Pengxiang Li
10 papers · 2021–2026 · 7 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 ↓+3 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (21)
π
Century Club Β· Bronze
β‘
Prolific Year Β· Productive
ποΈ
Keyword Collector
(50)
Top co-authors
Research topics
Artificial Intelligence
(7)
Core AI
(7)
Machine Learning
(4)
Computer Vision
(3)
Deep Learning
(3)
Natural Language Processing
(3)
Generation
(2)
Learning Types
(2)
Optimization & Theory
(2)
Resources & Methods
(2)
Computer Science
(1)
Analysis
(1)
Application Areas
(1)
Applications
(1)
Foundations
(1)
Keywords
multimodal large language model
(2)
vision-language model
(2)
benchmark evaluation
(1)
disparity estimation
(1)
video generation
(1)
depth estimation
(1)
object tracking
(1)
diffusion model
(1)
semantic alignment
(1)
computational efficiency
(1)
hierarchical reasoning
(1)
stereo matching
(1)
occlusion handling
(1)
feedback mechanism
(1)
exploration policy
(1)
visual grounding
(1)
multimodal agent
(1)
low-rank adaptation
(1)
gradient norm
(1)
visual perception
(1)
Papers
InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection
EACL 2026
InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization
AAAI 2026
SynthRGB-T: Language-Vision Guided Image Translation for Diversity Synthesis
CVPR 2026
Automated Evaluation of Large Vision-Language Models on Self-Driving Corner Cases
WACV 2025
Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN
ICLR 2025
Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage
ICLR 2025
Outlier-weighed Layerwise Sampling for LLM Fine-tuning
ACL 2025
TrackDiffusion: Tracklet-Conditioned Video Generation via Diffusion Models
WACV 2025
FIRE: A Dataset for Feedback Integration and Refinement Evaluation of Multimodal Models
NeurIPS 2024
A Decomposition Model for Stereo Matching
CVPR 2021