PAR) to improve the performance of sequential state-tracking models on longer problems. By training the model to match the state after a certain number of operations and rescaling recurrent states, PAR enables models to generalize better to longer problems.