DREAMSTATE: Diffusing States and Parameters for Recurrent Large Language Models
Paper • 2601.19221 • Published
rwkv4fun
community
AI & ML interests
None defined yet.
xiaol
authored 4
papers 2 months ago
Belief-State RWKV for Reinforcement Learning under Partial Observability
Paper • 2604.09671 • Published
Associative-State Universal Transformers: Sparse Retrieval Meets Structured Recurrence
Paper • 2604.25930 • Published
Generic Triple-Latent Compression with Gated Associative Retrieval
Paper • 2606.05175 • Published
xiaol
authored 4
papers about 1 year ago
WuNeng: Hybrid State with Attention
Paper • 2504.19191 • Published
Cross-attention for State-based model RWKV-7
Paper • 2504.14260 • Published
Millions of States: Designing a Scalable MoE Architecture with RWKV-7 Meta-learner
Paper • 2504.08247 • Published
State Tuning: State-based Test-Time Scaling on RWKV-7
Paper • 2504.05097 • Published