LARC: Lazy Adaptive Reachability Certification of Robot Manipulator Trajectories
为解决机器人轨迹中可能遗漏的碰撞问题,提出了一种基于自适应可达性的懒惰认证方法(LARC),通过仅细分不确定间距来减少计算量。
为解决机器人轨迹中可能遗漏的碰撞问题,提出了一种基于自适应可达性的懒惰认证方法(LARC),通过仅细分不确定间距来减少计算量。
为解决从3D CAD模型和2D工程图到制造过程规划的全链条推理问题,提出了一种基于大语言模型的多代理框架Design-to-Plan,通过协调各专业代理实现高效、可追溯的决策。
This work challenges the prevailing assumption in multimodal sentiment analysis that all missing modalities must be reconstructed under partial observability. To address this, the authors propose SIEVE, a novel framework featuring a sample-adaptive modality reconstruction mechanism. SIEVE employs a dual-branch architecture to directly compare the losses of reconstructing versus not reconstructing missing modalities, generating an empirical sufficiency signal. By integrating evidential deep learning with cognitive uncertainty modeling, it implements an evidence-gated mechanism that dynamically decides, on a per-sample basis, whether reconstruction is necessary. Notably, SIEVE operates as a plug-and-play module without requiring modifications to underlying reconstruction components. Experiments on CMU-MOSI and IEMOCAP demonstrate consistent and significant performance gains across diverse backbone models, approaching the theoretical sample-level optimum.
This work addresses the inefficiency of large language models (LLMs) in reasoning, where excessive computation—often termed “overthinking”—leads to wasted resources. Existing approaches apply uniform compression strategies that neglect variations in reasoning complexity both across problems and within individual reasoning steps. To overcome this limitation, the authors propose an “Economical Reasoning” framework featuring a hierarchical adaptive budgeting mechanism: at the problem level, it predicts the optimal reasoning depth; at the step level, it dynamically allocates token budgets via perplexity-based comparisons and Pareto optimization, while leveraging Fisher information pruning to guide the generator toward efficient reasoning patterns. This approach achieves the first dual-granularity, fine-grained resource allocation scheme, explicitly modeling the quality–efficiency trade-off as a locally adaptive objective. Experiments on GSM8K and MATH500 demonstrate simultaneous improvements in accuracy and reductions in token consumption, significantly outperforming standard chain-of-thought and other baselines.
This study addresses the heightened challenges in day-ahead scheduling caused by uncertainties in renewable generation and electricity demand, which hinder green energy curtailment reduction and intra-day power balancing. To tackle this issue, the paper proposes an incentive-compatible peer-to-peer (P2P) electricity trading mechanism integrated with a multi-agent reinforcement learning framework. This approach enables self-interested microgrids to autonomously optimize their bidding strategies and energy storage arbitrage under dynamic grid electricity prices. The mechanism jointly promotes individual economic gains and system-wide decarbonization objectives, achieving coordinated optimization that significantly enhances renewable energy utilization, reduces reliance on high-carbon power sources, and improves the overall economic welfare of the local energy community.
为解决机器人轨迹中可能遗漏的碰撞问题,提出了一种基于自适应可达性的懒惰认证方法(LARC),通过仅细分不确定间距来减少计算量。
为解决从3D CAD模型和2D工程图到制造过程规划的全链条推理问题,提出了一种基于大语言模型的多代理框架Design-to-Plan,通过协调各专业代理实现高效、可追溯的决策。
This work challenges the prevailing assumption in multimodal sentiment analysis that all missing modalities must be reconstructed under partial observability. To address this, the authors propose SIEVE, a novel framework featuring a sample-adaptive modality reconstruction mechanism. SIEVE employs a dual-branch architecture to directly compare the losses of reconstructing versus not reconstructing missing modalities, generating an empirical sufficiency signal. By integrating evidential deep learning with cognitive uncertainty modeling, it implements an evidence-gated mechanism that dynamically decides, on a per-sample basis, whether reconstruction is necessary. Notably, SIEVE operates as a plug-and-play module without requiring modifications to underlying reconstruction components. Experiments on CMU-MOSI and IEMOCAP demonstrate consistent and significant performance gains across diverse backbone models, approaching the theoretical sample-level optimum.
This work addresses the inefficiency of large language models (LLMs) in reasoning, where excessive computation—often termed “overthinking”—leads to wasted resources. Existing approaches apply uniform compression strategies that neglect variations in reasoning complexity both across problems and within individual reasoning steps. To overcome this limitation, the authors propose an “Economical Reasoning” framework featuring a hierarchical adaptive budgeting mechanism: at the problem level, it predicts the optimal reasoning depth; at the step level, it dynamically allocates token budgets via perplexity-based comparisons and Pareto optimization, while leveraging Fisher information pruning to guide the generator toward efficient reasoning patterns. This approach achieves the first dual-granularity, fine-grained resource allocation scheme, explicitly modeling the quality–efficiency trade-off as a locally adaptive objective. Experiments on GSM8K and MATH500 demonstrate simultaneous improvements in accuracy and reductions in token consumption, significantly outperforming standard chain-of-thought and other baselines.
This study addresses the heightened challenges in day-ahead scheduling caused by uncertainties in renewable generation and electricity demand, which hinder green energy curtailment reduction and intra-day power balancing. To tackle this issue, the paper proposes an incentive-compatible peer-to-peer (P2P) electricity trading mechanism integrated with a multi-agent reinforcement learning framework. This approach enables self-interested microgrids to autonomously optimize their bidding strategies and energy storage arbitrage under dynamic grid electricity prices. The mechanism jointly promotes individual economic gains and system-wide decarbonization objectives, achieving coordinated optimization that significantly enhances renewable energy utilization, reduces reliance on high-carbon power sources, and improves the overall economic welfare of the local energy community.