Tag
Proposes the Multi-Stream Fraud Transformer (MSFT) for financial fraud detection, which independently encodes transaction, login, and risk event streams using Transformers and fuses them with time-aware positional encoding and gated fusion, achieving 0.9961 AUROC on a large dataset.
X-Stream introduces the first benchmark for multi-stream video understanding, evaluating MLLMs as multiplexers across multiple concurrent streams. The study reveals that current MLLMs achieve only about 50% accuracy, exposing significant limitations in handling multiple streams.
This paper proposes Multi-Stream LLMs, which use multiple parallel input/output streams to allow models to read and generate simultaneously, unblocking limitations of sequential chat formats.
A new paper proposes LLMs with multiple parallel streams to overcome the bottleneck of single-stream message-based interactions in coding agents and chat models, enabling simultaneous reading, writing, and reasoning.