F-GRPO factorizes group-relative policy optimization into generation and ranking phases within one autoregressive sequence, using order-invariant coverage and position-aware utility rewards to improve top-ranked performance on recommendation and multi-hop QA tasks.
A personalized conversational benchmark: Towards simulating personalized conversations
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5roles
background 1polarities
unclear 1representative citing papers
Agent safety cannot be achieved via model refusal training and instead requires external least-privilege enforcement evaluated as action alignment.
TimeMM proposes a time-as-operator spectral filtering framework with adaptive mixing and modality routing to model non-stationary multimodal user preferences in recommendation systems.
A survey that introduces a taxonomy for LLM-based conversational user simulation, analyzes core techniques and evaluation methods, and identifies open challenges in the field.
citing papers explorer
-
F-GRPO: Factorized Group-Relative Policy Optimization for Unified Candidate Generation and Ranking
F-GRPO factorizes group-relative policy optimization into generation and ranking phases within one autoregressive sequence, using order-invariant coverage and position-aware utility rewards to improve top-ranked performance on recommendation and multi-hop QA tasks.
-
Agent Safety Is Action Alignment
Agent safety cannot be achieved via model refusal training and instead requires external least-privilege enforcement evaluated as action alignment.
-
TimeMM: Time-as-Operator Spectral Filtering for Dynamic Multimodal Recommendation
TimeMM proposes a time-as-operator spectral filtering framework with adaptive mixing and modality routing to model non-stationary multimodal user preferences in recommendation systems.
-
A Survey on LLM-based Conversational User Simulation
A survey that introduces a taxonomy for LLM-based conversational user simulation, analyzes core techniques and evaluation methods, and identifies open challenges in the field.
- Cat-DPO: Category-Adaptive Safety Alignment