0

Shiji Song

Papers
22

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile
Semantic Scholar
Attribution policy →
22papers

Authored papers

22

Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

arXiv 2025

2025

EchoWorld: Learning Motion-Aware World Models for Echocardiography Probe Guidance

CVPR 2025 1

2025

MOVE: A Simple Motion-Based Data Collection Paradigm for Spatial Generalization in Robotic Manipulation

arXiv 2025

2025

CheXWorld: Exploring Image World Modeling for Radiograph Representation Learning

CVPR 2025 1

2025

Bridging the Divide: Reconsidering Softmax and Linear Attention

arXiv 2024

2024

Efficient Diffusion Transformer with Step-wise Dynamic Attention Mediators

arXiv 2024

2024

Everything to the Synthetic: Diffusion-driven Test-time Adaptation via Synthetic-Domain Alignment

CVPR 2025 1

2024

Model Surgery: Modulating LLM's Behavior Via Simple Parameter Editing

arXiv 2024

2024

DyFADet: Dynamic Feature Aggregation for Temporal Action Detection

arXiv 2024

2024

ConvLLaVA: Hierarchical Backbones as Visual Encoder for Large Multimodal Models

arXiv 2024

2024

DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution

arXiv 2024

2024

DAT++: Spatially Dynamic Vision Transformer with Deformable Attention

arXiv 2023

2023

Agent Attention: On the Integration of Softmax and Linear Attention

arXiv 2023

2023

FLatten Transformer: Vision Transformer using Focused Linear Attention

ICCV 2023 1

2023

Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models

CVPR 2024 1

2023

Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement Learning

train-once-get-a-family-state-adaptive

2023

Adaptive Rotated Convolution for Rotated Object Detection

ICCV 2023 1

2023

Segment3D: Learning Fine-Grained Class-Agnostic 3D Segmentation without Manual Labels

arXiv 2023

2023

Dynamic Perceiver for Efficient Visual Recognition

ICCV 2023 1

2023

Pseudo-Q: Generating Pseudo Language Queries for Visual Grounding

CVPR 2022 1

2022

Domain Adaptation via Prompt Learning

arXiv 2022

2022

EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbones

ICCV 2023 1

2022

Affiliations

No known affiliations.

Frequent co-authors

10

from 22 papers