← 研踪 PaperTrailarXiv:2611.19493 · v1
Beyond Paired Inputs: Learning to Leverage RGB-T Cross-Modal Relations in Multimodal Large Language Models
首次提交 2026-11-15 00:28
版本更新 2026-11-15 00:28
雷达观测 2026-11-17 12:06
摘要
RGB and thermal infrared (TIR) sensors provide complementary observations, yet their distinct sensing characteristics make effective cross-modal coordination challenging. Although existing multimodal large language models (MLLMs) can process paired RGB-T inputs, they often fail to translate cross-modal relations into effective task-specific decisions, leaving the potential of these relations to improve task performance and robustness largely untapped. Motivated by this observation, we introduce RelMLLM, an RGB-T MLLM that explicitly learns to exploit cross-modal relations in task-specific decision making. It represents modality reliability, the cross-modal relation, and the dominant modality as a verifiable decision state. We derive task-grounded supervision for this state by comparing RGB-only, TIR-only, and paired RGB-T task outcomes. A hierarchical relation-guided reward supervises modality-specific evidence, relation-state prediction, and the final task output, while encouraging consistency across evidence, relation, and decision. We evaluate RelMLLM on natural RGB-T grounding, RGB-T visual question answering, and held-out sensor degradation. RelMLLM improves grounding accuracy and degradation robustness over its Qwen3-VL baselines while preserving performance on general RGB-T reasoning benchmarks. These results demonstrate that effectively exploiting cross-modal relations leads to more accurate and robust RGB-T decisions. Code and model weights are publicly available.
作者备注:9 pages, 4 figures
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-15 00:28 · 最新观测版本
Beyond Paired Inputs: Learning to Leverage RGB-T Cross-Modal Relations in Multimodal Large Language Models
RGB and thermal infrared (TIR) sensors provide complementary observations, yet their distinct sensing characteristics make effective cross-modal coordination challenging. Although existing multimodal large language models (MLLMs) can process paired RGB-T inputs, they often fail to translate cross-modal relations into effective task-specific decisions, leaving the potential of these relations to improve task performance and robustness largely untapped. Motivated by this observation, we introduce RelMLLM, an RGB-T MLLM that explicitly learns to exploit cross-modal relations in task-specific decision making. It represents modality reliability, the cross-modal relation, and the dominant modality as a verifiable decision state. We derive task-grounded supervision for this state by comparing RGB-only, TIR-only, and paired RGB-T task outcomes. A hierarchical relation-guided reward supervises modality-specific evidence, relation-state prediction, and the final task output, while encouraging consistency across evidence, relation, and decision. We evaluate RelMLLM on natural RGB-T grounding, RGB-T visual question answering, and held-out sensor degradation. RelMLLM improves grounding accuracy and degradation robustness over its Qwen3-VL baselines while preserving performance on general RGB-T reasoning benchmarks. These results demonstrate that effectively exploiting cross-modal relations leads to more accurate and robust RGB-T decisions. Code and model weights are publicly available.
查看此版本解读 →查看此版本原文 ↗