PaperHub

Yilun Du

~Yilun_Du1

35
论文总数
17.5
年均投稿
6.4
平均评分
接收情况28/35
会议分布
ICLR
22
NeurIPS
9
ICML
3
COLM
1

发表论文 (35 篇)

202519 篇

7.8
4

Generalizable Reasoning through Compositional Energy Minimization

NeurIPS 2025Spotlight
6.4
4

Learning 3D Persistent Embodied World Models

NeurIPS 2025Poster
6.7
3

Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains

ICLR 2025Poster
6.5
4

Looped Transformers for Length Generalization

ICLR 2025Poster
7.3
3

Grounding Video Models to Actions through Goal Conditioned Exploration

ICLR 2025Spotlight
6.5
4

Multi-Agent Verification: Scaling Test-Time Compute with Multiple Verifiers

COLM 2025Poster
7.5
5

Follow the Energy, Find the Path: Riemannian Metrics from Energy-Based Models

NeurIPS 2025Poster
5.5
4

AdaWorld: Learning Adaptable World Models with Latent Actions

ICML 2025Poster
6.4
5

Compositional Scene Understanding through Inverse Generative Modeling

ICML 2025Poster
6.8
5

AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark

ICLR 2025Poster
5.8
4

Solving New Tasks by Adapting Internet Video Knowledge

ICLR 2025Poster
7.8
4

Generative Trajectory Stitching through Diffusion Composition

NeurIPS 2025Spotlight
6.6
4

History-Guided Video Diffusion

ICML 2025Poster
4.3
4

Learning 4D Embodied World Models

ICLR 2025withdrawn
7.8
4

EvoLM: In Search of Lost Language Model Training Dynamics

NeurIPS 2025Oral
6.4
5

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs

NeurIPS 2025Spotlight
4.3
4

SnapMem: Snapshot-based 3D Scene Memory for Embodied Exploration and Reasoning

ICLR 2025withdrawn
6.4
4

MindJourney: Test-Time Scaling with World Models for Spatial Reasoning

NeurIPS 2025Poster
6.7
3

COMBO: Compositional World Models for Embodied Multi-Agent Cooperation

ICLR 2025Poster

202416 篇

7.0
4

Video Language Planning

ICLR 2024Poster
6.0
4

Improving Factuality and Reasoning in Language Models through Multiagent Debate

ICLR 2024Rejected
6.0
4

Learning to Jointly Understand Visual and Tactile Signals

ICLR 2024Poster
6.0
3

Few-Shot Task Learning through Inverse Generative Modeling

NeurIPS 2024Poster
3.8
4

Inverse Decision Making via Inverse Generative Modeling

ICLR 2024withdrawn
7.5
4

Learning Interactive Real-World Simulators

ICLR 2024Oral
6.3
4

Probabilistic Adaptation of Black-Box Text-to-Video Models

ICLR 2024Poster
7.0
4

Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion

NeurIPS 2024Poster
5.3
4

Disentangled Acoustic Fields For Multimodal Physical Scene Understanding

ICLR 2024Rejected
6.3
4

Training Diffusion Models with Reinforcement Learning

ICLR 2024Poster
7.5
4

Learning to Act from Actionless Videos through Dense Correspondences

ICLR 2024Spotlight
4.0
4

Potential Based Diffusion Motion Planning

ICLR 2024Rejected
6.3
3

Compositional Image Decomposition with Diffusion Models

ICLR 2024Rejected
7.0
4

Compositional Generative Inverse Design

ICLR 2024Spotlight
6.5
4

Building Cooperative Embodied Agents Modularly with Large Language Models

ICLR 2024Poster
6.8
4

HAZARD Challenge: Embodied Decision Making in Dynamically Changing Environments

ICLR 2024Poster
合作者 (20)