7 papers
SortedRL: Accelerating RL Training for LLMs through Online Length-Aware Scheduling
Yiqi Zhang, Huiqiang Jiang, Xufang Luo +7
Scaling reinforcement learning (RL) has shown strong promise for enhancing the reasoning abilities of large language models (LLMs), particularly in tasks requiring long chain-of-th…
Toward Relative Positional Encoding in Spiking Transformers
Changze Lv, Yansen Wang, Dongqi Han +4
Spiking neural networks (SNNs) are bio-inspired networks that mimic how neurons in the brain communicate through discrete spikes, which have great potential in various tasks due to…
Towards Graph Foundation Models: Training on Knowledge Graphs Enables Transferability to General Graphs
Kai Wang, Siqiang Luo, Caihua Shan +1
Inspired by the success of large language models, there is a trend toward developing graph foundation models to conduct diverse downstream tasks in various domains. However, curren…
What Makes a Good Diffusion Planner for Decision Making?
Haofei Lu, Dongqi Han, Yifei Shen +1
Diffusion models have recently shown significant potential in solving decision-making problems, particularly in generating behavior plans -- also known as diffusion planning. While…
Habitizing Diffusion Planning for Efficient and Effective Decision Making
Haofei Lu, Yifei Shen, Dongsheng Li +2
Diffusion models have shown great promise in decision-making, also known as diffusion planning. However, the slow inference speeds limit their potential for broader real-world appl…
Omni-DNA: A Unified Genomic Foundation Model for Cross-Modal and Multi-Task Learning
Zehui Li, Vallijah Subasri, Yifei Shen +4
Large Language Models (LLMs) demonstrate remarkable generalizability across diverse tasks, yet genomic foundation models (GFMs) still require separate finetuning for each downstrea…