Edge computing systems need to support diverse sensing workloads under tight energy and memory constraints, thereby motivating deployment-aware model selection. Spiking neural networks (SNNs) are a promising alternative to conventional artificial neural networks (ANNs), yet systematic evidence for when and why they pro...
Xin Du, Di Yu, Chang-Ze Lv et al.· 2 citations· ⚡1
Edge intelligence requires models to sense continuously in real time and to keep adapting on-device, all under tight compute, energy, and memory budgets. Although spiking neural networks (SNNs) enable efficient event-driven inference, standard surrogate-gradient backpropagation (BP) serializes updates and blocks ongoin...
Yan-Xun Zhang, Yi-Fei Wang, Chang-Ze Lv et al.· 0 citations
Spiking forecasting framework SpikeLite is introduced, a spiking forecasting framework built around two modules: a Frequency-Selective Spiking Encoder for frequency-sensitive temporal encoding and a Sparse Spiking Channel Attention (SSCA) module for selective cross-channel interaction.
Bang Hu, Chang-Ze Lv, Ming-Jie Li et al.· arXiv.org· 0 citations
QuantaSpike is proposed, a short-window spike-driven quantization framework for LLMs built around Logarithmic Ternary Integrate-and-Fire (LTIF) neurons that achieves state-of-the-art or competitive perplexity and zero-shot accuracy among spike-driven LLM quantization methods.
Bang Hu, Guo-Wei Zhu, Changze Lv et al.· arXiv.org· 0 citations
The evaluation reveals that model performance shifts systematically with the availability of target-specific experimental evidence: PLMs demonstrate proficiency in open-ended single-mutant generation by leveraging protein-specific priors, whereas LLMs and agents perform strongly in multi-mutant ranking, particularly wh...
Ya-Wen Ouyang, Xin-Bo Zhang, Zi-Yuan Ma et al.· 0 citations
Recast is an efficient and scalable framework for synthesizing datasets where each example incorporates far more constraints than those in existing benchmarks, aiming to challenge and extend the boundaries of models'ability to follow complex instructions.
Zheng-Kang Guo, Wen-Hao Liu, Min Xie et al.· 13 citations· ⚡5
ReDeck is proposed, a step-level render-grounded refinement framework that decomposes slide revision into atomic edit actions and returns renderer-derived observations after each step, turning refinement into"one edit, one observation."
Mu-Zhao Tian, Ze-Zi Zeng, Yi-Fan Yang et al.· 0 citations
This work shows that an agent's reliance on memory can be modeled as an explicit and user-controllable dimension, and proposes a framework that allows users to dynamically regulate memory reliance, ranging from a fresh-start mode that promotes innovation to a high-fidelity mode that closely follows interaction history.
Mu-Zhao Tian, Zi-Su Huang, Xiaohua Wang et al.· Annual Meeting of the Associ...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.