Tag: transformer-architecture

Jun 14, 2026

• ai/transformer
• ai/attention
• ai/qkv
• machine-learning
• neural-architecture
• 3blue1brown
• transformer-architecture
• attention-mechanism
• query-key-value
• linear-projection

Jun 14, 2026

• machine-learning
• transformers
• attention-mechanisms
• transformer-architecture
• long-range-dependencies
• context-window

Jun 13, 2026

• attention-mechanisms
• transformer-architecture
• neural-networks
• ai-foundations

Jun 13, 2026

• transformer-architecture
• pre-norm-dilution
• attention-mechanism
• kimi-model
• residual-connections

Jun 13, 2026

• contextual-embeddings
• transformer-architecture
• self-attention
• dynamic-representations
• vector-representations
• polysemy-resolution

Jun 13, 2026

• ai
• machine-learning
• llm
• foundation-models
• large-scale-models
• transformer-architecture

Jun 13, 2026

• hybrid-attention
• transformer-architecture
• sparse-attention
• linear-attention
• computational-efficiency
• long-context-modeling

Jun 13, 2026

• machine-learning
• peft
• fine-tuning
• transformer
• diffusion-models
• parameter-efficient
• low-rank-adaptation
• parameter-efficient-fine-tuning
• transformer-architecture
• deep-learning

Jun 13, 2026

• transformer-architecture
• large-language-models
• neural-networks
• inference-engines
• self-attention
• feed-forward-networks

Jun 13, 2026

• video-generation
• multimodal-ai
• transformer-architecture
• temporal-coherence
• google-omni
• unified-models
• video-understanding