pith. sign in

Yonghong Tian

Identifiers

  • name variant Yonghong Tian 0.60 · backfill

Papers (28)

  1. WorldArena 2.0: Extending Embodied World Model Benchmarking on Modality, Functionality and Platform cs.RO · 2026 · author #21
  2. Reasoning Portability: Guiding Continual Learning for MLLMs in the RLVR Era cs.LG · 2026 · author #6
  3. PowerStep: Memory-Efficient Adaptive Optimization via $\ell_p$-Norm Steepest Descent cs.LG · 2026 · author #4
  4. Dynamic Pondering Sparsity-aware Mixture-of-Experts Transformer for Event Stream based Visual Object Tracking cs.CV · 2026 · author #7
  5. Adaptive Spiking Neurons for Vision and Language Modeling cs.NE · 2026 · author #8
  6. Winner-Take-All Spiking Transformer for Language Modeling cs.NE · 2026 · author #9
  7. SMC-AI: Scaling Monte Carlo Simulation to Four Trillion Atoms with AI Accelerators physics.comp-ph · 2026 · author #12
  8. Retina gap junctions support the robust perception by warping neural representational geometries along the visual hierarchy q-bio.NC · 2026 · author #3
  9. BioProAgent: Neuro-Symbolic Grounding for Constrained Scientific Planning cs.AI · 2026 · author #4
  10. AscendKernelGen: A Systematic Study of LLM-Based Kernel Generation for Neural Processing Units cs.AI · 2026 · author #20
  11. Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting cs.CV · 2025 · author #8
  12. SGEMM-cube: Precision-Recovery FP32 GEMM Approximation on Ascend NPUs with FP16 Matrix Engines cs.DC · 2025 · author #7
  13. Open-Sora Plan: Open-Source Large Video Generation Model cs.CV · 2024 · author #23
  14. ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis cs.CV · 2024 · author #10
  15. QKFormer: Hierarchical Spiking Transformer using Q-K Attention cs.NE · 2024 · author #10
  16. A Retina-inspired Sampling Method for Visual Texture Reconstruction eess.IV · 2019 · author #4
  17. 2D LiDAR Map Prediction via Estimating Motion Flow with GRU cs.RO · 2019 · author #2
  18. ODN: Opening the Deep Network for Open-set Action Recognition cs.CV · 2019 · author #6
  19. Winner-Take-All as Basic Probabilistic Inference Unit of Neuronal Circuits q-bio.NC · 2018 · author #2
  20. Hierarchical Deep Co-segmentation of Primary Objects in Aerial Videos cs.CV · 2018 · author #4
  21. A simple blind-denoising filter inspired by electrically coupled photoreceptors in the retina cs.CV · 2018 · author #6
  22. Peeking the Impact of Points of Interests on Didi cs.CY · 2018 · author #1
  23. Learning a Repression Network for Precise Vehicle Search cs.CV · 2017 · author #3
  24. YoTube: Searching Action Proposal via Recurrent and Static Regression Networks cs.CV · 2017 · author #4
  25. Deep Transfer Learning for Person Re-identification cs.CV · 2016 · author #4
  26. Learning long-term dependencies for action recognition with a biologically-inspired deep network cs.CV · 2016 · author #2
  27. Joint Network based Attention for Action Recognition cs.CV · 2016 · author #2
  28. Sequential Deep Trajectory Descriptor for Action Recognition with Three-stream CNN cs.CV · 2016 · author #2

Mentions

  • 2403.16552 #10 · arxiv_oai · confidence 0.70 Yonghong Tian
  • 2605.18903 #6 · arxiv_oai · confidence 0.70 Yonghong Tian
  • 2605.17912 #21 · arxiv_oai · confidence 0.70 Yonghong Tian
  • 2603.00876 #4 · arxiv_oai · confidence 0.70 Yonghong Tian
  • 2508.04227 #8 · arxiv_oai · confidence 0.70 Yonghong Tian
  • 2412.00131 #23 · arxiv_oai · confidence 0.70 Yonghong Tian

Frequent Coauthors