Feedback-driven iteration is widely used to improve LLM-generated scientific ideas, but existing systems either leave revision decisions implicit in generation, align revisions with feedback-localized weaknesses, or restrict action selection to system-specific operations. This is problematic because problems, hypothese...
Feng-Xian Ji, Xie Yu, Zhe-Xuan Cui et al.· 0 citations
Genuine embodied agency requires robots to turn continuous real-world experience into lasting, transferable skills. This demands continual learning that integrates new capabilities without eroding prior knowledge as tasks and environments evolve. Experience replay mitigates forgetting, but storing complete demonstratio...
Zi-Rong Song, Zheng Lu, Hao-Ran Liao et al.· 0 citations
Whether unlearning runs exhibit exploitable structure in weight space is investigated, and it is observed that models from different runs still lie in a shared evaluation-performance basin, suggesting that stronger models may be recovered through an unlearning-tailored soup strategy, reducing the need for repeated tuni...
This work introduces Causal-Plan-Bench, a high-fidelity diagnostic suite spanning four causal dimensions, curated via multi-stage verification, and initiate the first effort to turn agents from superficial token predictors into physically grounded causal reasoners, bridging language modeling and world modeling.
Zi-Rong Song, Zheng Lu, Ming-Qi Gao et al.· 3 citations
Vision-Language-Action (VLA) policies leverage pretrained vision-language models (VLMs) to guide action generation for robot control. VLMs provide hierarchical visual-semantic representations that evolve across layers, from local visual geometry to abstract, language-aligned semantics; different manipulation tasks may...
Zi-Rong Song, Zheng Lu, Hao-Ran Liao et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.