Shiji Song

CheXWorld: Exploring Image World Modeling for Radiograph Representation Learning CVPR 2025 EchoWorld: Learning Motion-Aware World Models for Echocardiography Probe Guidance CVPR 2025 Everything to the Synthetic: Diffusion-driven Test-time Adaptation via Synthetic-Domain Alignment CVPR 2025 GridMix: Exploring Spatial Modulation for Neural Fields in PDE Modeling ICLR 2025 Model Surgery: Modulating LLM’s Behavior Via Simple Parameter Editing NAACL 2025 Agent Attention: On the Integration of Softmax and Linear Attention ECCV 2024 A Reinforcement-Learning-Based Multiple-Column Selection Strategy for Column Generation AAAI 2024 Boosting LLM Agents with Recursive Contemplation for Effective Deception Handling ACL 2024 Bridging the Divide: Reconsidering Softmax and Linear Attention NeurIPS 2024 Cardiac Copilot: Automatic Probe Guidance for Echocardiography with World Model MICCAI 2024 DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution NeurIPS 2024 Demystify Mamba in Vision: A Linear Attention Perspective NeurIPS 2024 DyFADet: Dynamic Feature Aggregation for Temporal Action Detection ECCV 2024 Efficient Diffusion Transformer with Step-wise Dynamic Attention Mediators ECCV 2024 GSVA: Generalized Segmentation via Multimodal Large Language Models CVPR 2024 PsychoGAT: A Novel Psychological Measurement Paradigm through Interactive Fiction Games with LLM Agents ACL 2024 Revisiting Non-Autoregressive Transformers for Efficient Image Synthesis CVPR 2024 Segment3D: Learning Fine-Grained Class-Agnostic 3D Segmentation without Manual Labels ECCV 2024 Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models CVPR 2024 Adaptive Rotated Convolution for Rotated Object Detection ICCV 2023 Boosting Offline Reinforcement Learning with Action Preference Query ICML 2023 Budgeted Training for Vision Transformer ICLR 2023 Causal Intervention for Human Trajectory Prediction with Cross Attention Mechanism AAAI 2023 Dynamic Perceiver for Efficient Visual Recognition ICCV 2023 EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbones ICCV 2023 FLatten Transformer: Vision Transformer using Focused Linear Attention ICCV 2023 Slide-Transformer: Hierarchical Vision Transformer With Local Self-Attention CVPR 2023 Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement Learning NeurIPS 2023 Understanding, Predicting and Better Resolving Q-Value Divergence in Offline-RL NeurIPS 2023 Zero-Shot Generative Model Adaptation via Image-Specific Prompt Learning CVPR 2023 ActiveNeRF: Learning Where to See with Uncertainty Estimation ECCV 2022 AdaFocusV3: On Unified Spatial-Temporal Dynamic Video Recognition ECCV 2022 Contrastive Language-Image Pre-Training with Knowledge Graphs NeurIPS 2022 Efficient Knowledge Distillation from Model Checkpoints NeurIPS 2022 Exploring the Equivalence of Siamese Self-Supervised Learning via a Unified Gradient Framework CVPR 2022 Latency-aware Spatial-wise Dynamic Networks NeurIPS 2022 Learning to Weight Samples for Dynamic Early-Exiting Networks ECCV 2022 On the Integration of Self-Attention and Convolution CVPR 2022 Pseudo-Q: Generating Pseudo Language Queries for Visual Grounding CVPR 2022 Vision Transformer With Deformable Attention CVPR 2022 3D Object Detection With Pointformer CVPR 2021 Adaptive Focus for Efficient Video Recognition ICCV 2021 CondenseNet V2: Sparse Feature Reactivation for Deep Networks CVPR 2021 Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition NeurIPS 2021 Revisiting Locally Supervised Learning: an Alternative to End-to-end Training ICLR 2021 Towards Learning Spatially Discriminative Feature Representations ICCV 2021 Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification NeurIPS 2020 Resolution Adaptive Networks for Efficient Inference CVPR 2020 Implicit Semantic Data Augmentation for Deep Networks NeurIPS 2019 Regularized Anderson Acceleration for Off-Policy Deep Reinforcement Learning NeurIPS 2019 Soft Policy Gradient Method for Maximum Entropy Deep Reinforcement Learning IJCAI 2019