5 papers
AnE: Pushing the Reasoning Frontier of Multimodal LLMs via Anchor Evolution
Zehao Wang, Yihan Zeng, Zidong Gong +5
Post-training via Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) is crucial for enhancing reasoning in Multimodal Large Language Models (MLLMs), yet existing paradigm…
IFDNS: An Iterative Feedback-Driven Neuro-Symbolic Method for Faithful Logical Reasoning
Xiaoheng Wang, Tongxuan Liu, Zi Gong +5
Large language models (LLMs) have demonstrated impressive capabilities across a wide range of reasoning tasks, including logical and mathematical problem-solving. While prompt-base…
Rodimus*: Breaking the Accuracy-Efficiency Trade-Off with Efficient Attentions
Zhihao He, Hang Yu, Zi Gong +3
Recent advancements in Transformer-based large language models (LLMs) have set new standards in natural language processing. However, the classical softmax attention incurs signifi…
Measurement of LLM's Philosophies of Human Nature
Minheng Ni, Ennan Wu, Zidong Gong +6
The widespread application of artificial intelligence (AI) in various tasks, along with frequent reports of conflicts or violations involving AI, has sparked societal concerns abou…
Every Sample Matters: Leveraging Mixture-of-Experts and High-Quality Data for Efficient and Accurate Code LLM
Codefuse, Ling Team, : +30
Recent advancements in code large language models (LLMs) have demonstrated remarkable capabilities in code generation and understanding. It is still challenging to build a code LLM…