Tag: #research297 results
DRPO tackles model collapse in off-policy generative recommendation via optimistic distributionally robust optimization. Proves hard filtering recovers high-quality data from noisy logs. Achieves SOTA on mixed-quality benchmarks.
RLCER reinforces chain-of-thought via self-evolving rubrics without human labels. Outperforms outcome-centric RLVR on reasoning tasks. Rubrics boost inference as prompts.
Explores adaptive rewiring and sparsification for scalable GNNs using Erdős-Rényi models. Tested on power grid N-1 analysis with GCN/GIN. Balances sparsity for generalization via tuning and early stopping.
RealHD offers 730k high-quality real and AI-generated images from advanced methods like text-to-image and inpainting. Addresses prior dataset flaws with diverse prompts, metadata, and masks. Includes lightweight noise entropy detection baseline with strong generalization.
Proposes quantum scheme using indefinite causal order (ICO) for integrated sensing and computation on one state. Agent superposes observation-then-compute and compute-then-observation orders. Achieves low losses in magnetic navigation tasks.
Co-jump enables two quadrupeds to synchronize jumps up to 1.5m via MAPPO and curriculum, without communication. Achieves 144% height gain over solo robots using proprioception. Transfers from sim to hardware.
Proposes principled upscaling for model widths inspired by μP, with theory guaranteeing equivalence to widened versions. Extends μTransfer for hyperparameter scaling, avoiding costly retuning at larger sizes. Applicable to diverse architectures and optimizers with infinite-width analysis.
ProtoGLAD detects graph-level anomalies by contrasting with nearest normal prototype graphs discovered via point-set kernels. It iteratively clusters normal graphs for unsupervised detection. Provides human-interpretable explanations outperforming black-box methods.
Framework anonymizes sensitive UI data with type-preserving placeholders for cloud-based GUI agents. Detects PII across screenshots, XML, and instructions via layered architecture. Achieves top privacy-utility trade-off on benchmarks.
PRISM-XR integrates multimodal LLMs for XR collaboration while filtering sensitive data from XR headset frames on edge servers. It features lightweight registration and customizable content-sharing for efficient synchronization. Evaluations show 90% accuracy in user requests and strong privacy protection.