We present PromptGAR, a novel framework for Group Activity Recognition (GAR) that offering both input flexibility and high recognition accuracy. The existing approaches suffer from limited real-world applicability due to their reliance on full prompt annotations, fixed number of frames and instances, and the lack of actor consistency. To bridge the gap, we proposed PromptGAR, which is the first GAR model to provide input flexibility across prompts, frames, and instances without the need for retraining. We leverage diverse visual prompts-like bounding boxes, skeletal keypoints, and instance identities-by unifying them as point prompts. A recognition decoder then cross-updates class and prompt tokens for enhanced performance. To ensure actor consistency for extended activity durations, we also introduce a relative instance attention mechanism that directly encodes instance identities. Comprehensive evaluations demonstrate that PromptGAR achieves competitive performances both on full prompts and partial prompt inputs, establishing its effectiveness on input flexibility and generalization ability for real-world applications.
Abstract Anthropologists and other scholarly authors are increasingly expected to disclose and describe their use of generative AI. In this commentary, we sketch emerging practices of AI disclosure and attribution, consider how these practices might be adapted to address anthropology's distinctive epistemic and ethical commitments, and recommend strategies for AI disclosure that build on existing norms in anthropological publishing. Looking beyond publishers’ policies, we also examine how the expectation to disclose AI use is being codified across scales and sectors, contextualizing anthropologists’ decision‐making with respect to relevant trends in other regulatory and professional domains.
This report analyzes salary data for professional staff working in ARL member libraries during 2025. In the Salary Survey, data for university library staff are usually reported in three distinct groups: general library systems, health sciences libraries, and law libraries.
Local-cloud collaboration is a practical way to deploy large language models under resource constraints, but existing methods often rely on trained routers or collaboration-aware finetuning that tie routing behavior to a particular operating regime. In this work, we show that such training may be unnecessary: the local model's own inference-time agreement across sampled responses already provides a strong signal for deciding when to trust local execution and when to offload to a stronger cloud model. We propose CARGO, a training-free routing framework that estimates this agreement through prompt-varied sampling, applies Bayesian early stopping for sample-efficient uncertainty control, and supports arbitrary target collaboration ratios through lightweight deployment-time calibration. Across diverse reasoning and question-answering tasks, multiple local LLM families and scales, and both pretrained and finetuned local models, CARGO consistently outperforms other training-free baselines and in several settings surpasses supervised learned routers. These results suggest that effective and adaptable local-cloud collaboration can emerge directly from the local model's intrinsic response behavior, without requiring an additional trained router.
