…We construct 75 social roles across five granularity levels and collect 91,200 role-conditioned responses over shared questions and prompt variants, then extract role-level hidden states and project them onto…
…We establish a unified taxonomy covering the broad landscape of AVI tasks, ranging from understanding (e.g., speech recognition , sound localization ) to generation (e.g., audio-driven video synthesis , video-to-audio…
…The following papers were recommended by the Semantic Scholar API Efficiency Follows Global-Local Decoupling (2026) Rethinking Attention Output Projection: Structured Hadamard Transforms for Efficient Transformers (2026) InfoMamba: An Attention-Free Hybrid…
…Project page GitHub 8 Add to collection Community Hi everyone, I’m one of the authors. Happy to answer questions about the method, evaluation setup, or reproducibility. This is an automated message…
…For more details, check out our project site: https://flat-pack-bench.github.io/ This is an automated message from the Librarian Bot . I found the following papers similar to this paper…
…We also reveal that strategies that change how the reviewer interprets the paper, such as related-work repositioning and analytical discussion expansion , substantially outperform surface edits such as local polishing, table formatting…
…View arXiv page View PDF Project page GitHub 19 Add to collection Community DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory This is an automated message from the Librarian Bot…
…project page includes pretrained checkpoints, code for training and evaluation, quantitative results, qualitative comparisons, the arXiv preprint, and a Google Colab demo: https://vitup.papers.discuna.com/ This is an automated message…
…Although the three variables x, epsilon, and v are linearly convertible for a fixed corruption time, a local Gaussian analysis shows that velocity regression inherits an isotropic target-covariance floor and amplifies…
…This formulation unifies category-conditioned counting with interpretable spatial localization. To support this setting, we construct CLOC, a Cross-domain Large-scale Object Counting dataset that reorganizes diverse public data sources into…