Xiu Li
~Xiu_Li1
33
论文总数
16.5
年均投稿
平均评分
接收情况17/33
会议分布
ICLR
21
NeurIPS
10
ICML
2
发表论文 (33 篇)
202521 篇
4
Offline-to-Online Reinforcement Learning with Prioritized Experience Selection
ICLR 2025Rejected
4
Decentralized Transformers with Centralized Aggregation are Sample-Efficient Multi-Agent World Models
ICLR 2025Rejected
4
Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration
ICLR 2025withdrawn
4
Revisiting Multi-Agent World Modeling from a Diffusion-Inspired Perspective
NeurIPS 2025Poster
4
LoRA-Gen: Specializing Language Model via Online LoRA Generation
ICLR 2025withdrawn
3
LoRA-Gen: Specializing Large Language Model via Online LoRA Generation
ICML 2025Poster
4
HyDance: A Novel Hybrid Dance Generation Network with temporal and frequency features
ICLR 2025Rejected
4
VLP: Vision-Language Preference Learning for Embodied Manipulation
ICLR 2025Rejected
8
UniQA: Unified Vision-Language Pre-training for Image Quality and Aesthetic Assessment
ICLR 2025withdrawn
4
Gamma: Toward Generic Image Assessment with Mixture of Assessment Experts
ICLR 2025withdrawn
3
InstantSwap: Fast Customized Concept Swapping across Sharp Shape Differences
ICLR 2025Poster
4
Egocentric Vision Language Planning
ICLR 2025withdrawn
4
MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO
NeurIPS 2025Poster
4
SAM-R1: Leveraging SAM for Reward Feedback in Multimodal Segmentation via Reinforcement Learning
NeurIPS 2025Poster
4
Reti-Diff: Illumination Degradation Image Restoration with Retinex-based Latent Diffusion Model
ICLR 2025Spotlight
4
Taming Rectified Flow for Inversion and Editing
ICML 2025Poster
4
ADG: Ambient Diffusion-Guided Dataset Recovery for Corruption-Robust Offline Reinforcement Learning
NeurIPS 2025Poster
5
InterDance: Reactive 3D Dance Generation with Realistic Duet Interactions
ICLR 2025Rejected
3
Cross-Domain Offline Policy Adaptation with Optimal Transport and Dataset Constraint
ICLR 2025Poster
5
Linear Differential Vision Transformer: Learning Visual Contrasts via Pairwise Differentials
NeurIPS 2025Poster
3
InteractiveCOT: Aligning Dynamic Chain-of-Thought Planning for Embodied Decision-Making
ICLR 2025Rejected
202412 篇
4
Realistic Human Motion Generation with Cross-Diffusion Models
ICLR 2024Rejected
4
Efficient Meshy Neural Fields for Animatable Human Avatars
ICLR 2024Rejected
3
Exploration and Anti-Exploration with Distributional Random Network Distillation
ICLR 2024Rejected
4
SEABO: A Simple Search-Based Method for Offline Imitation Learning
ICLR 2024Poster
4
Zero-shot Cross-task Preference Alignment for Offline RL via Optimal Transport
ICLR 2024Rejected
4
Bridging the Divide: Reconsidering Softmax and Linear Attention
NeurIPS 2024Poster
4
COVE: Unleashing the Diffusion Feature Correspondence for Consistent Video Editing
NeurIPS 2024Poster
4
Consistent123: One Image to Highly Consistent 3D Asset Using Case-Aware Diffusion Priors
ICLR 2024withdrawn
4
MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models
NeurIPS 2024Poster
4
MambaTree: Tree Topology is All You Need in State Space Model
NeurIPS 2024Spotlight
4
Strategic Preys Make Acute Predators: Enhancing Camouflaged Object Detectors by Generating Camouflaged Objects
ICLR 2024Poster
4
Real-world Image Dehazing with Coherence-based Pseudo Labeling and Cooperative Unfolding Network
NeurIPS 2024Spotlight