4 papers
DyCon: Dynamic Reasoning Control via Evolving Difficulty Modeling
Tengyao Tu, Yulin Li, Hui-Ling Zhen +6
Recent advances in Large Reasoning Models (LRMs) demonstrate remarkable performance improvements by iteratively reflecting, exploring, and executing complex tasks, yet suffer from…
DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding
Yanhua Jiao, Tianyi Wu, Xiaoxi Sun +6
While parallel decoding is central to the efficiency of Diffusion Large Language Models (dLLMs), current strategies are often hindered by overly conservative confidence thresholds.…
Task-Specific Data Selection for Instruction Tuning via Monosemantic Neuronal Activations
Da Ma, Gonghu Shang, Zhi Chen +6
Instruction tuning improves the ability of large language models (LLMs) to follow diverse human instructions, but achieving strong performance on specific target tasks remains chal…
LESA: Learnable LLM Layer Scaling-Up
Yifei Yang, Zouying Cao, Xinbei Ma +4
Training Large Language Models (LLMs) from scratch requires immense computational resources, making it prohibitively expensive. Model scaling-up offers a promising solution by leve…