Remember-R1 adds three process-level rewards to GRPO, encouraging keyword coverage, sustained visual attention, and focus on question-relevant regions, improving MLLM reasoning across seven benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Remember-R1: Mitigating Long-Context Visual Forgetting through Reinforcement Learning
Remember-R1 adds three process-level rewards to GRPO, encouraging keyword coverage, sustained visual attention, and focus on question-relevant regions, improving MLLM reasoning across seven benchmarks.