…Four core designs drive our architecture: (1) Hybrid Linear Attention combines frame-wise Gated DeltaNet (GDN) with softmax attention for memory-efficient long-context modeling. (2) Dual-Branch Camera Control ensures precise…
…No dataset linking this paper Cite arxiv.org/abs/2604.26904 in a dataset README.md to link it from this page. No Space linking this paper Cite arxiv.org/abs/2604…
…No dataset linking this paper Cite arxiv.org/abs/2604.23195 in a dataset README.md to link it from this page. No Space linking this paper Cite arxiv.org/abs/2604…
…Jointly Modeling Video Dynamics and Actions for Generalizable Robot Control (2026) VAG: Dual-Stream Video-Action Generation for Embodied Data Synthesis (2026) R3DP: Real-Time 3D-Aware Policy for Embodied Manipulation (2026…
…No dataset linking this paper Cite arxiv.org/abs/2604.28139 in a dataset README.md to link it from this page. No Space linking this paper Cite arxiv.org/abs/2604…
…View arXiv page View PDF Add to collection Community EverAnimate code, 480p LoRA checkpoints, minimal demo data, and training/inference scripts are now released: https://huggingface.co/epfl-vita/everanimate Resources: Code…
…after the bridge and outperforms a matched replay control by 2.8 points. The operational principal is to avoid using scarce labeled data on the least prepared policy: use sparse reward for…
…No dataset linking this paper Cite arxiv.org/abs/2605.09196 in a dataset README.md to link it from this page. No Space linking this paper Cite arxiv.org/abs/2605…
…In low-data fine-tuning settings, DLR matches or outperforms supervised fine-tuning across four datasets and six models, achieving a mean gain of +6.6 percentage points, while prior discrete-latent…
…MLS-Bench contains 140 tasks across 12 domains, each requiring an agent to improve one targeted component of an ML system or algorithm and demonstrate that the improvement generalizes across controlled settings…