3 papers
cs.CV2026
GramLoop: Training-Free Gram-Gated Replay for Robust Dense Prediction
Yang Chen, Canyu Shen, Xinzhe Rao +5
We aim to improve frozen DINOv3 dense-prediction models under distribution shift by adding inference computation inside the visual backbone, without changing model weights, task ad…
cs.CV2026
Training-Free Hidden-State Refinement for Flow-Matching Image Generators
Yuanyi Yan, Xinzhe Rao, Canyu Shen +5
We aim to improve frozen flow-matching image generators by adding inference computation inside the denoiser, without changing model weights or the outer sampler. Existing generator…
cs.LG2026
Drift-Aware Multimodal User Representation Learning via Multi-Scale Temporal Modeling and Sparse Mixture-of-Experts
Ziqing Qian, Haohang Chen, Shengqi Dang +4
Understanding user preferences from noisy and temporally evolving social media behaviors is fundamentally challenging due to interest drift, where user preferences shift across tim…