Skip to content
conftrace_

Jingwei Sun

16 papers · 2021–2026 · 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 ↓
+7 more ↓ πŸ—ΊοΈ Taxonomy Completionist (24) 🌍 Conference Polyglot Β· Silver πŸƒ Academic Marathon Β· Sprint πŸŒ‰ Interdisciplinary Bridge Β· Silver 🐣 Hot Topic Early Bird
πŸ† Grand Slam 🀝 Dynamic Duo (11) ⚑ Prolific Year Β· Productive πŸ”₯ Unstoppable Β· Bronze πŸ’Ž Century Club Β· Bronze 🌈 Renaissance Researcher (5) πŸ—ƒοΈ Keyword Collector (72)

Venues

ICML (3) AAAI (2) CVPR (2) ICCV (2) ICLR (2) NeurIPS (2) ACL (1) ECCV (1) NAACL (1)

Top co-authors

Yiran Chen (11) Hai Li (8) Jianyi Zhang (6) Jingyang Zhang (4) Guangzhong Sun (3) Minxue Tang (3) Ang Li (3) Dong Yang (2) Ziyue Xu (2) Yudong Liu (2)

Research topics

Artificial Intelligence (14) Machine Learning (14) Core AI (9) Application Areas (8) Learning Paradigms Β· Artificial Intelligence (5) Optimization & Theory (5) Computer Vision (2) Deep Learning (2) Mathematics & Optimization (2) Security & Privacy (2) Core Methods (2) Learning Paradigms Β· Machine Learning (2) Learning Types (2) Privacy (2) Natural Language Processing (1)

Keywords

federated learning (5) large language model (3) communication efficiency (2) model compression (2) graph structure (1) distributed learning (1) variational inference (1) text-to-image generation (1) few-shot learning (1) semantic representation (1) video understanding (1) neural network optimization (1) computational efficiency (1) maximum likelihood (1) mutual information (1) gaussian process (1) privacy preservation (1) diffusion model (1) convergence rate (1) semi-supervised learning (1)

Papers

CommitMoE: Efficient Fallback-Free MoE Inference with Offloading Under GPU Memory Constraints AAAI 2026 EvalMuse-40K: A Fine-Grained Benchmark with Comprehensive Human Annotations for Text-to-Image Generation Model Alignment Evaluation AAAI 2026 Introducing Graph Context into Language Models through Parameter-Efficient Fine-Tuning for Lexical Relation Mining ACL 2025 Keyframe-oriented Vision Token Pruning: Enhancing Efficiency of Large Vision Language Models on Long-Form Video Processing ICCV 2025 Min-K%++: Improved Baseline for Pre-Training Data Detection from Large Language Models ICLR 2025 Proactive Privacy Amnesia for Large Language Models: Safeguarding PII with Negligible Impact on Model Utility ICLR 2025 SADA: Stability-guided Adaptive Diffusion Acceleration ICML 2025 FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models ICML 2024 Reimagining Mutual Information for Enhanced Defense against Data Leakage in Collaborative Inference NeurIPS 2024 Structured Pruning for Large Language Models Using Coupled Components Elimination and Minor Fine-tuning NAACL 2024 Unlocking the Potential of Federated Learning: The Symphony of Dataset Distillation via Deep Generative Latents ECCV 2024 Communication-Efficient Vertical Federated Learning with Limited Overlapping Samples ICCV 2023 Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance Reduction ICML 2023 FedCor: Correlation-Based Active Client Selection Strategy for Heterogeneous Federated Learning CVPR 2022 FL-WBC: Enhancing Robustness against Model Poisoning Attacks in Federated Learning from a Client Perspective NeurIPS 2021 Soteria: Provable Defense Against Privacy Leakage in Federated Learning From Representation Perspective CVPR 2021