ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Jie Ma

Jie Ma

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 14, 2026, 11:22 PM AMS

16

papers

366

total citations

papers (16)

Federated Learning from Pre-Trained Models: A Contrastive Learning Approach

NEURIPS 2022arXiv

Debate on Graph: A Flexible and Reliable Reasoning Framework for Large Language Models

AlignSAM: Aligning Segment Anything Model to Open Context via Reinforcement Learning

EvoChart: A Benchmark and a Self-Training Approach Towards Real-World Chart Understanding

Active Evaluation Acquisition for Efficient LLM Benchmarking

A Study of Dropout-Induced Modality Bias on Robustness to Missing Video Frames for Audio-Visual Speech Recognition

SDGOCC: Semantic and Depth-Guided Bird's-Eye View Transformation for 3D Multimodal Occupancy Prediction

Deliberation on Priors: Trustworthy Reasoning of Large Language Models on Knowledge Graphs

NEURIPS 2025arXiv

ChartSketcher: Reasoning with Multimodal Feedback and Reflection for Chart Understanding

NEURIPS 2025arXiv

Feature Interactive Representation for Point Cloud Registration

Enhanced Soft Label for Semi-Supervised Semantic Segmentation

FASTer: Focal token Acquiring-and-Scaling Transformer for Long-term 3D Objection Detection

Structured Federated Learning through Clustered Additive Modeling

Co-Progression Knowledge Distillation with Knowledge Prototype for Industrial Anomaly Detection

Multi-Track Message Passing: Tackling Oversmoothing and Oversquashing in Graph Learning via Preventing Heterophily Mixing

Leveraging Large-Scale Weakly Labeled Data for Semi-Supervised Mass Detection in Mammograms