11 papers
Allocating Recurrent Compute in Looped Language Models
Ruhai Lin, Yiyang Guo, Rui-Jie Zhu +2
Looped language models improve reasoning and knowledge manipulation by applying shared computation repeatedly. Existing systems usually repeat an entire layer stack, although a mix…
From Local Learning to Global Prediction Through Layered Surprise Cascades
Andrew L. Smith, Linxing Preston Jiang, Jason K. Eshraghian +2
Hierarchical predictive coding proposes a compelling hypothesis of brain computation, suggesting that the cortex builds layered predictions to minimize surprise. Yet most models re…
Scaling Latent Reasoning via Looped Language Models
Rui-Jie Zhu, Zixuan Wang, Kai Hua +30
Modern LLMs are trained to "think" primarily via explicit text generation, such as chain-of-thought (CoT), which defers reasoning to post-training and under-leverages pre-training…
A Systematic Analysis of Hybrid Linear Attention
Dustin Wang, Rui-Jie Zhu, Steven Abreu +9
Transformers face quadratic complexity and memory issues with long sequences, prompting the adoption of linear attention mechanisms using fixed-size hidden states. However, linear…
VisualClaw: A Real-Time, Personalized Agent for the Physical World
Haoqin Tu, Jianwen Chen, Zijun Wang +14
Vision language models are serving as general-purpose interfaces for complex multimodal tasks. However, deployment still faces three gaps: VLMs typically incur high latency and cos…
SDTrack: A Baseline for Event-based Tracking via Spiking Neural Networks
Yimeng Shan, Zhenbang Ren, Haodi Wu +11
Event cameras provide superior temporal resolution, dynamic range, energy efficiency, and pixel bandwidth. Spiking Neural Networks (SNNs) naturally complement event data through di…