Announcement_24

🔔 Check out our new papers accepted at the NeurIPS 2026, Sydney, Australia 🇦🇺. The papers cover:
  (i) improving spatial and multi-view geometric reasoning in VLMs
  (ii) safety alignments in LLMs
  (iii) how reinforcement learning shapes the behavior and reasoning capabilities of LLMs during post-training

These works support our broader goal of data- and model-efficient multimodal learning, through better structure and adaptation. All codes will be released soon 🎉 — stay tuned!