pith. sign in

So, we move to Condition 1.2.2.1.2.2

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CL 1

years

2025 1

verdicts

UNVERDICTED 1

representative citing papers

Multimodal Policy Internalization for Conversational Agents

cs.CL · 2025-10-10 · unverdicted · novelty 7.0

The paper defines the MPI task and proposes TriMPI, a three-stage training pipeline of continual pretraining, supervised finetuning, and policy-aware reinforcement learning that internalizes multimodal policies into model parameters for improved adherence without prompts at inference.

citing papers explorer

Showing 1 of 1 citing paper.

  • Multimodal Policy Internalization for Conversational Agents cs.CL · 2025-10-10 · unverdicted · none · ref 18

    The paper defines the MPI task and proposes TriMPI, a three-stage training pipeline of continual pretraining, supervised finetuning, and policy-aware reinforcement learning that internalizes multimodal policies into model parameters for improved adherence without prompts at inference.