conftrace_

Zhiyuan Xu

17 papers · 2020–2026 · 8 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓
+10 more ↓ 🌈 Renaissance Researcher (7) πŸŒ‰ Interdisciplinary Bridge 🌍 Conference Polyglot (8) πŸƒ Academic Marathon (5) πŸ—ΊοΈ Taxonomy Completionist (48)
πŸ—ΊοΈ Taxonomy Completionist (48) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🧬 Topic Evolution 🀝 Dynamic Duo (12) πŸ‘₯ Mega-Team (37) ⚑ Prolific Year (6) πŸ”₯ Unstoppable (6) πŸ’Ž Century Club (16) πŸ—ƒοΈ Keyword Collector (87)

Conferences

AAAI (5) CVPR (4) ICCV (2) NIPS (2) ECCV (1) EMNLP (1) RSS (1) WACV (1)

Research topics

Papers

TSPE-GS: Probabilistic Depth Extraction for Semi-Transparent Surface Reconstruction via 3D Gaussian Splatting AAAI 2026 Positive2Negative: Breaking the Information-Lossy Barrier in Self-Supervised Single Image Denoising CVPR 2025 Diffusion-Based Visual Anagram as Multi-Task Learning WACV 2025 RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation RSS 2025 A Comprehensive Overhaul of Multimodal Assistant with Small Language Models AAAI 2025 Training-free Generation of Temporally Consistent Rewards from VLMs ICCV 2025 ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Model EMNLP 2025 Exploring Gradient Explosion in Generative Adversarial Imitation Learning: A Probabilistic Perspective AAAI 2024 CP3: Channel Pruning Plug-In for Point-Based Networks CVPR 2023 ScaleKD: Distilling Scale-Aware Knowledge in Small Object Detector CVPR 2023 RGB-Depth Fusion GAN for Indoor Depth Completion CVPR 2022 Label-Guided Auxiliary Training Improves 3D Object Detector ECCV 2022 CADRE: A Cascade Deep Reinforcement Learning Framework for Vision-Based Autonomous Urban Driving AAAI 2022 Teach Less, Learn More: On the Undistillable Classes in Knowledge Distillation NIPS 2022 Hierarchical Graph Attention Network for Few-Shot Visual-Semantic Learning ICCV 2021 Knowledge Transfer in Multi-Task Deep Reinforcement Learning for Continuous Control NIPS 2020 AutoCompress: An Automatic DNN Structured Pruning Framework for Ultra-High Compression Rates AAAI 2020