15 citations · 16 across the 13 of their papers we have counts for
13 papers
Event-Driven Language Models with Sparse Neural Activity for Neuromorphic Hardware
Simon Richter, Ruhai Lin, Jason Yik +4
Inference with transformer-based large language models (LLMs) is often limited by the memory-bound KV cache and quadratic attention cost. State-space models (SSMs) mitigate this th…
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…
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…
SATFormer: Learning When to Use Early Value Residuals in Transformers
Skye Gunasekaran, Téa Wright, Rui-Jie Zhu +1
Recent Transformer architectures expose later layers to representations computed in earlier layers, motivated by the observation that low-level features can become harder to recove…
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 Survey on Latent Reasoning
Rui-Jie Zhu, Tianhao Peng, Tianhao Cheng +30
Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, especially when guided by explicit chain-of-thought (CoT) reasoning that verbalizes intermediate s…
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…
Neuromorphic Principles for Efficient Large Language Models on Intel Loihi 2
Steven Abreu, Sumit Bam Shrestha, Rui-Jie Zhu +1
Large language models (LLMs) deliver impressive performance but require large amounts of energy. In this work, we present a MatMul-free LLM architecture adapted for Intel's neuromo…
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…
ARFlow: Autoregressive Flow with Hybrid Linear Attention
Mude Hui, Rui-Jie Zhu, Songlin Yang +5
Flow models are effective at progressively generating realistic images, but they generally struggle to capture long-range dependencies during the generation process as they compres…
Reducing Data Bottlenecks in Distributed, Heterogeneous Neural Networks
Ruhai Lin, Rui-Jie Zhu, Jason K. Eshraghian
The rapid advancement of embedded multicore and many-core systems has revolutionized computing, enabling the development of high-performance, energy-efficient solutions for a wide…
A Predictive Approach To Enhance Time-Series Forecasting
Skye Gunasekaran, Assel Kembay, Hugo Ladret +4
Accurate time-series forecasting is crucial in various scientific and industrial domains, yet deep learning models often struggle to capture long-term dependencies and adapt to dat…