13 citations · 19 across the 12 of their papers we have counts for
12 papers
QiMeng-Kernel: Macro-Thinking Micro-Coding Paradigm for LLM-Based High-Performance GPU Kernel Generation
Xinguo Zhu, Shaohui Peng, Jiaming Guo +10
Developing high-performance GPU kernels is critical for AI and scientific computing, but remains challenging due to its reliance on expert crafting and poor portability. While LLMs…
Code Driven Planning with Domain-Adaptive Critic
Zikang Tian, Shaohui Peng, Du Huang +11
Large Language Models (LLMs) have been widely adopted as task planners for AI agents in sequential decision-making problems, leveraging their extensive world knowledge. However, th…
QiMeng-Attention: SOTA Attention Operator is generated by SOTA Attention Algorithm
Qirui Zhou, Shaohui Peng, Weiqiang Xiong +11
The attention operator remains a critical performance bottleneck in large language models (LLMs), particularly for long-context scenarios. While FlashAttention is the most widely u…
QiMeng-TensorOp: Automatically Generating High-Performance Tensor Operators with Hardware Primitives
Xuzhi Zhang, Shaohui Peng, Qirui Zhou +12
Computation-intensive tensor operators constitute over 90\% of the computations in Large Language Models (LLMs) and Deep Neural Networks.Automatically and efficiently generating hi…
Emergent Communication for Rules Reasoning
Yuxuan Guo, Yifan Hao, Rui Zhang +14
Research on emergent communication between deep-learning-based agents has received extensive attention due to its inspiration for linguistics and artificial intelligence. However,…
Context Shift Reduction for Offline Meta-Reinforcement Learning
Yunkai Gao, Rui Zhang, Jiaming Guo +10
Offline meta-reinforcement learning (OMRL) utilizes pre-collected offline datasets to enhance the agent's generalization ability on unseen tasks. However, the context shift problem…
Efficient Symbolic Policy Learning with Differentiable Symbolic Expression
Jiaming Guo, Rui Zhang, Shaohui Peng +8
Deep reinforcement learning (DRL) has led to a wide range of advances in sequential decision-making tasks. However, the complexity of neural network policies makes it difficult to…
Contrastive Modules with Temporal Attention for Multi-Task Reinforcement Learning
Siming Lan, Rui Zhang, Qi Yi +10
In the field of multi-task reinforcement learning, the modular principle, which involves specializing functionalities into different modules and combining them appropriately, has b…
Self-driven Grounding: Large Language Model Agents with Automatical Language-aligned Skill Learning
Shaohui Peng, Xing Hu, Qi Yi +9
Large language models (LLMs) show their powerful automatic reasoning and planning capability with a wealth of semantic knowledge about the human world. However, the grounding probl…
Online Prototype Alignment for Few-shot Policy Transfer
Qi Yi, Rui Zhang, Shaohui Peng +10
Domain adaptation in reinforcement learning (RL) mainly deals with the changes of observation when transferring the policy to a new environment. Many traditional approaches of doma…
Conceptual Reinforcement Learning for Language-Conditioned Tasks
Shaohui Peng, Xing Hu, Rui Zhang +7
Despite the broad application of deep reinforcement learning (RL), transferring and adapting the policy to unseen but similar environments is still a significant challenge. Recentl…
Causality-driven Hierarchical Structure Discovery for Reinforcement Learning
Shaohui Peng, Xing Hu, Rui Zhang +9
Hierarchical reinforcement learning (HRL) effectively improves agents' exploration efficiency on tasks with sparse reward, with the guide of high-quality hierarchical structures (e…