会员服务
Unraveling Syntax: Language Modeling and the Substructure of Grammars
Arxiv
0+阅读 · 6月10日
Decoupled Delay Compensation: Enhancing Pre-trained MARL Policies via Learned Dynamics Filtering
Arxiv
0+阅读 · 5月25日
Positional versus Symbolic Attention Heads: Learning Dynamics, RoPE Geometry, and Length Generalization
Arxiv
0+阅读 · 5月29日
Physics-Informed Neural Networks for Biological $2\mathrm{D}{+}t$ Reaction-Diffusion Systems
Arxiv
0+阅读 · 4月20日
Departure Time Choice with Parametric Heterogeneity: Equilibrium and Instability
Arxiv
0+阅读 · 4月15日
Dynamic Free-Rider Detection in Federated Learning via Simulated Attack Patterns
Arxiv
0+阅读 · 4月6日
Efficient Uncoupled Learning Dynamics with $\tilde{O}\!\left(T^{-1/4}\right)$ Last-Iterate Convergence in Bilinear Saddle-Point Problems over Convex Sets under Bandit Feedback
Arxiv
0+阅读 · 2月24日
Sink equilibria and the attractors of learning in games
Arxiv
0+阅读 · 3月4日
COLD-Steer: Steering Large Language Models via In-Context One-step Learning Dynamics
Arxiv
0+阅读 · 3月6日
A universal compression theory for lottery ticket hypothesis and neural scaling laws
Arxiv
0+阅读 · 3月2日
The Bounds of Algorithmic Collusion; $Q$-learning, Gradient Learning, and the Folk Theorem
Arxiv
0+阅读 · 3月3日
On the Learning Dynamics of RLVR at the Edge of Competence
Arxiv
0+阅读 · 2月16日
Computing stable limit cycles of learning in games
Arxiv
0+阅读 · 2月11日
Low-Dimensional Execution Manifolds in Transformer Learning Dynamics: Evidence from Modular Arithmetic Tasks
Arxiv
0+阅读 · 2月13日
Games with Payments between Learning Agents
Arxiv
0+阅读 · 2月11日
参考链接
微信扫码咨询专知VIP会员
Top