pith. sign in

Shengbang Tong

Identifiers

  • name variant Shengbang Tong 0.60 · backfill

Papers (7)

  1. VisionFoundry: Teaching VLMs Visual Perception with Synthetic Images cs.CV · 2026 · author #4
  2. Cambrian-S: Towards Spatial Supersensing in Video cs.CV · 2025 · author #7
  3. Diffusion Transformers with Representation Autoencoders cs.CV · 2025 · author #3
  4. SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training cs.AI · 2025 · author #4
  5. MetaMorph: Multimodal Understanding and Generation via Instruction Tuning cs.CV · 2024 · author #1
  6. MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark cs.CL · 2024 · author #6
  7. Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs cs.CV · 2024 · author #1

Mentions

  • 2511.04670 #7 · arxiv_oai · confidence 0.70 Shengbang Tong
  • 2412.14164 #1 · arxiv_oai · confidence 0.70 Shengbang Tong
  • 2406.16860 #1 · arxiv_oai · confidence 0.70 Shengbang Tong

Frequent Coauthors