ProactiveLLM enables active interaction in streaming LLMs by learning semantic sufficiency cues from partial inputs through mask-based modeling and synchronized privileged self-distillation without external supervision.
STITCH: Simultaneous Thinking and Talking with Chunked Reasoning for Spoken Language Models
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
ASPIRin decouples speaking timing from token content via binary action space projection and applies GRPO with rule-based rewards to optimize interactivity in SLMs without semantic collapse or repetition.
MPS proposes a dual-brain architecture separating formulation reasoning from articulation to achieve real-time CoT in SLMs with accuracy comparable to full pre-computation but much lower latency.
citing papers explorer
-
Mind-Paced Speaking: A Dual-Brain Approach to Real-Time Reasoning in Spoken Language Models
MPS proposes a dual-brain architecture separating formulation reasoning from articulation to achieve real-time CoT in SLMs with accuracy comparable to full pre-computation but much lower latency.