I-Lora: Iterative Merging of Routing-Tuned Low-Rank Adapters for Multi-task Learning | OpenReview

The advancement of vision-language models has significantly boosted the performance of embodied and game AI, endowing them with more robust general visual understanding capabilities and logical...

Verifying your browser | OpenReview Verifying your browser Complete the check below to continue to OpenReview Please complete the verification above. Have an OpenReview account? Sign in to skip this check.

related reading

• LoRA Without Regret - Thinking Machines Labthinkingmachines.ai
• Explore | alphaXivalphaxiv.org
• [2106.09685] LoRA: Low-Rank Adaptation of Large Language Modelsarxiv.org
• Inkling: Our Open-Weights Model - Thinking Machines Labthinkingmachines.ai
• Explore | alphaXivalphaxiv.org
• Learning to Reason in 13 Parametersarxiv.org
• Language Models can Solve Computer Tasksarxiv.org
• How We Build Trillion Parameter Reasoning RL with 10% GPUsmacaron.im
• [2506.06105] Text-to-LoRA: Instant Transformer Adaptionarxiv.org
• State of Vision-Language-Action (VLA) Research at ICLR 2026 – Moritz Reussmbreuss.github.io
• [2310.18547] Punica: Multi-Tenant LoRA Servingarxiv.org
• 2106.09685arxiv.org