Bei Yu

Analytical FFN-to-MoE Restructuring via Activation Pattern Analysis ACL 2026 TRAC: Teacher-Guided Token Reward with Adaptive Calibration for Robust Policy Optimization ACL 2026 KCLNet: Electrically Equivalence-Oriented Graph Representation Learning for Analog Circuits AAAI 2026 Does Your Vision-Language Model Get Lost in the Long Video Sampling Dilemma? ICCV 2025 Mixture-of-Scores: Robust Image-Text Data Valuation via Three Lines of Code ICCV 2025 Learnable Feature Patches and Vectors for Boosting Low-light Image Enhancement without External Knowledge ICCV 2025 Enhancing LLM Knowledge Learning through Generalization EMNLP 2025 FlexPose: Pose Distribution Adaptation with Limited Guidance AAAI 2025 Intelligent OPC Engineer Assistant for Semiconductor Manufacturing AAAI 2025 Efficient OpAmp Adaptation for Zoom Attention to Golden Contexts ACL 2025 Divergent Thoughts toward One Goal: LLM-based Multi-Agent Collaboration System for Electronic Design Automation NAACL 2025 Low-Light Video Enhancement via Spatial-Temporal Consistent Decomposition IJCAI 2025 TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization ICML 2025 DreamOmni: Unified Image Generation and Editing CVPR 2025 Generative Video Propagation CVPR 2025 VisionZip: Longer is Better but Not Necessary in Vision Language Models CVPR 2025 Bridging Layout and RTL: Knowledge Distillation based Timing Prediction ICML 2025 Circuit Representation Learning with Masked Gate Modeling and Verilog-AIG Alignment ICLR 2025 BiE: Bi-Exponent Block Floating-Point for Large Language Models Quantization ICML 2024 Decoupled Kullback-Leibler Divergence Loss NIPS 2024 Improving Neural ODE Training with Temporal Adaptive Batch Normalization NIPS 2024 Towards Automated RISC-V Microarchitecture Design with Reinforcement Learning AAAI 2024 p-Laplacian Adaptation for Generative Pre-trained Vision-Language Models AAAI 2024 Progressively Knowledge Distillation via Re-parameterizing Diffusion Reverse Process AAAI 2024 Classes Are Not Equal: An Empirical Study on Image Recognition Fairness CVPR 2024 Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks EMNLP 2024 BetterV: Controlled Verilog Generation with Discriminative Guidance ICML 2024 LithoBench: Benchmarking AI Computational Lithography for Semiconductor Manufacturing NIPS 2023 ATFormer: A Learned Performance Model with Transfer Learning Across Devices for Deep Learning Tensor Programs EMNLP 2023 AutoGraph: Optimizing DNN Computation Graph for Parallel GPU Kernel Execution AAAI 2023 Do Not Train It: A Linear Neural Architecture Search of Graph Neural Networks ICML 2023 Can ChatGPT Understand Causal Language in Science Claims? ACL 2023 FastGR: Global Routing on CPU-GPU with Heterogeneous Task Graph Scheduler (Extended Abstract) IJCAI 2023 Efficient Deep Space Filling Curve ICCV 2023 PCL: Proxy-Based Contrastive Learning for Domain Generalization CVPR 2022 Context-Based Contrastive Learning for Scene Text Recognition AAAI 2022 “Devils Are in the Details”: Annotating Specificity of Clinical Advice from Medical Literature NAACL 2022 Efficient Point Cloud Analysis Using Hilbert Curve ECCV 2022 Fast and Efficient DNN Deployment via Deep Gaussian Transfer Learning ICCV 2021 Seeing Dynamic Scene in the Dark: A High-Quality Video Dataset With Mechatronic Alignment ICCV 2021 Parametric Contrastive Learning ICCV 2021 Detecting Health Advice in Medical Research Literature EMNLP 2021 Self Promotion in US Congressional Tweets NAACL 2021 Dive Deeper Into Box for Object Detection ECCV 2020 Measuring Correlation-to-Causation Exaggeration in Press Releases COLING 2020 Tensor Low-Rank Reconstruction for Semantic Segmentation ECCV 2020 Detecting Causal Language Use in Science Findings EMNLP 2019 Detecting Causal Language Use in Science Findings IJCNLP 2019 An Evaluation of Information Extraction Tools for Identifying Health Claims in News Headlines COLING 2018 Function Words for Chinese Authorship Attribution NAACL 2012