Vision-Language-Action (VLA) models have recently achieved strong performance in robot manipulation, with promising generalization across diverse tasks and environments. However, long-horizon executions and unseen scenarios can still lead to failures, highlighting the need for online failure detection to enable timely...
Long-context LLM serving is increasingly bottlenecked by KV-cache memory, especially in resource-constrained scenarios. Among existing KV-cache compression strategies, token-wise methods reduce cached states but risk information loss through eviction or condensation, while feature-wise methods reduce per-token KV dimen...
Zi-Han Teng, Jiayu Zhao, Wen-Tao Ren et al.· 0 citations
BitsMoE is proposed, a cost-aware mixed-precision quantization framework built on two complementary techniques that separates expert weights into a shared basis and expert-specific spectral components, defining structural quantization units while exploiting cross-expert redundancy.
Jiayu Zhao, Zi-Han Teng, Min-Hao Fan et al.· 0 citations
CoTM is proposed, a coherence-aware task mapping framework that constructs task graphs by inferring inter-task dependencies from dynamic coherence behavior, guided by a coherence-aware penalty function that jointly considers coherence traffic and NoC performance metrics.
Co is proposed, a coherence-aware co-optimization framework that jointly integrates task mapping and routing under a unified cost model for realistic scenarios, enabling coherence-aware decision-making and effective trade-offs among optimization goals.
A retention-oriented scheduling framework for always-on arbitrary-deadline Directed Acyclic Graph workloads, consisting of two algorithms with a clear progression, and shows that, compared with a representative work-conserving baseline with automatic retention/PG, PREHS reduces static energy consumption.
Xiangzhen Xiao, Weijie Wang, Wei-Chen Liu et al.· ACM Transactions on Embedded...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
