Lujun Li

Are Small Language Models the Silver Bullet to Low-Resource Languages Machine Translation? EACL 2026 Bit-by-Bit: Progressive QAT Strategy with Outlier Channel Splitting for Stable Low-Bit LLMs ACL 2026 BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary Codebook ACL 2026 Outlier Matters: Efficient Long-to-Short Reasoning via Outlier-Guided Model Merging AAAI 2026 Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert Merging AAAI 2026 AIRA: Activation-Informed Low-Rank Adaptation for Large Models ICCV 2025 BayesKD: Bayesian Knowledge Distillation for Compact LLMs in Constrained Fine-tuning Scenarios ACL 2025 Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression ICML 2025 Delta Decompression for MoE-based LLMs Compression ICML 2025 Efficient Fine-Tuning of Large Models via Nested Low-Rank Adaptation ICCV 2025 How LLMs React to Industrial Spatio-Temporal Data? Assessing Hallucination with a Novel Traffic Incident Benchmark Dataset NAACL 2025 MoE-SVD: Structured Mixture-of-Experts LLMs Compression via Singular Value Decomposition ICML 2025 ParZC: Parametric Zero-Cost Proxies for Efficient NAS AAAI 2025 Small Language Models in the Real World: Insights from Industrial Text Classification ACL 2025 STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs ICLR 2025 Adaptive Layer Sparsity for Large Language Models via Activation Correlation Assessment NeurIPS 2024 AttnZero: Efficient Attention Discovery for Vision Transformers ECCV 2024 Auto-DAS: Automated Proxy Discovery for Training-free Distillation-aware Architecture Search ECCV 2024 Auto-GAS: Automated Proxy Discovery for Training-free Generative Architecture Search ECCV 2024 Auto-Prox: Training-Free Vision Transformer Architecture Search via Automatic Proxy Discovery AAAI 2024 DetKDS: Knowledge Distillation Search for Object Detectors ICML 2024 Discovering Sparsity Allocation for Layer-wise Pruning of Large Language Models NeurIPS 2024 LPZero: Language Model Zero-cost Proxy Search from Zero EMNLP 2024 Pruner-Zero: Evolving Symbolic Pruning Metric From Scratch for Large Language Models ICML 2024 SasWOT: Real-Time Semantic Segmentation Architecture Search WithOut Training AAAI 2024 UniADS: Universal Architecture-Distiller Search for Distillation Gap AAAI 2024 Automated Knowledge Distillation via Monte Carlo Tree Search ICCV 2023 DisWOT: Student Architecture Search for Distillation WithOut Training CVPR 2023 EMQ: Evolving Training-free Proxies for Automated Mixed Precision Quantization ICCV 2023 KD-Zero: Evolving Knowledge Distiller for Any Teacher-Student Pairs NeurIPS 2023 Activation Modulation and Recalibration Scheme for Weakly Supervised Semantic Segmentation AAAI 2022 Self-Regulated Feature Learning via Teacher-Free Feature Distillation ECCV 2022 Shadow Knowledge Distillation: Bridging Offline and Online Knowledge Transfer NeurIPS 2022