---

1. MegaTrain: Full Precision Training of 100B+ Parameter Large Language Models on a Single GPU
   arXiv.org2026-04-06alphaXiv arXiv S2
2. Expert Threshold Routing for Autoregressive Language Modeling with Dynamic Computation Allocation and Load Balancing
   arXiv.org2026-03-12alphaXiv arXiv S2
3. Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination
   arXiv.org2024-11-15alphaXiv arXiv S2
4. Virtual Context: Enhancing Jailbreak Attacks with Special Token Injection
   arXiv.org2024-06-28alphaXiv arXiv S2
5. Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models
   arXiv.org2024-02-27alphaXiv arXiv S2
6. FairCoder: Evaluating Social Bias of LLMs in Code Generation
   S2