SH
Songfang Huang
cs.CLcs.AIcs.CVcs.LGcs.ROactive learningalgorithm developmentbig dataCausal inferenceCognitive Behavioral Therapy
On Valency
published · living versionsW_mp5jgnwa·v1 · currentpublished
Event2Reward: Learning Robotic Rewards from Progress Relations
with Junnan Nie, Zitian Fan, Jiachen Zhang, Junyi Lao +12
1 version
Preprints & journals
64 papers in the corpus · 2015–2026MemOPD: On-Policy Distillation through Memory State Alignment for Long-Horizon Agents2608.07068v1 · Zhiyuan Liu, Tinghong Ye, Chenghao Liu et al.2026 · 0 citationsarXiv
MORPH: Generative Retrieval via Diffusion Transformer with Metric-Ordered Sequence Training and Hybrid-Policy Preference Optimization2606.26899v2 · Chenghao Liu, Yu Zhang, Zhongtao Jiang et al.2026 · 0 citationsarXiv
PACE: Phase-Aware Chunk Execution for Robot Policies with Action Chunking2606.00537v3 · Junnan Nie, Jiayi Li, Chenghao Liu et al.2026 · 0 citationsarXiv
What Frozen VLAs Already Know About Success: A Probing Study of Value-Like Structure in Foundation Robot Policies2605.28527v1 · Jiachen Zhang, Junnan Nie, Junyi Lao et al.2026 · 0 citationsarXiv
VFEAgent: A Multimodal Agent Framework for End-to-End Automated Finite Element Analysis2605.28978v2 · Jiachen Zhang, Junyi Lao, Chenghao Liu et al.2026 · 0 citationsarXiv
MSNav: Zero-Shot Vision-and-Language Navigation with Dynamic Memory and LLM Spatial Reasoning2508.16654v3 · Chenghao Liu, Zhimu Zhou, Jiachen Zhang et al.2025 · 1 citationarXiv
TTF-VLA: Temporal Token Fusion via Pixel-Attention Integration for Vision-Language-Action Models2508.19257v3 · Chenghao Liu, Jiachen Zhang, Chengxuan Li et al.2025 · 1 citationarXiv
Unlocking the Potential of Model Merging for Low-Resource Languages2407.03994v3 · Mingxu Tao, Chen Zhang, Quzhe Huang et al.2024 · 3 citationsarXiv
Synergetic Event Understanding: A Collaborative Approach to Cross-Document Event Coreference Resolution with Large Language Models2406.02148v1 · Qingkai Min, Qipeng Guo, Xiangkun Hu et al.2024 · 12 citationsarXiv
Harder Tasks Need More Experts: Dynamic Routing in MoE Models2403.07652v1 · Quzhe Huang, Zhenwei An, Nan Zhuang et al.2024 · 3 citationsarXiv
Assisting schizophrenia diagnosis using clinical electroencephalography and interpretable graph neural networks: a real-world and cross-site study.37491671 · Jiang, Haiteng, Chen, Peiyin, Sun, Zhaohong et al.2023 · 18 citationsNeuropsychopharmacology : official publication of the American College of Neuropsychopharmacology. 2023;48(13):1920-1930
BUS:Efficient and Effective Vision-language Pre-training with Bottom-Up Patch Summarization2307.08504v2 · Chaoya Jiang, Haiyang Xu, Wei Ye et al.2023 · 8 citationsarXiv
DiffDTM: A conditional structure-free framework for bioactive molecules generation targeted for dual proteins2306.13957v1 · Lei Huang, Zheng Yuan, Huihui Yan et al.2023 · 0 citationsarXiv
Towards Adaptive Prefix Tuning for Parameter-Efficient Language Model Fine-tuning2305.15212v1 · Zhen-Ru Zhang, Chuanqi Tan, Haiyang Xu et al.2023 · 97 citationsarXiv
TRIPS: Efficient Vision-and-Language Pre-training with Text-Relevant Image Patch Selection2305.04474v4 · Chaoya Jiang, Haiyang Xu, Chenliang Li et al.2023 · 9 citationsarXiv
Transforming Visual Scene Graphs to Image Captions2305.02177v4 · Xu Yang, Jiawei Peng, Zihua Wang et al.2023 · 32 citationsarXiv
VECO 2.0: Cross-lingual Language Model Pre-training with Multi-granularity Contrastive Learning2304.08205v1 · Zhen-Ru Zhang, Chuanqi Tan, Songfang Huang et al.2023 · 3 citationsarXiv
RRHF: Rank Responses to Align Language Models with Human Feedback without tears2304.05302v3 · Zheng Yuan, Hongyi Yuan, Chuanqi Tan et al.2023 · 41 citationsarXiv
Optimizing multi-domain hematologic biomarkers and clinical features for the differential diagnosis of unipolar depression and bipolar depression.38609642 · Zeng, Jinkun, Zhang, Yaoyun, Xiang, Yutao et al.2024 · 12 citationsNpj mental health research. 2023;2(1):4
Comparative Effectiveness of Digital Cognitive Behavioral Therapy vs Medication Therapy Among Patients With Insomnia.37040111 · Lu, Menglin, Zhang, Yaoyun, Zhang, Junhang et al.2023 · 38 citationsJAMA network open. 2023;6(4):e237597
Revisiting Automatic Question Summarization Evaluation in the Biomedical Domain2303.10328v1 · Hongyi Yuan, Yaoyun Zhang, Fei Huang et al.2023 · 0 citationsarXiv
How well do Large Language Models perform in Arithmetic tasks?2304.02015v1 · Zheng Yuan, Hongyi Yuan, Chuanqi Tan et al.2023 · 29 citationsarXiv
