7 papers
Vision Token Reduction via Attention-Driven Self-Compression for Efficient Multimodal Large Language Models
Omer Faruk Deniz, Ruiyu Mao, Ruochen Li +2
Multimodal Large Language Models (MLLMs) incur significant computational cost from processing numerous vision tokens through all LLM layers. Prior pruning methods operate either be…
LDC: Learning to Generate Research Idea with Dynamic Control
Ruochen Li, Liqiang Jing, Chi Han +2
Recent advancements in large language models (LLMs) have demonstrated their potential in automating the scientific research ideation. Existing approaches primarily focus on prompti…
MLR-Copilot: Autonomous Machine Learning Research based on Large Language Models Agents
Ruochen Li, Teerth Patel, Qingyun Wang +1
Autonomous machine learning research has gained significant attention recently. We present MLR-COPILOT, an autonomous Machine Learning Research framework powered by large language…
The Ramon Llull's Thinking Machine for Automated Ideation
Xinran Zhao, Boyuan Zheng, Chenglei Si +8
This paper revisits Ramon Llull's Ars combinatoria - a medieval framework for generating knowledge through symbolic recombination - as a conceptual foundation for building a modern…
AALC: Large Language Model Efficient Reasoning via Adaptive Accuracy-Length Control
Ruosen Li, Ziming Luo, Quan Zhang +4
Large reasoning models (LRMs) achieve impressive reasoning capabilities by generating lengthy chain-of-thoughts, but this "overthinking" incurs high latency and cost without commen…
Coherent Multimodal Reasoning with Iterative Self-Evaluation for Vision-Language Models
Wenjie Luo, Ruocheng Li, Shanshan Zhu +1
Despite significant advancements, current large language models (LLMs) and vision-language models (LVLMs) continue to struggle with complex, multi-step, cross-modal common sense re…