Pokemon Red is a long-horizon JRPG with sparse rewards, partial observability, and quirky control mechanics that make it a challenging benchmark for reinforcement learning. While recent work has shown that PPO agents can clear the first two gyms using heavy reward shaping and engineered observations, training remains brittle in practice, with agents often degenerating into action loops, menu spam, or unproductive wandering. In this paper, we present PokeRL, a modular system that trains deep reinforcement learning agents to […]

Ver mais

“The company is ready and getting more ready for every day,” Rauch said about an IPO at HumanX conference.

Ver mais

arXiv:2602.08933v1 Announce Type: new Abstract: Regression neural networks (NNs) are most commonly trained by minimizing the mean squared prediction error, which is highly sensitive to outliers and data contamination. Existing robust training methods for regression NNs are often limited in scope and rely primarily on empirical validation, with only a few offering partial theoretical guarantees. In this paper, we propose a new robust learning framework for regression NNs based on the $beta$-divergence (also known as the density power […]

Ver mais

arXiv:2604.06253v1 Announce Type: new Abstract: Cross-lingual code generation is critical in enterprise environments where multiple programming languages coexist. However, fine-tuning large language models (LLMs) individually for each language is computationally prohibitive. This paper investigates whether parameter-efficient fine-tuning methods and optimizer enhancements can improve cross-lingual transfer from Python to languages like Java. We fine-tune the Code Llama 7B model using low-rank adaptation (LoRA) to optimize a small subset of parameters and compare Adam and Sophia optimizers, while exploring a […]

Ver mais

arXiv:2602.10246v1 Announce Type: new Abstract: Solid State Drives (SSDs) are critical to datacenters, consumer platforms, and mission-critical systems. Yet diagnosing their performance and reliability is difficult because data are fragmented and time-disjoint, and existing methods demand large datasets and expert input while offering only limited insights. Degradation arises not only from shifting workloads and evolving architectures but also from environmental factors such as temperature, humidity, and vibration. We present KORAL, a knowledge driven reasoning framework that integrates Large […]

Ver mais

arXiv:2602.03890v1 Announce Type: new Abstract: Point clouds provide a compact and expressive representation of 3D objects, and have recently been integrated into multimodal large language models (MLLMs). However, existing methods primarily focus on static objects, while understanding dynamic point cloud sequences remains largely unexplored. This limitation is mainly caused by the lack of large-scale cross-modal datasets and the difficulty of modeling motions in spatio-temporal contexts. To bridge this gap, we present 4DPC$^2$hat, the first MLLM tailored for dynamic […]

Ver mais

We present Speculative Rollout with Tree-Structured Cache (SRT), a simple, model-free approach to accelerate on-policy reinforcement learning (RL) for language models without sacrificing distributional correctness. SRT exploits the empirical similarity of rollouts for the same prompt across training steps by storing previously generated continuations in a per-prompt tree-structured cache. During generation, the current policy uses this tree as the draft model for performing speculative decoding. To keep the cache fresh and improve draft model quality, SRT updates trees […]

Ver mais

arXiv:2601.19156v1 Announce Type: new Abstract: We analyze Muon as originally proposed and used in practice — using the momentum orthogonalization with a few Newton-Schulz steps. The prior theoretical results replace this key step in Muon with an exact SVD-based polar factor. We prove that Muon with Newton-Schulz converges to a stationary point at the same rate as the SVD-polar idealization, up to a constant factor for a given number $q$ of Newton-Schulz steps. We further analyze this constant […]

Ver mais

Discover OpenAI’s Child Safety Blueprint—a roadmap for building AI responsibly with safeguards, age-appropriate design, and collaboration to protect and empower young people online.

Ver mais

arXiv:2603.06672v1 Announce Type: new Abstract: Semantic noise initialization has been reported to improve robustness and controllability in image diffusion models. Whether these gains transfer to text-to-video (T2V) generation remains unclear, since temporal coupling can introduce extra degrees of freedom and instability. We benchmark semantic noise initialization against standard Gaussian noise using a frozen VideoCrafter-style T2V diffusion backbone and VBench on 100 prompts. Using prompt-level paired tests with bootstrap confidence intervals and a sign-flip permutation test, we observe a […]

Ver mais