Profiles2021-2026
Xia Hu
Rice University
25Papers
18Last author
64Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers25
- AutoL2S: Auto Long-Short Reasoning for Efficient Large Language ModelsAuthor 12 of 12ACL Findings 2026
- Understanding and Mitigating Numerical Sources of Nondeterminism in LLM InferenceAuthor 9 of 10NeurIPS 2025 · 74 citations
- AD-LLM: Benchmarking Large Language Models for Anomaly DetectionAuthor 11 of 12ACL Findings 2025 · 11 citations
- 70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float (DFloat11)Author 6 of 7NeurIPS 2025 · 1 citation
- ReasonerRank: Redefining Language Model Evaluation with Ground-Truth-Free Ranking FrameworksAuthor 8 of 8ACL Findings 2025 · 1 citation
- FFB: A Fair Fairness Benchmark for In-Processing Group Fairness MethodsAuthor 7 of 7ICLR 2024 · 48 citations
- Unraveling the 'Anomaly' in Time Series Anomaly Detection: A Self-supervised Tri-domain SolutionAuthor 5 of 6ICDE 2024 · 18 citations
- Soft Prompt Recovers Compressed LLMs, TransferablyAuthor 8 of 9ICML 2024 · 9 citations
- TVE: Learning Meta-attribution for Transferable Vision ExplainerAuthor 11 of 11ICML 2024 · 1 citation
- Taylor Unswift: Secured Weight Release for Large Language Models via Taylor ExpansionAuthor 11 of 11EMNLP 2024
- Setting the Trap: Capturing and Defeating Backdoors in Pretrained Language Models through HoneypotsAuthor 6 of 6NeurIPS 2023 · 31 citations
- RSC: Accelerate Graph Neural Networks Training via Randomized Sparse ComputationsAuthor 6 of 6ICML 2023 · 24 citations
- One Less Reason for Filter Pruning: Gaining Free Adversarial Robustness with Structured Grouped Kernel PruningAuthor 10 of 10NeurIPS 2023 · 13 citations
- MLPInit: Embarrassingly Simple GNN Training Acceleration with MLP InitializationAuthor 4 of 5ICLR 2023 · 12 citations
- DIVISION: Memory Efficient Training via Dual Activation PrecisionAuthor 6 of 6ICML 2023 · 4 citations
- CoRTX: Contrastive Framework for Real-time ExplanationAuthor 7 of 7ICLR 2023 · 3 citations
- Assessing Privacy Risks in Language Models: A Case Study on Summarization TasksAuthor 6 of 6EMNLP Findings 2023 · 2 citations
- Orthogonal Graph Neural NetworksAuthor 3 of 6AAAI 2022 · 41 citations
- DreamShard: Generalizable Embedding Table Placement for Recommender SystemsAuthor 9 of 9NeurIPS 2022 · 37 citations
- DEGREE: Decomposition Based Explanation for Graph Neural NetworksAuthor 6 of 6ICLR 2022 · 33 citations
- Accelerating Shapley Explanation via Contributive Cooperator SelectionAuthor 8 of 8ICML 2022 · 25 citations
- Geometric Graph Representation Learning via Maximizing Rate ReductionAuthor 4 of 4WWW 2022 · 24 citations
- Towards Debiasing DNN Models from Spurious Feature InfluenceAuthor 4 of 4AAAI 2022 · 9 citations
- Fairness via Representation NeutralizationAuthor 6 of 6NeurIPS 2021 · 91 citations
- DivAug: Plug-in Automated Data Augmentation with Explicit Diversity MaximizationAuthor 5 of 5ICCV 2021 · 26 citations
