Shiji Song

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