Zixian Ma
12 papers · 2021–2026 · 5 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 ↓+6 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (27) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π€
Dynamic Duo
(10)
π₯
Mega-Team Β· Squad
β
The Questioner
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(61)
π₯
Unstoppable Β· Bronze
Venues
Top co-authors
Research topics
Artificial Intelligence
(10)
Core AI Β· Artificial Intelligence
(10)
Machine Learning
(6)
Computer Vision
(5)
Deep Learning
(4)
Learning Types Β· Machine Learning
(4)
Models
(4)
Natural Language Processing
(3)
Application Areas
(3)
Core AI Β· Computer Vision
(2)
Learning Types Β· Deep Learning
(2)
Processing
(2)
Resources & Methods
(2)
Reinforcement Learning
(1)
Analysis
(1)
Keywords
vision-language model
(5)
benchmark evaluation
(3)
multimodal language model
(3)
multimodal learning
(2)
visual question answering
(2)
adversarial robustness
(2)
compositional reasoning
(2)
adversarial evaluation
(2)
video understanding
(2)
referring expression
(1)
question answering
(1)
text classification
(1)
temporal reasoning
(1)
knowledge distillation
(1)
natural language processing
(1)
adversarial training
(1)
visual grounding
(1)
video captioning
(1)
object tracking
(1)
scene graph generation
(1)
Papers
Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding
CVPR 2026
SAGE: Training Smart Any-Horizon Agents for Long Video Reasoning with Reinforcement Learning
CVPR 2026
Coarse Correspondences Boost Spatial-Temporal Reasoning in Multimodal Language Model
CVPR 2025
LATTE: Learning to Think with Vision Specialists
EMNLP 2025
Synthetic Visual Genome
CVPR 2025
m&mβs: A Benchmark to Evaluate Tool-Use for multi-step multi-modal Tasks
ECCV 2024
NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples
NeurIPS 2024
Task Me Anything
NeurIPS 2024
CREPE: Can Vision-Language Foundation Models Reason Compositionally?
CVPR 2023
SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality
NeurIPS 2023
ELIGN: Expectation Alignment as a Multi-Agent Intrinsic Reward
NeurIPS 2022
OpenAttack: An Open-source Textual Adversarial Attack Toolkit
ACL 2021