会员服务
Behavioral Steering in a 35B MoE Language Model via SAE-Decoded Probe Vectors: One Agency Axis, Not Five Traits
Arxiv
0+阅读 · 3月17日
DynamicGate MLP Conditional Computation via Learned Structural Dropout and Input Dependent Gating for Functional Plasticity
Arxiv
0+阅读 · 3月17日
Is the reconstruction loss culprit? An attempt to outperform JEPA
Arxiv
0+阅读 · 3月14日
Variational Garrote for Sparse Inverse Problems
Arxiv
0+阅读 · 3月13日
HiAP: A Multi-Granular Stochastic Auto-Pruning Framework for Vision Transformers
Arxiv
0+阅读 · 3月12日
CODA: Difficulty-Aware Compute Allocation for Adaptive Reasoning
Arxiv
0+阅读 · 3月9日
Attention Deficits in Language Models: Causal Explanations for Procedural Hallucinations
Arxiv
0+阅读 · 2月22日
A Framework for Cross-Domain Generalization in Coronary Artery Calcium Scoring Across Gated and Non-Gated Computed Tomography
Arxiv
0+阅读 · 2月25日
Carbon-Aware Governance Gates: An Architecture for Sustainable GenAI Development
Arxiv
0+阅读 · 2月23日
The Inference Bottleneck: Antitrust and Neutrality Duties in the Age of Cognitive Infrastructure
Arxiv
0+阅读 · 2月26日
FigEx2: Visual-Conditioned Panel Detection and Captioning for Scientific Compound Figures
Arxiv
0+阅读 · 2月25日
MME: Mixture of Mesh Experts with Random Walk Transformer Gating
Arxiv
0+阅读 · 2月28日
Peaceful Anarcho-Accelerationism: Decentralized Full Automation for a Society of Universal Care
Arxiv
0+阅读 · 2月28日
CMoE: Contrastive Mixture of Experts for Motion Control and Terrain Adaptation of Humanoid Robots
Arxiv
0+阅读 · 3月3日
Regularity and Stability Properties of Selective SSMs with Discontinuous Gating
Arxiv
0+阅读 · 2月24日
参考链接
微信扫码咨询专知VIP会员
Top