TiCo enables spoken dialogue models to follow explicit time constraints in generated responses using Spoken Time Markers and reinforcement learning with verifiable rewards, cutting duration error by 2.7x over its backbone.
Prompt-based one-shot exact length-controlled generation with llms
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4roles
background 1polarities
background 1representative citing papers
Parallel compaction for LLM agent context management provides predictable volume control and reduces wall time versus sequential baselines on HotpotQA and LoCoMo.
LenVM trains a token-level value head to predict discounted remaining length, enabling length control and efficiency steering on LLMs and VLMs.
An annotation-free synthetic data pipeline for intent classification reaches 93.3% of human-annotated performance by prioritizing style diversity over topic diversity and using LLM-as-a-judge filtering.
citing papers explorer
-
TiCo: Time-Controllable Spoken Dialogue Model
TiCo enables spoken dialogue models to follow explicit time constraints in generated responses using Spoken Time Markers and reinforcement learning with verifiable rewards, cutting duration error by 2.7x over its backbone.
-
Parallel Context Compaction for Long-Horizon LLM Agent Serving
Parallel compaction for LLM agent context management provides predictable volume control and reduces wall time versus sequential baselines on HotpotQA and LoCoMo.
-
Length Value Model: Scalable Value Pretraining for Token-Level Length Modeling
LenVM trains a token-level value head to predict discounted remaining length, enabling length control and efficiency steering on LLMs and VLMs.
-
The Significance of Style Diversity in Annotation-Free Synthetic Data Generation
An annotation-free synthetic data pipeline for intent classification reaches 93.3% of human-annotated performance by prioritizing style diversity over topic diversity and using LLM-as-a-judge filtering.