199 citations · 209 across the 32 of their papers we have counts for
33 papers
TailSieve: Partial-Rollout-Guided Tail Routing for LLM Rollouts
Tianqi Xu, Lu Lv, Haoyang Huang +15
Large-scale rollouts have become a core component of modern LLM systems, spanning reinforcement learning (RL) post-training, on-policy distillation (OPD), and sampling-heavy evalua…
Task-Anchored Representation Shaping for Pre-Trained Model-Based Continual Learning
Zhiming Xu, Huiyu Yi, Zhen-Hao Xie +4
Pre-trained models (PTMs) provide a strong foundation for continual learning by offering stable representations that facilitate lightweight adaptation to new tasks. However, adapti…
-Mem: An Online Reliability Memory for LLM-based Multi-Agent Systems
Peilin Feng, Suorong Yang, Soujanya Poria
Memory is central to long-horizon LLM agents, yet existing memory systems primarily preserve interaction content rather than modeling which agents can be trusted and under what con…
Redirecting the Flow: Image Customization through Attention Distribution Shift
Jie Li, Suorong Yang, Jian Zhao +1
Subject-driven image customization aims to generate images that not only follow textual instructions but also preserve the identity of a given reference subject. Existing approache…
Beyond What to Select: A Plug-and-play Oscillatory Data-Volume Scheduling for Efficient Model Training
Suorong Yang, Hanqi Zhu, Hai Gan +4
Data selection accelerates training by identifying representative training data while preserving model performance. However, existing methods mainly focus on designing sample-impor…
Meow-Omni 1: A Multimodal Large Language Model for Feline Ethology
Jucheng Hu, Zhangquan Chen, Yulin Chen +9
Deciphering animal intent is a fundamental challenge in computational ethology, largely because of semantic aliasing, the phenomenon where identical external signals (e.g., a cat's…
PolyReal: A Benchmark for Real-World Polymer Science Workflows
Wanhao Liu, Weida Wang, Jiaqing Xie +12
Multimodal Large Language Models (MLLMs) excel in general domains but struggle with complex, real-world science. We posit that polymer science, an interdisciplinary field spanning…
Free-Flow Class-Incremental Learning: Towards Robust CIL under Variable Class Arrivals
Zhiming Xu, Baile Xu, Jian Zhao +2
Class-incremental learning (CIL) is commonly evaluated under predefined schedules with fixed or nearly equal class increments, leaving irregular class-arrival scenarios underexplor…
Data Agent: Learning to Select Data via End-to-End Dynamic Optimization
Suorong Yang, Fangjian Su, Hai Gan +5
Dynamic Data selection aims to accelerate training by prioritizing informative samples during online training. However, existing methods typically rely on task-specific handcrafted…
Structure-Level Disentangled Diffusion for Few-Shot Chinese Font Generation
Jie Li, Suorong Yang, Jian Zhao +1
Few-shot Chinese font generation aims to synthesize new characters in a target style using only a handful of reference images. Achieving accurate content rendering and faithful sty…
One-shot Optimized Steering Vector for Hallucination Mitigation for VLMs
Youxu Shi, Suorong Yang, Dong Liu
Vision Language Models (VLMs) achieve strong performance on multimodal tasks but still suffer from hallucination and safety-related failures that persist even at scale. Steering of…
Pushing the Limits of Distillation-Based Continual Learning via Classifier-Proximal Lightweight Plugins
Zhiming Xu, Baile Xu, Jian Zhao +2
Continual learning requires models to learn continuously while preserving prior knowledge under evolving data streams. Distillation-based methods are appealing for retaining past k…
On-the-Fly Data Augmentation via Gradient-Guided and Sample-Aware Influence Estimation
Suorong Yang, Jie Zong, Lihang Wang +6
Data augmentation has been widely employed to improve the generalization of deep neural networks. Most existing methods apply fixed or random transformations. However, we find that…
Exposing Hallucinations To Suppress Them: VLMs Representation Editing With Generative Anchors
Youxu Shi, Suorong Yang, Dong Liu
Multimodal large language models (MLLMs) have achieved remarkable success across diverse vision-language tasks, yet they remain highly susceptible to hallucinations, producing cont…
IPF-RDA: An Information-Preserving Framework for Robust Data Augmentation
Suorong Yang, Hongchao Yang, Suhan Guo +2
Data augmentation is widely utilized as an effective technique to enhance the generalization performance of deep models. However, data augmentation may inevitably introduce distrib…
-AttnMask: Attention-Guided Masked Hidden States for Efficient Data Selection and Augmentation
Jucheng Hu, Suorong Yang, Dongzhan Zhou
Visual Instruction Finetuning (VIF) is pivotal for post-training Vision-Language Models (VLMs). Unlike unimodal instruction finetuning in plain-text large language models, which ma…
Multimodal-Guided Dynamic Dataset Pruning for Robust and Efficient Data-Centric Learning
Suorong Yang, Peijia Li, Yujie Liu +5
Modern deep models are trained on large real-world datasets, where data quality varies and redundancy is common. Data-centric approaches such as dataset pruning have shown promise…
Neural-Driven Image Editing
Pengfei Zhou, Jie Xia, Xiaopeng Peng +15
Traditional image editing typically relies on manual prompting, making it labor-intensive and inaccessible to individuals with limited motor control or language abilities. Leveragi…
RL-Selector: Reinforcement Learning-Guided Data Selection via Redundancy Assessment
Suorong Yang, Peijia Li, Furao Shen +1
Modern deep architectures often rely on large-scale datasets, but training on these datasets incurs high computational and storage overhead. Real-world datasets often contain subst…
Position: Intelligent Science Laboratory Requires the Integration of Cognitive and Embodied AI
Sha Zhang, Suorong Yang, Tong Xie +18
Scientific discovery has long been constrained by human limitations in expertise, physical capability, and sleep cycles. The recent rise of AI scientists and automated laboratories…
A Smart Multimodal Healthcare Copilot with Powerful LLM Reasoning
Xuejiao Zhao, Siyan Liu, Su-Yin Yang +1
Misdiagnosis causes significant harm to healthcare systems worldwide, leading to increased costs and patient risks. MedRAG is a smart multimodal healthcare copilot equipped with po…
When Dynamic Data Selection Meets Data Augmentation
Suorong Yang, Peng Ye, Furao Shen +1
Dynamic data selection aims to accelerate training with lossless performance. However, reducing training data inherently limits data diversity, potentially hindering generalization…
Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning
Di Zhang, Junxian Li, Jingdi Lei +10
Vision-language models (VLMs) have shown remarkable advancements in multimodal reasoning tasks. However, they still often generate inaccurate or irrelevant responses due to issues…
Dual Prototypes for Adaptive Pre-Trained Model in Class-Incremental Learning
Zhiming Xu, Suorong Yang, Baile Xu +2
Class-incremental learning (CIL) aims to learn new classes while retaining previous knowledge. Although pre-trained model (PTM) based approaches show strong performance, directly f…