144 citations · 865 across the 49 of their papers we have counts for
53 papers
InJePA: Intention-First Latent Planning with Coupled JEPA World Models for Visual Navigation
Siming Zhou, Bowen Ma, Ruiran Du +7
Visual navigation requires goal directed planning informed by predictions of environment dynamics. Representative navigation world model methods propose complete action candidates…
Hypernetwork-Parameterized Spatially Adaptive Neural Operators for PDE Learning
Jiaquan Zhang, Chaoning Zhang, Shuxu Chen +7
Spatially heterogeneous partial differential equations (PDEs) exhibit location-dependent dynamics arising from variations in geometry and physical coefficients. Existing neural ope…
When and What to Teach: Budget-Aware Online Adaptation for Web Agents
Jianwei Zhang, Sihan Cao, Pengcheng Zheng +7
Web agents have achieved significant success in automating complex internet tasks but deploying them in real-world environments requires continuous online adaptation. Given that de…
Geometry-aware Incremental Neural Operator for Long-Horizon PDE prediction
Jiaquan Zhang, Shuxu Chen, Haifan Meng +6
Neural operators have shown strong potential for learning solution operators of partial differential equations (PDEs). However, long-horizon autoregressive prediction remains chall…
HERO: History-Enriched Rollout Training for Long-Horizon Autoregressive Neural Operators
Jiaquan Zhang, Shuxu Chen, Haifan Meng +6
Neural operators provide fast surrogates for time-dependent partial differential equations (PDEs) by applying a learned evolution operator recursively to its own predictions, but t…
TF-SNO: Time-Frequency Gated Spectral Neural Operators for Learning Non-Stationary Partial Differential Equations
Yitian Zhou, Chaoning Zhang, Zhenzhen Huang +8
Non-stationary partial differential equations (PDEs) arise throughout scientific computing, where the dominant frequency content and energy distribution can drift over time. While…
Autoregression-Free Neural Operators for Time-Dependent PDEs
Jiaquan Zhang, Caiyan Qin, Haoyu Bian +7
Neural operators learn mappings from function-dependent inputs to solutions, providing an effective framework for solving partial differential equations (PDEs). For time-dependent…
Efficient RAG with Intent-Aware Retrieval and Semantics-Preserving Chunking
Fachrina Dewi Puspitasari, Chaoning Zhang, Jiaquan Zhang +6
The demand for powerful instruction following and reasoning capability of large language models (LLMs) has promoted rapid development of retrieval-augmented generation (RAG). The R…
From Talking to Singing: A New Challenge for Audio-Visual Deepfake Detection
Ke Liu, Jiwei Wei, Wenyu Zhang +5
With rapid advances in audio-visual generative models, reliable forgery detection becomes increasingly critical. Existing methods for audio-visual deepfake detection typically rely…
CAP-CoT: Cycle Adversarial Prompt for Improving Chain of Thoughts in LLM Reasoning
Shuxu Chen, Yitian Zhou, Jiaquan Zhang +6
Chain-of-Thought (CoT) prompting has emerged as a simple and effective way to elicit step-by-step solutions from large language models (LLMs). However, CoT reasoning can be unstabl…
Topology-Aware Layer Pruning for Large Vision-Language Models
Pengcheng Zheng, Chaoning Zhang, Ya Wen +10
Large Language Models (LLMs) have demonstrated strong capabilities in natural language understanding and reasoning, while recent extensions that incorporate visual inputs enable th…
Exploring Kernel Transformations for Implicit Neural Representations
Sheng Zheng, Chaoning Zhang, Dongshen Han +4
Implicit neural representations (INRs), which leverage neural networks to represent signals by mapping coordinates to their corresponding attributes, have garnered significant atte…
A Complete Survey on LLM-based AI Chatbots
Sumit Kumar Dam, Choong Seon Hong, Yu Qiao +1
The past few decades have witnessed an upsurge in data, forming the foundation for data-hungry, learning-based AI technology. Conversational agents, often referred to as AI chatbot…
Logit Calibration and Feature Contrast for Robust Federated Learning on Non-IID Data
Yu Qiao, Chaoning Zhang, Apurba Adhikary +1
Federated learning (FL) is a privacy-preserving distributed framework for collaborative model training on devices in edge networks. However, challenges arise due to vulnerability t…
FedCCL: Federated Dual-Clustered Feature Contrast Under Domain Heterogeneity
Yu Qiao, Huy Q. Le, Mengchun Zhang +3
Federated learning (FL) facilitates a privacy-preserving neural network training paradigm through collaboration between edge clients and a central server. One significant challenge…
Towards Understanding Dual BN In Hybrid Adversarial Training
Chenshuang Zhang, Chaoning Zhang, Kang Zhang +3
There is a growing concern about applying batch normalization (BN) in adversarial training (AT), especially when the model is trained on both adversarial samples and clean samples…
Towards Robust Federated Learning via Logits Calibration on Non-IID Data
Yu Qiao, Apurba Adhikary, Chaoning Zhang +1
Federated learning (FL) is a privacy-preserving distributed management framework based on collaborative model training of distributed devices in edge networks. However, recent stud…
Sora as a World Model? A Complete Survey on Text-to-Video Generation
Fachrina Dewi Puspitasari, Chaoning Zhang, Joseph Cho +13
The evolution of video generation from text, from animating MNIST to simulating the world with Sora, has progressed at a breakneck speed. Here, we systematically discuss how far te…
Interpreting and Improving Attention From the Perspective of Large Kernel Convolution
Chenghao Li, Chaoning Zhang, Boheng Zeng +7
Attention mechanisms have significantly advanced visual models by capturing global context effectively. However, their reliance on large-scale datasets and substantial computationa…
MobileSAMv2: Faster Segment Anything to Everything
Chaoning Zhang, Dongshen Han, Sheng Zheng +3
Segment anything model (SAM) addresses two practical yet challenging segmentation tasks: \textbf{segment anything (SegAny)}, which utilizes a certain point to predict the mask for…
Single Image Reflection Removal with Patch Reflectance Prior
Dongshen Han, Heechan Yoon, Hyukmin Kwon +4
Single Image Reflection Removal (SIRR) in real-world images is a challenging task due to diverse image degradations occurring on the glass surface during light transmission and ref…
Understanding Segment Anything Model: SAM is Biased Towards Texture Rather than Shape
Chaoning Zhang, Yu Qiao, Shehbaz Tariq +5
In contrast to the human vision that mainly depends on the shape for recognizing the objects, deep image recognition models are widely known to be biased toward texture. Recently,…
Toward a Deeper Understanding: RetNet Viewed through Convolution
Chenghao Li, Chaoning Zhang
The success of Vision Transformer (ViT) has been widely reported on a wide range of image recognition tasks. ViT can learn global dependencies superior to CNN, yet CNN's inherent l…
SAM Meets UAP: Attacking Segment Anything Model With Universal Adversarial Perturbation
Dongshen Han, Chaoning Zhang, Sheng Zheng +3
As Segment Anything Model (SAM) becomes a popular foundation model in computer vision, its adversarial robustness has become a concern that cannot be ignored. This works investigat…