3 citations · 7 across the 26 of their papers we have counts for
27 papers
OccamView: Object-Conditioned View Selection for Frame-Budgeted Active 3D Gaussian Reconstruction
Hongbo Gao, Wei Zhang, Zeyu Ni +4
Active 3D Gaussian reconstruction fundamentally relies on selecting informative next-best views under limited sensing budgets. Existing active 3DGS methods primarily plan viewpoint…
LoSA: Near-Lossless Sparse Attention for Training-Free Video Diffusion Acceleration
Enhuai Liu, Yunke Wang, Yutong Wang +2
Video diffusion transformers are costly to sample: every denoising step applies self-attention over a long 3D token sequence, a quadratic cost that dominates as resolution and dura…
StellaVLA: In-Context Structured Demonstration for Generalizable Vision-Language-Action Models
Siyu Xu, Yunke Wang, Zijian Wang +6
Vision-Language-Action (VLA) models can follow instructions and manipulate objects, but their performance often collapses out of distribution (OOD), when the scene, viewpoint, or o…
Diversifying Personalized Research Ideation against AI-Induced Homogenization
Rui Xu, Yunke Wang, Linwei Tao +2
AI-assisted research ideation has emerged as a promising paradigm for accelerating scientific discovery, with systems now capable of generating research directions conditioned on p…
PARE: Pruning and Adaptive Routing for Efficient Video Generation
Yutong Wang, Yunke Wang, Tianfan Xue +4
Video Diffusion Transformers (DiTs) generate high-quality videos but demand substantial compute due to wide blocks, deep architectures, and iterative sampling. Recent methods reduc…
BEAT: Rhythm-Elastic Alignment for Agentic Music-guided Movie Trailer Generation
Yutong Wang, Yunke Wang, Xinyuan Chen +1
Automatic movie trailer generation must select shots from a full-length film and synchronize them with background music. Existing methods either relegate music alignment to post-pr…
See What Matters: Differentiable Grid Sample Pruning for Generalizable Vision-Language-Action Model
Yixu Feng, Zinan Zhao, Yanxiang Ma +4
Vision-Language-Action (VLA) models have shown remarkable promise in robotics manipulation, yet their high computational cost hinders real-time deployment. Existing token pruning m…
Early Semantic Grounding in Image Editing Models for Zero-Shot Referring Image Segmentation
Jingxuan He, Xiyu Wang, Yunke Wang +2
Instruction-based image editing (IIE) models have recently demonstrated strong capability in modifying specific image regions according to natural language instructions, which impl…
Seeing Realism from Simulation: Efficient Video Transfer for Vision-Language-Action Data Augmentation
Chenyu Hui, Xiaodi Huang, Siyu Xu +5
Vision-language-action (VLA) models typically rely on large-scale real-world videos, whereas simulated data, despite being inexpensive and highly parallelizable to collect, often s…
Rethinking Where to Edit: Task-Aware Localization for Instruction-Based Image Editing
Jingxuan He, Xiyu Wang, Mengyu Zheng +3
Instruction-based image editing (IIE) aims to modify an image according to a natural language instruction. Despite recent advances in diffusion transformers, existing methods often…
HiCI: Hierarchical Construction-Integration for Long-Context Attention
Xiangyu Zeng, Qi Xu, Yunke Wang +1
Long-context language modeling is commonly framed as a scalability challenge of token-level attention, yet local-to-global information structuring remains largely implicit in exist…
Prepare to Turn: Learning Anticipatory Maneuvering for Fast Sequential Quadrupedal Navigation
Zunzhi You, Yunke Wang, Haolan Guo +1
Fast quadrupedal navigation requires preparing for the next turn while approaching the current goal. Policies trained to reach and remain at a single target can instead produce sto…
Affordance Field Intervention: Enabling VLAs to Escape Memory Traps in Robotic Manipulation
Siyu Xu, Zijian Wang, Yunke Wang +3
Vision-Language-Action (VLA) models have shown great performance in robotic manipulation by mapping visual observations and language instructions directly to actions. However, they…
MambaScope: Coarse-to-Fine Scoping for Efficient Vision Mamba
Shanhui Liu, Rui Xu, Yunke Wang
Vision Mamba has emerged as a promising and efficient alternative to Vision Transformers, yet its efficiency remains fundamentally constrained by the number of input tokens. Existi…
NashPG: A Policy Gradient Method with Iteratively Refined Regularization for Finding Nash Equilibria
Eason Yu, Tzu Hao Liu, Clément L. Canonne +4
Finding Nash equilibria in two-player zero-sum imperfect-information games remains a central challenge in multi-agent reinforcement learning. Recent multi-round regularization meth…
Action-aware Dynamic Pruning for Efficient Vision-Language-Action Manipulation
Xiaohuan Pei, Yuxing Chen, Siyu Xu +3
Robotic manipulation with Vision-Language-Action models requires efficient inference over long-horizon multi-modal context, where attention to dense visual tokens dominates computa…
Rethinking Visual Token Reduction in LVLMs Under Cross-Modal Misalignment
Rui Xu, Yunke Wang, Yong Luo +1
Large Vision-Language Models (LVLMs) encode visual inputs as dense sequences of patch-level tokens to capture fine-grained semantics. These visual tokens often outnumber their text…
Marine Saliency Segmenter: Object-Focused Conditional Diffusion with Region-Level Semantic Knowledge Distillation
Laibin Chang, Yunke Wang, JiaXing Huang +3
Marine Saliency Segmentation (MSS) plays a pivotal role in various vision-based marine exploration tasks. However, existing marine segmentation techniques face the dilemma of objec…
VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching
Siyu Xu, Yunke Wang, Chenghao Xia +3
Vision-Language-Action (VLA) models have demonstrated strong multi-modal reasoning capabilities, enabling direct action generation from visual perception and language instructions…
Position: AI Scaling: From Up to Down and Out
Yunke Wang, Yanxi Li, Chang Xu
AI Scaling has traditionally been synonymous with Scaling Up, which builds larger and more powerful models. However, the growing demand for efficiency, adaptability, and collaborat…
FusionSAM: Visual Multi-Modal Learning with Segment Anything
Daixun Li, Weiying Xie, Mingxiang Cao +5
Multimodal image fusion and semantic segmentation are critical for autonomous driving. Despite advancements, current models often struggle with segmenting densely packed elements d…
CollagePrompt: A Benchmark for Budget-Friendly Visual Recognition with GPT-4V
Siyu Xu, Yunke Wang, Daochang Liu +2
Recent advancements in generative AI have suggested that by taking visual prompts, GPT-4V can demonstrate significant proficiency in visual recognition tasks. Despite its impressiv…
Visual Imitation Learning with Calibrated Contrastive Representation
Yunke Wang, Linwei Tao, Bo Du +2
Adversarial Imitation Learning (AIL) allows the agent to reproduce expert behavior with low-dimensional states and actions. However, challenges arise in handling visual states due…
MAEDiff: Masked Autoencoder-enhanced Diffusion Models for Unsupervised Anomaly Detection in Brain Images
Rui Xu, Yunke Wang, Bo Du
Unsupervised anomaly detection has gained significant attention in the field of medical imaging due to its capability of relieving the costly pixel-level annotation. To achieve thi…