Recent 3D Large Language Models (3D-LLMs) have shown strong performance on scene question answering with extensive post-training. Yet, existing benchmarks rarely evaluate how 3D-LLMs respond to referential ambiguity, insufficient scene evidence, or false presuppositions, obscuring whether their responses are grounded i...
Yi-Fei Zhao, Fan-Yu Zhao, Han Zhang et al.· 0 citations
Experiments show that COPE consistently outperforms strong training-free and training-based baselines under sparse feedback, and remains complementary to Retrieval-Augmented Prompting, and further analyses confirm COPE's reliable self-evaluation, meaningful preference patterns, stable general capabilities, and robustne...
Rui-Ke Cao, Fu-Gen Yao, Liang Dong et al.· Conference on Empirical Meth...· 0 citations
MemCalib-RL is proposed, an ordered bidirectional counterfactual credit-assignment algorithm that separates over- and under-use signals and localizes their credit to response tokens through exact atom ablation and achieves the best overall performance while better balancing over-use and under-use.
Rui-Ke Cao, Fan-Yu Zhao, Fu-Gen Yao et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.