30 citations · 44 across the 15 of their papers we have counts for
16 papers
EvoTok: A Unified Image Tokenizer via Residual Latent Evolution for Visual Understanding and Generation
Yan Li, Ning Liao, Xiangyu Zhao +5
The development of unified multimodal large language models (MLLMs) is fundamentally challenged by the granularity gap between visual understanding and generation: understanding re…
CrossEarth-SAR: A SAR-Centric and Billion-Scale Geospatial Foundation Model for Domain Generalizable Semantic Segmentation
Ziqi Ye, Ziyang Gong, Ning Liao +10
Synthetic Aperture Radar (SAR) enables global, all-weather earth observation. However, owing to diverse imaging mechanisms, domain shifts across sensors and regions severely hinder…
FineRMoE: Dimension Expansion for Finer-Grained Expert with Its Upcycling Approach
Ning Liao, Xiaoxing Wang, Xiaohan Qin +1
As revealed by the scaling law of fine-grained MoE, model performance ceases to be improved once the granularity of the intermediate dimension exceeds the optimal threshold, limiti…
Repulsor: Accelerating Generative Modeling with a Contrastive Memory Bank
Shaofeng Zhang, Xuanqi Chen, Ning Liao +7
The dominance of denoising generative models (e.g., diffusion, flow-matching) in visual synthesis is tempered by their substantial training costs and inefficiencies in representati…
Co-Training Vision Language Models for Remote Sensing Multi-task Learning
Qingyun Li, Shuran Ma, Junwei Luo +8
With Transformers achieving outstanding performance on individual remote sensing (RS) tasks, we are now approaching the realization of a unified model that excels across multiple t…
NTKMTL: Mitigating Task Imbalance in Multi-Task Learning from Neural Tangent Kernel Perspective
Xiaohan Qin, Xiaoxing Wang, Ning Liao +1
Multi-Task Learning (MTL) enables a single model to learn multiple tasks simultaneously, leveraging knowledge transfer among tasks for enhanced generalization, and has been widely…
ssToken: Self-modulated and Semantic-aware Token Selection for LLM Fine-tuning
Xiaohan Qin, Xiaoxing Wang, Ning Liao +5
Data quality plays a critical role in enhancing supervised fine-tuning (SFT) for large language models (LLMs), and token-level data selection has emerged as a promising direction f…
Innovator: Scientific Continued Pretraining with Fine-grained MoE Upcycling
Ning Liao, Xiaoxing Wang, Zehao Lin +18
A large language model (LLM) with knowledge in both scientific and general tasks is the foundation of science general intelligence. However, directly continued pretraining an LLM u…
Modeling All Response Surfaces in One for Conditional Search Spaces
Jiaxing Li, Wei Liu, Chao Xue +4
Bayesian Optimization (BO) is a sample-efficient black-box optimizer commonly used in search spaces where hyperparameters are independent. However, in many practical AutoML scenari…
Boosting Order-Preserving and Transferability for Neural Architecture Search: a Joint Architecture Refined Search and Fine-tuning Approach
Beichen Zhang, Xiaoxing Wang, Xiaohan Qin +1
Supernet is a core component in many recent Neural Architecture Search (NAS) methods. It not only helps embody the search space but also provides a (relative) estimation of the fin…
Poisson Process for Bayesian Optimization
Xiaoxing Wang, Jiaxing Li, Chao Xue +5
BayesianOptimization(BO) is a sample-efficient black-box optimizer, and extensive methods have been proposed to build the absolute function response of the black-box function throu…
EAutoDet: Efficient Architecture Search for Object Detection
Xiaoxing Wang, Jiale Lin, Junchi Yan +2
Training CNN for detection is time-consuming due to the large dataset and complex network modules, making it hard to search architectures on detection datasets directly, which usua…
ZARTS: On Zero-order Optimization for Neural Architecture Search
Xiaoxing Wang, Wenxuan Guo, Junchi Yan +2
Differentiable architecture search (DARTS) has been a popular one-shot paradigm for NAS due to its high efficiency. It introduces trainable architecture parameters to represent the…
DAAS: Differentiable Architecture and Augmentation Policy Search
Xiaoxing Wang, Xiangxiang Chu, Junchi Yan +1
Neural architecture search (NAS) has been an active direction of automatic machine learning (Auto-ML), aiming to explore efficient network structures. The searched architecture is…
ROME: Robustifying Memory-Efficient NAS via Topology Disentanglement and Gradient Accumulation
Xiaoxing Wang, Xiangxiang Chu, Yuda Fan +4
Albeit being a prevalent architecture searching approach, differentiable architecture search (DARTS) is largely hindered by its substantial memory cost since the entire supernet re…
DARTS-: Robustly Stepping out of Performance Collapse Without Indicators
Xiangxiang Chu, Xiaoxing Wang, Bo Zhang +3
Despite the fast development of differentiable architecture search (DARTS), it suffers from long-standing performance instability, which extremely limits its application. Existing…