21 citations · 22 across the 12 of their papers we have counts for
7 papers · 1 filter
Cut-ViT: Task-Specific Model Pruning via Gram Anchoring Subspace Consistency
Jianjian Yin, Liulei Li, Tao Chen +3
Pruning visual foundation models has attracted considerable attention. However, existing methods focus on rigid point-to-point token alignment on a single dataset for pruning, suff…
Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation
Hongyu Qu, Jianzhe Gao, Xiaobin Hu +6
Mainstream Vision-Language-Action (VLA) models predict actions primarily from the current observation under a Markovian assumption, thus struggling with long-horizon, temporally de…
SinkTrack: Attention Sink based Context Anchoring for Large Language Models
Xu Liu, Guikun Chen, Wenguan Wang
Large language models (LLMs) suffer from hallucination and context forgetting. Prior studies suggest that attention drift is a primary cause of these problems, where LLMs' focus sh…
Learning 3D Representations for Spatial Intelligence from Unposed Multi-View Images
Bo Zhou, Qiuxia Lai, Zeren Sun +3
Robust 3D representation learning forms the perceptual foundation of spatial intelligence, enabling downstream tasks in scene understanding and embodied AI. However, learning such…
Iris: Bringing Real-World Priors into Diffusion Model for Monocular Depth Estimation
Xinhao Cai, Gensheng Pei, Zeren Sun +3
In this paper, we propose \textbf{Iris}, a deterministic framework for Monocular Depth Estimation (MDE) that integrates real-world priors into the diffusion model. Conventional fee…
PKINet-v2: Towards Powerful and Efficient Poly-Kernel Remote Sensing Object Detection
Xinhao Cai, Liulei Li, Gensheng Pei +3
Object detection in remote sensing images (RSIs) is challenged by the coexistence of geometric and spatial complexity: targets may appear with diverse aspect ratios, while spanning…
Spatio-temporal Decoupled Knowledge Compensator for Few-Shot Action Recognition
Hongyu Qu, Xiangbo Shu, Rui Yan +3
Few-Shot Action Recognition (FSAR) is a challenging task that requires recognizing novel action categories with a few labeled videos. Recent works typically apply semantically coar…