8 papers
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…
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…
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,…
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,…
S2TX: Cross-Attention Multi-Scale State-Space Transformer for Time Series Forecasting
Zihao Wu, Juncheng Dong, Haoming Yang +1
Time series forecasting has recently achieved significant progress with multi-scale models to address the heterogeneity between long and short range patterns. Despite their state-o…