alphaFeedback
XS

Xiangchen Song

cs.LGcs.AIcs.CLcs.IRstat.MLcs.CVstat.MEBrain Networkcs.CYcs.DL

On Valency

published · living versions
W_af3g4cpf·v1 · currentpublished
PEAR: Adaptive Advantage Reshaping for Perception and Exploration in Large Vision-Language Models
with Junxin Wang, Yingfeng Luo, Weiqiao Shan, Runsong Zhao +10
1 version

Preprints & journals

26 papers in the corpus · 2020–2025
Score-based Greedy Search for Structure Identification of Partially Observed Linear Causal Models2510.04378v2 · Xinshuai Dong, Ignavier Ng, Haoyue Dai et al.2025 · 0 citationsarXiv
Advancing Reasoning in Diffusion Language Models with Denoising Process Rewards2510.01544v2 · Shaoan Xie, Lingjing Kong, Xiangchen Song et al.2025 · 0 citationsarXiv
LLM Interpretability with Identifiable Temporal-Instantaneous Representation2509.23323v2 · Xiangchen Song, Jiaqi Sun, Zijian Li et al.2025 · 0 citationsarXiv
Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs2505.20254v1 · Xiangchen Song, Aashiq Muhamed, Yujia Zheng et al.2025 · 0 citationsarXiv
Reflection-Window Decoding: Text Generation with Selective Refinement2502.03678v3 · Zeyu Tang, Zhenhao Chen, Xiangchen Song et al.2025 · 0 citationsarXiv
A randomized controlled trial on anonymizing reviewers to each other in peer review discussions.39729478 · Rastogi, Charvi, Song, Xiangchen, Jin, Zhijing et al.2024 · 2 citationsPloS one. 2024;19(12):e0315674
Causal Temporal Representation Learning with Nonstationary Sparse Transition2409.03142v1 · Xiangchen Song, Zijian Li, Guangyi Chen et al.2024 · 0 citationsarXiv
On the Identification of Temporally Causal Representation with Instantaneous Dependence2405.15325v4 · Zijian Li, Yifan Shen, Kaitao Zheng et al.2024 · 0 citationsarXiv
Nonstationary Time Series Forecasting via Unknown Distribution Adaptation2402.12767v4 · Zijian Li, Ruichu Cai, Zhenhui Yang et al.2024 · 1 citationarXiv
CaRiNG: Learning Temporal Causal Representation under Non-Invertible Generation Process2401.14535v2 · Guangyi Chen, Yifan Shen, Zhenhao Chen et al.2024 · 0 citationsarXiv
A Versatile Causal Discovery Framework to Allow Causally-Related Hidden Variables2312.11001v1 · Xinshuai Dong, Biwei Huang, Ignavier Ng et al.2023 · 1 citationarXiv
DEEP DAG LEARNING OF EFFECTIVE BRAIN CONNECTIVITY FOR FMRI ANALYSIS.38868456 · Yu, Yue, Kan, Xuan, Cui, Hejie et al.2024 · 6 citationsProceedings. IEEE International Symposium on Biomedical Imaging. 2023;2023
Estimating Treatment Effects from Irregular Time Series Observations with Hidden Confounders2303.02320v1 · Defu Cao, James Enouen, Yujing Wang et al.2023 · 12 citationsarXiv
PLOT: Prompt Learning with Optimal Transport for Vision-Language Models2210.01253v2 · Guangyi Chen, Weiran Yao, Xiangchen Song et al.2022 · 42 citationsarXiv
TaxoEnrich: Self-Supervised Taxonomy Completion via Structure-Semantic Representations2202.04887v1 · Minhao Jiang, Xiangchen Song, Jieyu Zhang et al.2022 · 31 citationsarXiv
Learning Multi-granularity User Intent Unit for Session-based Recommendation2112.13197v3 · Jiayan Guo, Yaming Yang, Xiangchen Song et al.2021 · 88 citationsarXiv
Creating Training Sets via Weak Indirect Supervision2110.03484v3 · Jieyu Zhang, Bohan Wang, Xiangchen Song et al.2021 · 3 citationsarXiv
Who Should Go First? A Self-Supervised Concept Sorting Model for Improving Taxonomy Expansion2104.03682v2 · Xiangchen Song, Jiaming Shen, Jieyu Zhang et al.2021 · 5 citationsarXiv
Taxonomy Completion via Triplet Matching Network2101.01896v3 · Jieyu Zhang, Xiangchen Song, Ying Zeng et al.2021 · 35 citationsarXiv
COVID-19 Literature Knowledge Graph Construction and Drug Repurposing Report Generation2007.00576v6 · Qingyun Wang, Manling Li, Xuan Wang et al.2020 · 121 citationsarXiv
Comprehensive Named Entity Recognition on CORD-19 with Distant or Weak Supervision2003.12218v5 · Xuan Wang, Xiangchen Song, Bangzheng Li et al.2020 · 37 citationsarXiv
Career total: 32 works. 26 are in this corpus.

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.