Liangchen Song

13 papers · 2019–2026 · 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 ↓

+4 more ↓

🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (32)

🧬 Topic Evolution 💎 Century Club · Bronze 🔥 Unstoppable · Bronze 🗃️ Keyword Collector (65)

Venues

CVPR (3) ICCV (3) AAAI (2) ICLR (2) ECCV (1) ICML (1) IJCAI (1)

Top co-authors

Junsong Yuan (7) Ming Yang (3) Jiasen Lu (3) Jialian Wu (3) Qian Zhang (3) Yinfei Yang (3) Guoli Wang (2) Chen Chen (2) Xuan Gong (2) Ziyan Wu (2)

Research topics

Computer Vision (9) Deep Learning (8) Machine Learning (5) Artificial Intelligence (4) Learning Types (4) Analysis (3) Application Areas (3) Architectures (3) Generation (3) Models (3) Processing (3) Core AI (2) Core Methods (2) Learning Paradigms (2) Optimization & Theory (2)

Keywords

object detection (3) domain adaptation (2) text-to-video generation (2) diffusion model (2) image generation (2) knowledge distillation (2) pedestrian detection (1) preference optimization (1) video generation (1) autoregressive generation (1) multi-view learning (1) 3d vision (1) information retrieval (1) bird's eye view (1) synthetic data generation (1) efficient computing (1) instance segmentation (1) video tracking (1) knowledge transfer (1) transfer learning (1)

Papers

AToken: A Unified Tokenizer for Vision CVPR 2026 Pico-Banana-400K: A Large-Scale Dataset for Text-Guided Image Editing CVPR 2026 Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated Attention ICML 2025 STIV: Scalable Text and Image Conditioned Video Generation ICCV 2025 Efficient-3Dim: Learning a Generalizable Single-image Novel-view Synthesizer in One Day ICLR 2024 NeuRBF: A Neural Fields Representation with Adaptive Radial Basis Functions ICCV 2023 Progressive Multi-View Human Mesh Recovery with Self-Supervision AAAI 2023 PREF: Predictability Regularized Neural Motion Fields ECCV 2022 Rethinking Soft Labels for Knowledge Distillation: A Bias–Variance Tradeoff Perspective ICLR 2021 Robust Knowledge Transfer via Hybrid Forward on the Teacher-Student Model AAAI 2021 Stacked Homography Transformations for Multi-View Pedestrian Detection ICCV 2021 Track To Detect and Segment: An Online Multi-Object Tracker CVPR 2021 Neurons Merging Layer: Towards Progressive Redundancy Reduction for Deep Supervised Hashing IJCAI 2019