3 papers
cs.LG2026
Learning Chaos Without Seeing Chaos: Extrapolation of Global Dynamics in Autoregressive Transformers
Yilun Liu, Yi Zhang, Ganyu Wu +5
Autoregressive models are trained to predict a system's behavior one step at a time, and recursive generation allows the learned dynamics to unfold over long horizons. To what exte…
cs.AI2026
DeepLook: Uncertainty-Guided Branching with Lookahead Confidence for Efficient Reasoning
Tingxin Yang, Zefeng Wang, Mengyue Wang +4
Test-time scaling improves large language model reasoning, but spends compute uniformly along a reasoning trace, even in stretches that are already stable. Motivated by the observa…
cs.CV2025
METok: Multi-Stage Event-based Token Compression for Efficient Long Video Understanding
Mengyue Wang, Shuo Chen, Kristian Kersting +2
Recent advances in Video Large Language Models (VLLMs) have significantly enhanced their ability to understand video content. Nonetheless, processing long videos remains challengin…