Wafer-scale computing, with its high integration density and die-to-die bandwidth, offers a promising solution to the exponentially growing computational demands of large AI models. However, mapping large-scale AI training workloads onto wafer-scale architectures poses unique challenges compared to traditional GPU or AI accelerator clusters-namely, limited on-chip memory, non-uniform collective communication, and an exponentially large, sparsely populated search space. To address these challenges, we introduce RAM-Wafer, an innovative reinforcement learning (RL)-based automatic mapping framework designed specifically for wafer-scale computing. Built by extending the production-level AI compiler framework OpenXLA, our compiler-based end-to-end mapping solution incorporates an accurate and fast performance model that accounts for the distinctive constraints of wafer-scale systems. Moreover, our RL-based mapping method efficiently explores the vast search space to identify near-optimal mapping solutions in a fraction of the time required by conventional methods. Extensive experimental results demonstrate that RAM-Wafer outperforms manual expert baselines by 22 % and 9.5 % on Dojo and Waferscale GPU platforms, respectively, and achieves improvements of 15 % and 6.5 % compared to a genetic algorithm (GA). Additionally, RAM-Wafer reduces search time by$28 \times$, cutting mapping time from 2.3 hours to just 5 minutes.

Vision-Language models have dramatically improved embodied and game AI by improving visual understanding and logical planning. However, high computational costs and performance drops during fine-tuning hinder their ability to continually learn new tasks. To address this, we present I-LoRA, a Low-Rank Adapter-Based fine-tuning method that incrementally and independently learns new tasks while retaining the model’s existing logical capabilities. First, our routing-tuning strategy minimizes the LoRA activation values on general tasks to reduce interference from newly introduced tasks. Next, we introduce an iterative approach to merge adapters, allowing new tasks to be integrated without affecting each other’s performance. Comprehensive experiments on Atari datasets with diverse behavioral and logical task requirements show that I-LoRA delivers outstanding single-task performance, robust multitask compatibility, and flexible scalability—without increasing model parameters.

Unsupervised skill discovery aims to learn diverse and distinguishable behaviors in open-ended reinforcement learning. For the existing methods, they focus on improving the diversity via pure exploration, mutual information optimization and learning temporal representation. Despite they perform well on exploration, they remain limited in terms of efficiency, especially for the high-dimensional situations. In this work, we frame the skill discovery as a min-max game of skill generation and policy learning, proposing a regret-aware method on top of temporal representation learning that expands the discovered skill space along the direction of upgradable policy strength. The key insight behind the proposed method is that the skill discovery is adversarial to the policy learning, i.e., skills with weak strength should be further explored while less exploration for the skills with converged strength. As an implementation, we score the degree of strength convergence with regret, and guide the skill discovery with a learnable skill generator. To avoid degeneration, the skill generation comes from an upgradable population of skill generators. We conduct experiments on environments with varying complexities and dimension sizes. Empirical results show that our method outperforms baselines on both efficiency and diversity. Moreover, our method achieves 15% zero-shot improvement on high-dimensional environments, compared to existing methods.