Papers with MENTOR
MENTOR: Mitigating Identity Drift in Dynamic Role-Playing via Dual-Chain Structured Memory (2026.findings-acl)
Copied to clipboard
| Challenge: | Long-context LLMs are evolving into long-term agents that interact with users over extended horizons. |
| Approach: | They propose a cognitive architecture that mitigates identity drift without fine-tuning . MENTOR uses a Dual-Chain Memory Mechanism: a Global Chain (G) for long-term event logging and isolated Role Chains (Rr) as per-role working memories. |
| Outcome: | The proposed architecture improves the overall score (Avg) from 0.46 to 0.75 on average, with substantial gains in identity adherence and knowledge fidelity. |
MENTOR: Efficient Autoregressive Image Generation with Balanced Multimodal Control (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent text-to-image models achieve impressive visual quality but still face challenges in precise controllability, balancing multimodal inputs, and high training cost for multimodal image generation. |
| Approach: | They propose an autoregressive framework with a two-stage training paradigm for controllable multimodal image generation. |
| Outcome: | Extensive experiments on DreamBench++ and DreamBech show that the proposed framework achieves a strong balance between textual and visual guidance for controllable image generation. |