Xiaojian Ma
31 papers · 2019–2026 · 9 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+11 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (53) π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
π
Grand Slam
π§¬
Topic Evolution
π€
Dynamic Duo
(14)
π
Triple Crown
π¬
Deep Specialist
(12)
π
Conference Pioneer
π₯
Unstoppable Β· Bronze
β‘
Prolific Year Β· Prolific
π
Century Club Β· Bronze
π
Renaissance Researcher
(5)
ποΈ
Keyword Collector
(160)
Top co-authors
Research topics
Artificial Intelligence
(22)
Core AI
(21)
Machine Learning
(16)
Learning Types Β· Machine Learning
(13)
Deep Learning
(10)
Reinforcement Learning
(7)
Computer Vision
(6)
Learning Paradigms
(6)
Methods
(6)
Architectures
(4)
Learning Types Β· Deep Learning
(4)
Robotics
(3)
Analysis
(3)
Capabilities
(3)
Core Methods
(3)
Keywords
vision-language model
(6)
imitation learning
(4)
multimodal learning
(4)
instruction following
(4)
scene understanding
(3)
embodied ai
(3)
large language model
(2)
tool usage
(2)
vision language action
(2)
energy-based model
(2)
reinforcement learning
(2)
spatial reasoning
(2)
visual grounding
(2)
question answering
(2)
visual reasoning
(2)
foundation model
(2)
latent diffusion
(2)
policy optimization
(1)
zero-shot learning
(1)
autoregressive transformer
(1)
Papers
TongUI: Internet-Scale Trajectories from Multimodal Web Tutorials for Generalized GUI Agents
AAAI 2026
Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding
ICCV 2025
Falcon: Fast Visuomotor Policies via Partial Denoising
ICML 2025
GROOT-2: Weakly Supervised Multimodal Instruction Following Agents
ICLR 2025
JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse
ACL 2025
Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation
ICCV 2025
Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage
ICLR 2025
ROCKET-1: Mastering Open-World Interaction with Visual-Temporal Context Prompting
CVPR 2025
An Embodied Generalist Agent in 3D World
ICML 2024
Bongard-OpenWorld: Few-Shot Reasoning for Free-form Visual Concepts in the Real World
ICLR 2024
CLOVA: A Closed-LOop Visual Assistant with Tool Usage and Update
CVPR 2024
GROOT: Learning to Follow Instructions by Watching Gameplay Videos
ICLR 2024
MindAgent: Emergent Gaming Interaction
NAACL 2024
MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning
ICLR 2024
Multi-modal Situated Reasoning in 3D Scenes
NeurIPS 2024
OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents
NeurIPS 2024
UltraEdit: Instruction-based Fine-Grained Image Editing at Scale
NeurIPS 2024
Unifying 3D Vision-Language Understanding via Promptable Queries
ECCV 2024
VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding
ECCV 2024
3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment
ICCV 2023
Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction
CVPR 2023
SQA3D: Situated Question Answering in 3D Scenes
ICLR 2023
Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions
CVPR 2022
Latent Diffusion Energy-Based Model for Interpretable Text Modelling
ICML 2022
RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning
ICLR 2022
Adversarial Option-Aware Hierarchical Imitation Learning
ICML 2021
Unsupervised Foreground Extraction via Deep Region Competition
NeurIPS 2021
Reinforcement Learning from Imperfect Demonstrations under Soft Expert Guidance
AAAI 2020
Theory-Based Causal Transfer:Integrating Instance-Level Induction and Abstract-Level Structure Learning
AAAI 2020
Imitation Learning from Observations by Minimizing Inverse Dynamics Disagreement
NeurIPS 2019
Task Transfer by Preference-Based Cost Learning
AAAI 2019