Recurrent neural networks and their variants, including training methods, architectures, and applications in sequence modeling
表格 4 results
| Name | Categories | Topics | References | Credibility | CreateDate | UpdateDate | Title | RelatedNotes | NavigationOrder | Eleventy | TemplateEngineOverride | Created |
|---|
| 20260604_pretraining_recurrent_networks_without_recurrence | paper_analysis | memory_mechanism, recurrent_neural_networks, llm, reinforce_learning, neuro_science | mit, supervised_memory_training, backpropagation_through_time | 100 | | | Pretraining Recurrent Networks without Recurrence | | [object Object] | [object Object] | md | |
| 20260618_fixed_point_reasoners_stable_adaptive_deep_looped_transformers | paper_analysis | reasoning, llm, recurrent_neural_networks, memory_mechanism, agent_architecture | tuebingen_ai_center, eth_zurich, liquidai, max_planck_institute | 100 | | | Fixed-Point Reasoners: Stable and Adaptive Deep Looped Transformers | | [object Object] | [object Object] | md | |
| 20260629_carve_content_aware_recurrent_value_efficiency | paper_analysis | memory_mechanism, recurrent_neural_networks, llm, reasoning, linear_attention | carve, deltanet | 100 | | | CARVE: Content-Aware Recurrent with Value Efficiency for Chunk-Parallel Linear Attention | Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention | [object Object] | [object Object] | md | |
| 20260719_t2mlr_transformer_temporal_middle_layer_recurrence | paper_analysis | reasoning, llm, memory_mechanism, recurrent_neural_networks, reasoning_memory | princeton_university, chain_of_thought, backpropagation_through_time, gsm8k, hotpotqa | 100 | | | T²MLR: Transformer with Temporal Middle-Layer Recurrence | searchos_v1_open_domain_information_seeking_agent_collaboration, chain_of_thought_prompting_elicits_reasoning, memory_r1_enhancing_llm_agents_manage_utilize_memories_rl | [object Object] | [object Object] | md | |