Skip to content
conftrace_

Kai Qiu

11 papers · 2019–2026 · 6 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 ↓
+2 more ↓ πŸŒ‰ Interdisciplinary Bridge Β· Bronze 🌍 Conference Polyglot Β· Silver πŸƒ Academic Marathon Β· Sprint πŸ—ΊοΈ Taxonomy Completionist (23) 🐣 Hot Topic Early Bird
πŸ’Ž Century Club Β· Bronze πŸ—ƒοΈ Keyword Collector (55)

Venues

CVPR (4) AAAI (2) ICCV (2) ECCV (1) ICLR (1) WACV (1)

Top co-authors

Qi Dai (6) Chong Luo (6) Jianmin Bao (4) Yifan Yang (3) Zuxuan Wu (2) Hao Chen (2) Baining Guo (2) Yueming Pan (2) Bhiksha Raj (2) Jianlong Fu (2)

Research topics

Computer Vision (8) Deep Learning (7) Generation (5) Models (5) Artificial Intelligence (4) Architectures (4) Core AI (4) Machine Learning (3) Analysis (2) Core Methods (2) Learning Types Β· Deep Learning (2) Processing (2) Application Areas (1) Learning Types Β· Machine Learning (1)

Keywords

diffusion model (3) video generation (3) text-to-video generation (2) image generation (2) autoregressive model (1) video understanding (1) efficient training (1) spatio-temporal modeling (1) density estimation (1) image inpainting (1) human pose estimation (1) stable diffusion (1) variational autoencoder (1) dynamic graph (1) latent space (1) video restoration (1) benchmark evaluation (1) multimodal reasoning (1) video question answering (1) reinforcement learning (1)

Papers

FlashPortrait: 6x Faster Infinite Portrait Animation with Adaptive Latent Prediction CVPR 2026 FPS-Bench: A Benchmark for High Frame-Rate Video Understanding CVPR 2026 HiTVideo: Hierarchical Tokenizers for Enhancing Text-to-Video Generation with Autoregressive Large Language Models AAAI 2026 MageBench: Bridging Large Multimodal Models to Agents WACV 2026 HomoGen: Enhanced Video Inpainting via Homography Propagation and Diffusion CVPR 2025 ImageFolder: Autoregressive Image Generation with Folded Tokens ICLR 2025 REDUCIO! Generating 1K Video within 16 Seconds using Extremely Compressed Motion Latents ICCV 2025 MicroCinema: A Divide-and-Conquer Approach for Text-to-Video Generation CVPR 2024 R^2-Bench: Benchmarking the Robustness of Referring Perception Models under Perturbations ECCV 2024 DGCN: Dynamic Graph Convolutional Network for Efficient Multi-Person Pose Estimation AAAI 2020 Learn to Scale: Generating Multipolar Normalized Density Maps for Crowd Counting ICCV 2019