RAMM: Retrieval-augmented Biomedical Visual Question Answering with Multi-modal Pre-training2303.00534v1 · Zheng Yuan, Qiao Jin, Chuanqi Tan et al.2023 · 42 citationsarXiv
Molecular Geometry-aware Transformer for accurate 3D Atomic System modeling2302.00855v1 · Zheng Yuan, Yaoyun Zhang, Chuanqi Tan et al.2023 · 3 citationsarXiv
mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video2302.00402v1 · Haiyang Xu, Qinghao Ye, Ming Yan et al.2023 · 49 citationsICML2023
Learning Trajectory-Word Alignments for Video-Language Tasks2301.01953v3 · Xu Yang, Zhangzikang Li, Haiyang Xu et al.2023 · 5 citationsarXiv
SeqDiffuSeq: Text Diffusion with Encoder-Decoder Transformers2212.10325v5 · Hongyi Yuan, Zheng Yuan, Chuanqi Tan et al.2022 · 21 citationsarXiv
HyPe: Better Pre-trained Language Model Fine-tuning with Hidden Representation Perturbation2212.08853v2 · Hongyi Yuan, Zheng Yuan, Chuanqi Tan et al.2022 · 6 citationsarXiv
State-of-the-Art Evidence Retriever for Precision Medicine: Algorithm Development and Validation.36409468 · Jin, Qiao, Tan, Chuanqi, Chen, Mosha et al.2023 · 6 citationsJMIR medical informatics. 2022;10(12):e40743
SpanProto: A Two-stage Span-based Prototypical Network for Few-shot Named Entity Recognition2210.09049v2 · Jianing Wang, Chengcheng Han, Chengyu Wang et al.2022 · 39 citationsarXiv
Disentangled representation for sequential treatment effect estimation.36242866 · Chu, Jiebin, Zhang, Yaoyun, Huang, Fei et al.2022 · 3 citationsComputer methods and programs in biomedicine. 2022;226:107175
A Survey on Open Information Extraction from Rule-based Model to Large Language Model2208.08690v7 · Pai Liu, Wenyang Gao, Wenjie Dong et al.2022 · 14 citationsarXiv
mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections2205.12005v2 · Chenliang Li, Haiyang Xu, Junfeng Tian et al.2022 · 184 citationsEMNLP2022
Parameter-Efficient Sparsity for Large Language Models Fine-Tuning2205.11005v1 · Yuchao Li, Fuli Luo, Chuanqi Tan et al.2022 · 10 citationsarXiv
Towards Unified Prompt Tuning for Few-shot Text Classification2205.05313v1 · Jianing Wang, Chengyu Wang, Fuli Luo et al.2022 · 37 citationsarXiv
Image Captioning In the Transformer Age2204.07374v1 · Yang Xu, Li Li, Haiyang Xu et al.2022 · 7 citationsarXiv
Probing Structured Pruning on Multilingual Pre-trained Models: Settings, Algorithms, and Efficiency2204.02601v1 · Yanyang Li, Fuli Luo, Runxin Xu et al.2022 · 2 citationsarXiv
Making Pre-trained Language Models End-to-end Few-shot Learners with Contrastive Prompt Tuning2204.00166v1 · Ziyun Xu, Chengyu Wang, Minghui Qiu et al.2022 · 28 citationsarXiv
Code Synonyms Do Matter: Multiple Synonyms Matching Network for Automatic ICD Coding2203.01515v2 · Zheng Yuan, Chuanqi Tan, Songfang Huang2022 · 88 citationsarXiv
From Dense to Sparse: Contrastive Pruning for Better Pre-trained Language Model Compression2112.07198v1 · Runxin Xu, Fuli Luo, Chengyu Wang et al.2021 · 22 citationsarXiv
LOGEN: Few-shot Logical Knowledge-Conditioned Text Generation with Self-training2112.01404v3 · Shumin Deng, Jiacheng Yang, Hongbin Ye et al.2021 · 6 citationsarXiv
Achieving Human Parity on Visual Question Answering2111.08896v3 · Ming Yan, Haiyang Xu, Chenliang Li et al.2021 · 26 citationsarXiv
A Chinese Multi-type Complex Questions Answering Dataset over Wikidata2111.06086v1 · Jianyun Zou, Min Yang, Lichao Zhang et al.2021 · 3 citationsarXiv
Fusing Heterogeneous Factors with Triaffine Mechanism for Nested Named Entity Recognition2110.07480v3 · Zheng Yuan, Chuanqi Tan, Songfang Huang et al.2021 · 68 citationsarXiv
Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning2109.05687v1 · Runxin Xu, Fuli Luo, Zhiyuan Zhang et al.2021 · 141 citationsarXiv
E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learning2106.01804v2 · Haiyang Xu, Ming Yan, Chenliang Li et al.2021 · 86 citationsarXiv
StructuralLM: Structural Pre-training for Form Understanding2105.11210v1 · Chenliang Li, Bin Bi, Ming Yan et al.2021 · 101 citationsarXiv
Improving Biomedical Pretrained Language Models with Knowledge2104.10344v1 · Zheng Yuan, Yijia Liu, Chuanqi Tan et al.2021 · 86 citationsarXiv
Lattice-BERT: Leveraging Multi-Granularity Representations in Chinese Pre-trained Language Models2104.07204v2 · Yuxuan Lai, Yijia Liu, Yansong Feng et al.2021 · 40 citationsarXiv
Automated Conformance Testing for JavaScript Engines via Deep Compiler Fuzzing2104.07460v1 · Guixin Ye, Zhanyong Tang, Shin Hwei Tan et al.2021 · 77 citationsarXiv
Career total: 120 works. 64 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.