most citedPAT: Accelerating LLM Decoding via Prefix-Aware Attention with Resource Efficient Multi-Tile Kernel

1 citations · 1 across the 10 of their papers we have counts for

collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2026

Leader Reward for POMO-Based Neural Combinatorial Optimization

Chaoyang Wang, Pengzhi Cheng, Jingze Li +1

Deep neural networks based on reinforcement learning (RL) for solving combinatorial optimization (CO) problems are developing rapidly and have shown a tendency to approach or even…

cs.LG2026

Reinforcing Human Behavior Simulation via Verbal Feedback

Weiwei Sun, Xuhui Zhou, Jiarui Liu +13

Humans learn social norms and behaviors from verbal feedback (e.g., a parent saying "that was rude" or a friend explaining "here's why that hurt"). Yet, learning from feedback for…

cs.LG2026

Spend Less, Fit Better: Budget-Efficient Scaling Law Fitting via Active Experiment Selection

Sijie Li, Shanda Li, Haowei Lin +3

Scaling laws are used to plan multi-million-dollar training runs, but fitting those laws can itself cost millions. In modern large-scale workflows, assembling a sufficiently inform…

cs.LG2026

FrontierCO: Real-World and Large-Scale Evaluation of Machine Learning Solvers for Combinatorial Optimization

Shengyu Feng, Weiwei Sun, Shanda Li +2

Machine learning (ML) has shown promise for tackling combinatorial optimization (CO), but much of the reported progress relies on small-scale, synthetic benchmarks that fail to cap…

cs.LG2026

GradAlign: Gradient-Aligned Data Selection for LLM Reinforcement Learning

Ningyuan Yang, Weihua Du, Weiwei Sun +2

Reinforcement learning (RL) has become a central post-training paradigm for large language models (LLMs), but its performance is highly sensitive to the quality of training problem…

cs.LG2026

CodePDE: An Inference Framework for LLM-driven PDE Solver Generation

Shanda Li, Tanya Marwah, Junhong Shen +4

Partial differential equations (PDEs) are fundamental to modeling physical systems, yet solving them remains a complex challenge. Traditional numerical solvers rely on expert knowl…