streaming

Definition

Processing input incrementally as it arrives and emitting output before the full input is available. It is required wherever latency is part of the product — live transcription, simultaneous translation, token-by-token chat responses. Accuracy is usually somewhat worse than offline processing, which can condition on the entire input, so streaming work is largely about managing that latency-quality trade-off.

Explainers using this term

• Paper Walkthrough — Beyond Retrieval: LatentStream Turns Retrieved Video Into Latent MemoryBeyond Retrieval: Progressive Latent Memory Evolution for Streaming Video Understanding
• Paper Walkthrough: Eleven Frames Are Enough — Revisiting Local Context for Long-Horizon Streaming 3D ReconstructionRevisiting Local Context for Long-Horizon Streaming 3D Reconstruction
• Paper Walkthrough: VoiceMem — A Left Brain and a Right Brain for Voice Agents, at Zero Added LatencyVoiceMem: Streaming Dual-Brain Memory for Real-Time Interaction