Aojun Zhou

From Solver to Tutor: Evaluating the Pedagogical Intelligence of LLMs with KMP-Bench AAAI 2026 MathCanvas: Intrinsic Visual Chain-of-Thought for Multimodal Mathematical Reasoning ACL 2026 Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understanding CVPR 2025 Alignment with Fill-In-the-Middle for Enhancing Code Generation EMNLP 2025 BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices CVPR 2025 Chimera: Improving Generalist Model with Domain-Specific Experts ICCV 2025 GenieBlue: Integrating both Linguistic and Multimodal Capabilities for Large Language Models on Mobile Devices ICCV 2025 LM-Searcher: Cross-domain Neural Architecture Search with LLMs via Unified Numerical Encoding EMNLP 2025 MathCoder2: Better Math Reasoning from Continued Pretraining on Model-translated Mathematical Code ICLR 2025 MathCoder-VL: Bridging Vision and Code for Enhanced Multimodal Mathematical Reasoning ACL 2025 MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine ICLR 2025 Probability-Consistent Preference Optimization for Enhanced LLM Reasoning ACL 2025 ReflectionCoder: Learning from Reflection Sequence for Enhanced One-off Code Generation ACL 2025 ThinK: Thinner Key Cache by Query-Driven Pruning ICLR 2025 Graph Lottery Ticket Automated ICLR 2024 LLaMA-Adapter: Efficient Fine-tuning of Large Language Models with Zero-initialized Attention ICLR 2024 MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning ICLR 2024 MathGenie: Generating Synthetic Data with Question Back-translation for Enhancing Mathematical Reasoning of LLMs ACL 2024 MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems? ECCV 2024 Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset NeurIPS 2024 Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models ACL 2024 Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification ICLR 2024 SPP: Sparsity-Preserved Parameter-Efficient Fine-Tuning for Large Language Models ICML 2024 JourneyDB: A Benchmark for Generative Image Understanding NeurIPS 2023 Not All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior Refinement ICCV 2023 SparseMAE: Sparse Training Meets Masked Autoencoders ICCV 2023 Group R-CNN for Weakly Semi-Supervised Object Detection With Points CVPR 2022 Omni-Dimensional Dynamic Convolution ICLR 2022 Differentiable Dynamic Wirings for Neural Networks ICCV 2021 DominoSearch: Find layer-wise fine-grained N:M sparse schemes from dense neural networks NeurIPS 2021 Group Fisher Pruning for Practical Network Compression ICML 2021 Incorporating Convolution Designs Into Visual Transformers ICCV 2021 Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch ICLR 2021 Adversarial Robustness vs. Model Compression, or Both? ICCV 2019 Deeply-Supervised Knowledge Synergy CVPR 2019 HBONet: Harmonious Bottleneck on Two Orthogonal Dimensions ICCV 2019 Explicit Loss-Error-Aware Quantization for Low-Bit Deep Neural Networks CVPR 2018