Yunji Chen

QiMeng-CRUX: Narrowing the Gap Between Natural Language and Verilog via Core Refined Understanding eXpression AAAI 2026 QiMeng-Kernel: Macro-Thinking Micro-Coding Paradigm for LLM-Based High-Performance GPU Kernel Generation AAAI 2026 QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization ACL 2026 Run, Ruminate, and Regulate: A Dual-process Thinking System for Vision-and-Language Navigation AAAI 2026 Automated Superscalar Processor Design by Learning Data Dependencies IJCAI 2025 InverseCoder: Self-improving Instruction-Tuned Code LLMs with Inverse-Instruct AAAI 2025 QiMeng-Attention: SOTA Attention Operator is generated by SOTA Attention Algorithm ACL 2025 QiMeng-GEMM: Automatically Generating High-Performance Matrix Multiplication Code by Exploiting Large Language Models AAAI 2025 QiMeng-TensorOp: One-Line Prompt is Enough for High-Performance Tensor Operator Generation with Hardware Primitives IJCAI 2025 QiMeng-Xpiler: Transcompiling Tensor Programs for Deep Learning Systems with a Neural-Symbolic Approach OSDI 2025 Automated CPU Design by Learning from Input-Output Examples IJCAI 2024 AutoOS: Make Your OS More Powerful by Exploiting Large Language Models ICML 2024 DA-Ada: Learning Domain-Aware Adapter for Domain Adaptive Object Detection NeurIPS 2024 Emergent Communication for Numerical Concepts Generalization AAAI 2024 Hypothesis, Verification, and Induction: Grounding Large Language Models with Self-Driven Skill Learning AAAI 2024 Introducing Compiler Semantics into Large Language Models as Programming Language Translators: A Case Study of C to x86 Assembly EMNLP 2024 OCEAN-MBRL: Offline Conservative Exploration for Model-Based Offline Reinforcement Learning AAAI 2024 Prompt-based Visual Alignment for Zero-shot Policy Transfer ICML 2024 ANPL: Towards Natural Programming with Interactive Decomposition NeurIPS 2023 BALTO: fast tensor program optimization with diversity-based active learning ICLR 2023 Conceptual Reinforcement Learning for Language-Conditioned Tasks AAAI 2023 Context Shift Reduction for Offline Meta-Reinforcement Learning NeurIPS 2023 Contrastive Modules with Temporal Attention for Multi-Task Reinforcement Learning NeurIPS 2023 Decompose a Task into Generalizable Subtasks in Multi-Agent Reinforcement Learning NeurIPS 2023 Efficient Symbolic Policy Learning with Differentiable Symbolic Expression NeurIPS 2023 Emergent Communication for Rules Reasoning NeurIPS 2023 Learning Domain-Aware Detection Head with Prompt Tuning NeurIPS 2023 Non-autoregressive Machine Translation with Probabilistic Context-free Grammar NeurIPS 2023 Online Prototype Alignment for Few-shot Policy Transfer ICML 2023 Online Symbolic Regression with Informative Query AAAI 2023 Accelerating Sparse Convolution with Column Vector-Wise Sparsity NeurIPS 2022 BabelTower: Learning to Auto-parallelized Program Translation ICML 2022 Causality-driven Hierarchical Structure Discovery for Reinforcement Learning NeurIPS 2022 Neural Program Synthesis with Query ICLR 2022 Object-Category Aware Reinforcement Learning NeurIPS 2022 Distilling Object Detectors with Feature Richness NeurIPS 2021 Hindsight Value Function for Variance Reduction in Stochastic Dynamic Environment IJCAI 2021 ScaleCert: Scalable Certified Defense against Adversarial Patches with Sparse Superficial Layers NeurIPS 2021 DWM: A Decomposable Winograd Method for Convolution Acceleration AAAI 2020 Fixed-Point Back-Propagation Training CVPR 2020 TDSNN: From Deep Neural Networks to Deep Spike Neural Networks with Temporal-Coding AAAI 2019