Zirui Liu

From Hypothesis to Premises: LLM-based Backward Logical Reasoning with Selective Symbolic Translation AAAI 2026 How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior ACL 2026 Re3: Relevance & Recency Retrieval for Mitigating Temporal Hallucination ACL 2026 VisualAD: Language-Free Zero-Shot Anomaly Detection via Vision Transformer CVPR 2026 Accelerating LLM Reasoning via Early Rejection with Partial Reward Modeling EMNLP 2025 am-ELO: A Stable Framework for Arena-based LLM Evaluation ICML 2025 AssistedDS: Benchmarking How External Domain Knowledge Assists LLMs in Automated Data Science EMNLP 2025 Flexible Group Count Enables Hassle-Free Structured Pruning CVPR 2025 From Commands to Prompts: LLM-based Semantic File System for AIOS ICLR 2025 Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource Languages AAAI 2025 LoRATK: LoRA Once, Backdoor Everywhere in the Share-and-Play Ecosystem EMNLP 2025 Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding ICML 2025 Word Salad Chopper: Reasoning Models Waste A Ton Of Decoding Budget On Useless Repetitions, Self-Knowingly EMNLP 2025 Zeroth-Order Fine-Tuning of LLMs with Transferable Static Sparsity ICLR 2025 ARM: An Alignment-and-Replacement Module for Chinese Spelling Check Based on LLMs EMNLP 2024 Chasing Fairness in Graphs: A GNN Architecture Perspective AAAI 2024 Computerized Adaptive Testing via Collaborative Ranking NeurIPS 2024 GNNs Also Deserve Editing, and They Need It More Than Once ICML 2024 Gradient Rewiring for Editable Graph Neural Network Training NeurIPS 2024 In Defense of Structural Sparse Adapters for Concurrent LLM Serving EMNLP 2024 KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache ICML 2024 Knowledge Graphs Can be Learned with Just Intersection Features ICML 2024 KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches EMNLP 2024 Learning to Compress Prompt in Natural Language Formats NAACL 2024 LLM Maybe LongLM: SelfExtend LLM Context Window Without Tuning ICML 2024 QUEST: Efficient Extreme Multi-Label Text Classification with Large Language Models on Commodity Hardware EMNLP 2024 Soft Prompt Recovers Compressed LLMs, Transferably ICML 2024 Taylor Unswift: Secured Weight Release for Large Language Models via Taylor Expansion EMNLP 2024 TVE: Learning Meta-attribution for Transferable Vision Explainer ICML 2024 DIVISION: Memory Efficient Training via Dual Activation Precision ICML 2023 One Less Reason for Filter Pruning: Gaining Free Adversarial Robustness with Structured Grouped Kernel Pruning NeurIPS 2023 RSC: Accelerate Graph Neural Networks Training via Randomized Sparse Computations ICML 2023 Setting the Trap: Capturing and Defeating Backdoors in Pretrained Language Models through Honeypots NeurIPS 2023 Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model NeurIPS 2023 A Comprehensive Study on Large-Scale Graph Training: Benchmarking and Rethinking NeurIPS 2022 An Information Fusion Approach to Learning with Instance-Dependent Label Noise ICLR 2022 DreamShard: Generalizable Embedding Table Placement for Recommender Systems NeurIPS 2022 EXACT: Scalable Graph Neural Networks Training via Extreme Activation Compression ICLR 2022 Table2Graph: Transforming Tabular Data to Unified Weighted Graph IJCAI 2022 DivAug: Plug-In Automated Data Augmentation With Explicit Diversity Maximization ICCV 2021 LightGuardian: A Full-Visibility, Lightweight, In-band Telemetry System Using Sketchlets NSDI 2021 Segmental Alignment of English Syllables with Singleton and Cluster Onsets Interspeech 2021 Coarticulation as Synchronised Sequential Target Approximation: An EMA Study Interspeech 2020 Detecting Interactions from Neural Networks via Topological Analysis NeurIPS 2020