PaperHub

Jiajun Wu

~Jiajun_Wu1

25
论文总数
12.5
年均投稿
5.8
平均评分
接收情况16/25
会议分布
ICLR
16
NeurIPS
7
ICML
2

发表论文 (25 篇)

202516 篇

6.8
4

From Programs to Poses: Factored Real-World Scene Generation via Learned Program Libraries

NeurIPS 2025Poster
6.0
3

Predicate Hierarchies Improve Few-Shot State Classification

ICLR 2025Poster
6.8
4

Model-Based Policy Adaptation for Closed-Loop End-to-end Autonomous Driving

NeurIPS 2025Poster
5.3
4

Understanding Complexity in VideoQA via Visual Program Generation

ICLR 2025Rejected
6.1
4

Understanding Complexity in VideoQA via Visual Program Generation

ICML 2025Poster
6.8
5

What Makes a Maze Look Like a Maze?

ICLR 2025Poster
5.0
5

Learning Counterfactual Interventions for Self-Supervised Motion Estimation

ICLR 2025withdrawn
6.0
3

Range, not Independence, Drives Modularity in Biologically Inspired Representations

ICLR 2025Poster
4.8
4

The Scene Language: Representing Scenes with Programs, Words, and Embeddings

ICLR 2025withdrawn
4.5
4

Visually Descriptive Language Model for Vector Graphics Reasoning

ICLR 2025withdrawn
7.3
4

Seeing the Wind from a Falling Leaf

NeurIPS 2025Poster
7.8
4

Self-Supervised Learning of Motion Concepts by Optimizing Counterfactuals

NeurIPS 2025Spotlight
4.0
4

AdaptVis: Spatial Understanding in Vision-Language Models Requires Adaptive Attention

ICLR 2025withdrawn
6.1
4

Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas

ICML 2025Poster
6.4
4

Taming generative video models for zero-shot optical flow extraction

NeurIPS 2025Poster
7.3
4

VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents

NeurIPS 2025Poster
合作者 (20)