18 papers
Optimizing CUDA like a Human: Micro-Profiling Tools as Expert Surrogates for LLM-Based GPU Kernel Optimization
Jiading Gai, Shuai Zhang, Kaj Bostrom +6
We present KernelPro, a closed-loop multi-agent system that automatically generates, profiles, and iteratively optimizes GPU kernel code by integrating large language model (LLM) c…
LLMZero: Discovering Adaptive Training Strategies for RL Post-Training via LLM Agents
Haoyang Fang, Wei Zhu, Boran Han +11
RL post-training strategies are dataset-dependent and reveal a recurring empirical pattern: capacity parameters accumulate monotonically across stages, while regularization paramet…
DualKV: Shared-Prompt Flash Attention for Efficient RL Training with Large Rollouts and Long Contexts
Jiading Gai, Shuai Zhang, Xiang Song +2
Modern RL post-training methods such as GRPO and DAPO train on N response sequences of R tokens sampled from a shared prompt of P tokens, but standard FlashAttention replicates all…
Tiny but Mighty: A Software-Hardware Co-Design Approach for Efficient Multimodal Inference on Battery-Powered Small Devices
Yilong Li, Shuai Zhang, Yijing Zeng +5
Large Multimodal Models (LMMs) are inherently modular, comprising vision and audio encoders, a projector, and a language backbone. Yet existing systems execute them monolithically,…
HetRL: Efficient Reinforcement Learning for LLMs in Heterogeneous Environments
Yongjun He, Shuai Zhang, Jiading Gai +5
As large language models (LLMs) continue to scale and new GPUs are released even more frequently, there is an increasing demand for LLM post-training in heterogeneous environments…
OPERA: Online Data Pruning for Efficient Retrieval Model Adaptation
Haoyang Fang, Shuai Zhang, Yifei Ma +5
Domain-specific finetuning is essential for dense retrievers, yet not all data pairs contribute equally to the learning process. We introduce OPERA, a data pruning framework that e…