Multimodal Continual Instruction Tuning (MCIT) aims to exploit the incrementally accumulated knowledge to process multimodal inputs of diverse tasks, where parameter routing plays an important role. State-of-the-art methods rely on sample-to-task center similarity and cross-modal fusion with equal weight during routing...
Kun-Lun Xu, Yan-Qin Zhang, Wen-Wen Qiang et al.· 0 citations
Scaling robot manipulation models requires large amounts of interaction data, yet collecting diverse real-robot experience remains costly. Human manipulation videos, in contrast, provide abundant and diverse task experience that could potentially benefit robot learning. However, differences in morphology, action spaces...
Xing-Yu Zhang, Ying-Chao Li, Pei-Zheng Guo et al.· 0 citations
Time series forecasting (TSF) plays an important role in a wide range of real-world applications. Recently, time series foundation models (TSFMs), pretrained on large-scale datasets, have demonstrated strong generalization capabilities and emerged as an important paradigm for TSF. Reinforcement learning (RL) post-train...
Jian-Qi Zhang, Xing-Yu Zhang, Ze-En Song et al.· 1 citation
GAPrompt++ is proposed, a multi-granular geometry-aware prompting method that provides richer geometric guidance for efficient 3D task adaptation and achieves state-of-the-art performance among prompting-based PEFT methods and even surpasses full fine-tuning across diverse benchmarks, while requiring less than 2% train...
Zi-Xiang Ai, Zhen-Yu Cui, Yu-Fei Guo et al.· IEEE Transactions on Pattern...· 0 citations
This work introduces CutCraft, the first benchmark for editing-technique execution in multi-shot audio-video generation and designs an agentic editing baseline that decomposes generation into planning, shot-level synthesis, and post-hoc composition, explicitly realizing editing semantics such as J-cuts, L-cuts, and tra...
Tian-Yi Zeng, Junchao Liao, Yu-Jie Wei et al.· 1 citation
Temporal GRPO addresses the problem of trajectory-level credit aliasing in post-train VLA policies by constructing detectable task stages, aligning each rollout with stage-specific action intervals, and comparing only rollouts that have entered the same stage.
Gradient Uncertainty-Aware Policy Optimization is proposed, which models each group gradient as a random variable under a Bayesian formulation and estimates its probability distribution and derives gradient uncertainty using a Dirichlet-based formulation and uses it to calibrate the contribution of each group gradient...
Peizheng Guo, Jian-Qi Zhang, Xing-Yu Zhang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.