MG-RWKV: Multi-Grained Context-Aware RWKV for Temporal Forgery Localization
A multi-granularity RWKV framework for Temporal Forgery Localization that achieves state-of-the-art performance with linear O(T) complexity.
Publications
Research papers and scientific articles.
DeskCraft: Benchmarking Desktop Agents on Professional Workflows and Human-in-the-Loop Collaboration
A desktop GUI agent benchmark targeting long-horizon professional workflows and proactive human-agent collaboration.
Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training
A fully open-source multi-module agent framework for deep research agents and agent foundation models training.
AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents
An adaptive user-centric memory framework for long-horizon dialogue agents.
FCL-COD: Weakly Supervised Camouflaged Object Detection with Frequency-aware and Contrastive Learning
A frequency-aware and contrastive learning-based weakly-supervised camouflaged object detection framework.
Natural-Language Agent Harnesses
Externalizing agent harness control logic as portable natural-language artifacts with a shared runtime.
SAHSR: Semantic Alignment and Hard-Sample Retraining Framework for Cross-Modal Person Re-Identification
A framework addressing semantic mismatch and hard-sample discrimination in Visible-Infrared Person Re-Identification.
IteRPrimE: Zero-shot Referring Image Segmentation with Iterative Grad-CAM Refinement and Primary Word Emphasis
A method for zero-shot referring image segmentation with iterative Grad-CAM refinement and primary word emphasis.