Fei Wu

NaviCache redefines how we approach computational efficiency in video generation, achieving superior error judgment and performance without the burdens of traditional calibration methods.

ForeAgent outperforms existing deepfake detection methods by 16.41% while continuously evolving its reasoning capabilities through self-reflection and high-quality sample generation.

Observational metrics can mislead evaluations of VLA models, revealing that high trajectory quality does not guarantee meaningful CoT reasoning.

Even state-of-the-art AI-generated image detectors struggle when images are cropped, resized, or compressed, revealing a critical gap in real-world robustness.

Fuzzy logic bridges the gap between LLM reasoning and low-level artifact detection, creating a surprisingly effective AI-generated image detector.

Forget outcome-based filtering: TopoCurate uses interaction topology to surface informative tool-use trajectories and tasks, boosting SFT and RL performance by up to 6.9%.

Achieve Transformer-level handwritten text recognition accuracy with 1.6-1.9x faster inference and 38-42% less memory by ditching attention for a linear-time RetNet architecture.

Forget expensive MoE training from scratch: ExpertWeaver unlocks inherent MoE structure within dense LLMs using GLU activation patterns, offering a training-free conversion.