activity
20232026
most citedDR-Encoder: Encode Low-rank Gradients with Random Prior for Large Language Models Differentially Privately

4 citations · 11 across the 34 of their papers we have counts for

collaborators
Showing cs.CVShow all

18 papers · 1 filter

cs.CV2026

Remember-R1: Mitigating Long-Context Visual Forgetting through Reinforcement Learning

Jianmin Chen, Jiaqi Tang, Wei Wei +9

Multimodal large language models (MLLMs) increasingly rely on long chain-of-thought reasoning for complex tasks. However, as reasoning sequences lengthen, models may gradually rely…

cs.CV2026

Unveiling the Unknown: Open Vocabulary Object Detection with Scene Graphs

Yi Chen, Yinghao Lu, Zhehao Li +4

Open-vocabulary object detection seeks to identify novel object categories that were not part of the training data. Many knowledge distillation-based approaches have shown promisin…

cs.CV2026

HoloFair: Unified T2I Fairness Evaluation and Fair-GRPO Debiasing

Ruyi Chen, Lu Zhou, Xiaogang Xu +3

Text-to-Image (T2I) models have made significant strides in visual realism and semantic consistency, yet they often perpetuate and amplify societal biases. Existing evaluation meth…

cs.CV2026

AHPA: Adaptive Hierarchical Prior Alignment for Diffusion Transformers

Ruibin Min, Yexin Liu, Aimin Pan +5

Representation alignment has recently emerged as an effective paradigm for accelerating Diffusion Transformer training. Despite their success, existing alignment methods typically…

cs.CV2026

Low-Light Video Enhancement with An Effective Spatial-Temporal Decomposition Paradigm

Xiaogang Xu, Kun Zhou, Tao Hu +4

Low-Light Video Enhancement (LLVE) seeks to restore dynamic or static scenes plagued by severe invisibility and noise. In this paper, we present an innovative video decomposition s…

cs.CV2025

Class Incremental Medical Image Segmentation via Prototype-Guided Calibration and Dual-Aligned Distillation

Shengqian Zhu, Chengrong Yu, Qiang Wang +6

Class incremental medical image segmentation (CIMIS) aims to preserve knowledge of previously learned classes while learning new ones without relying on old-class labels. However,…