1 citations · 1 across the 7 of their papers we have counts for
7 papers
Embedding Compression via Spherical Coordinates
Han Xiao
We present an -bounded compression method for unit-norm embeddings that achieves 1.5 compression, 25% better than the best prior lossless method. The method exploits tha…
Embedding Inversion via Conditional Masked Diffusion Language Models
Han Xiao
We frame embedding inversion as conditional masked diffusion, recovering all tokens in parallel through iterative denoising rather than sequential autoregressive generation. A mask…
MemGUI-Bench: Benchmarking Memory of Mobile GUI Agents in Dynamic Environments
Guangyi Liu, Pengxiang Zhao, Yaozhen Liang +12
Reliable mobile GUI agents must retain and reuse information across actions, applications, and repeated interactions. However, current benchmarks systematically underrepresent thes…
Mitigating the Safety Alignment Tax with Null-Space Constrained Policy Optimization
Yifan Niu, Han Xiao, Dongyi Liu +2
As Large Language Models (LLMs) are increasingly deployed in real-world applications, it is important to ensure their behaviors align with human values, societal norms, and ethical…
Improving Data-aware and Parameter-aware Robustness for Continual Learning
Hanxi Xiao, Fan Lyu
The goal of Continual Learning (CL) task is to continuously learn multiple new tasks sequentially while achieving a balance between the plasticity and stability of new and old know…
Learning Accurate Performance Predictors for Ultrafast Automated Model Compression
Ziwei Wang, Jiwen Lu, Han Xiao +2
In this paper, we propose an ultrafast automated model compression framework called SeerNet for flexible network deployment. Conventional non-differen-tiable methods discretely sea…
Token-Label Alignment for Vision Transformers
Han Xiao, Wenzhao Zheng, Zheng Zhu +2
Data mixing strategies (e.g., CutMix) have shown the ability to greatly improve the performance of convolutional neural networks (CNNs). They mix two images as inputs for training…