8 papers
Measure gradients, not activations! Enhancing neuronal activity in deep reinforcement learning
Jiashun Liu, Zihao Wu, Johan Obando-Ceron +3
Deep reinforcement learning (RL) agents frequently suffer from neuronal activity loss, which impairs their ability to adapt to new data and learn continually. A common method to qu…
InvarDiff: Cross-Scale Invariance Caching for Accelerated Diffusion Models
Zihao Wu
Diffusion models deliver high-fidelity synthesis but remain slow due to iterative sampling. We empirically observe there exists feature invariance in deterministic sampling, and pr…
Autono: A ReAct-Based Highly Robust Autonomous Agent Framework
Zihao Wu
This paper proposes a highly robust autonomous agent framework based on the ReAct paradigm, designed to solve complex tasks through adaptive decision making and multi-agent collabo…
Bhakti: A Lightweight Vector Database Management System for Endowing Large Language Models with Semantic Search Capabilities and Memory
Zihao Wu
With the rapid development of big data and artificial intelligence technologies, the demand for effective processing and retrieval of vector data is growing. Against this backdrop,…
Score-Based Metropolis-Hastings Algorithms
Ahmed Aloui, Ali Hasan, Juncheng Dong +2
In this paper, we introduce a new approach for integrating score-based models with the Metropolis-Hastings algorithm. While traditional score-based diffusion models excel in accura…
Teleportation With Null Space Gradient Projection for Optimization Acceleration
Zihao Wu, Juncheng Dong, Ahmed Aloui +1
Optimization techniques have become increasingly critical due to the ever-growing model complexity and data scale. In particular, teleportation has emerged as a promising approach,…