This renders them impractical to use in a wide range of use-cases, limiting who can benefit from them to a handful of big corporations. As an attempt to mitigate this issue, Touvron et al.

The original MuZero did not use sticky actions (Machado et al., 2017) (a 25% chance that the selected action is ignored and that instead the previous action is repeated) for Atari experiments. For all experiments in this work we used a network architecture based on the one introduced by MuZero(Schrittwieser etal.,2020), To implement the network, we used the modules provided by the Haiku neural network library (Henniganetal.,2020). We did not observe any benefit from using a Gaussian mixture, so instead inallourexperiments weusedasingle Gaussian withdiagonal covariance. All experiments used the Adam optimiser (Kingma & Ba, 2015) with decoupled weight decay (Loshchilov & Hutter, 2017) for training.

UAD has a wide range of applications, e.g., industrial

Thus,theassumption of the policy being conditionally-independent ofzω givenziα corresponds well to the assumption of agents only using local information (rather than joint information) in MARL to inform their policy/decision-making. Note that we found that cyclically-annealing [82]theβ term in our variational lower bound from0to the values specified in Table 5to help avoid KL-vanishing. A.2.4 ComputationalDetails For MARL trajectory data generation, we used an internal CPU cluster for both the 3-agent hillclimbing and 2-agent coordination domains, using TPUs for only the multiagent MuJoCo data generation. Given a characteristic of interest (e.g., the level of dispersion of agents), we define a training set consisting of joint latentszω and class labelsy (e.g., classes corresponding to different intervals of team returns). Using these definitions, we can gauge the representational power ofzω by learning a mapping g: ˆνc(zω) y. In practice, g is a simple model (e.g., shallow network or linear projection) so as to gauge the expressivity of the latent space.

Recent research has developed several LLM architectures suitable for inference on end-user devices, such as the Mixture of Lookup Experts (MoLE)~\parencite{jie_mixture_2025}. A key feature of MoLE is that each token id is associated with a dedicated group of experts. For a given input, only the experts corresponding to the input token id will be activated. Since the communication overhead of loading this small number of activated experts into RAM during inference is negligible, expert parameters can be offloaded to storage, making MoLE suitable for resource-constrained devices. However, MoLE's context-independent expert selection mechanism, based solely on input ids, may limit model performance. To address this, we propose the \textbf{M}ixture \textbf{o}f \textbf{L}ookup \textbf{K}ey-\textbf{V}alue Experts (\textbf{MoLKV}) model. In MoLKV, each expert is structured as a key-value pair. For a given input, the input-derived query interacts with the cached key-value experts from the current sequence, generating a context-aware expert output. This context-aware mechanism alleviates the limitation of MoLE, and experimental results demonstrate that MoLKV achieves significantly lower validation loss in small-scale evaluations.

We present MetaTT, a Tensor Train (TT) adapter framework for fine-tuning of pre-trained transformers. MetaTT enables flexible and parameter-efficient model adaptation by using a single shared TT to factorize transformer sub-modules. This factorization indexes key structural dimensions, including layer and matrix type, and can optionally incorporate heads and tasks. This design allows MetaTT's parameter count to scale with the sum, rather than the product, of the modes, resulting in a substantially more compact adapter. Our benchmarks compare MetaTT with LoRA along with recent state-of-the-art matrix and tensor decomposition based fine-tuning methods. We observe that when tested on single-task standard language modeling benchmarks, MetaTT achieves competitive parameter efficiency to accuracy tradeoff. We further demonstrate that MetaTT performs competitively when compared to state-of-the-art methods on multi-task learning. Finally, we leverage the TT-ansatz to design a rank adaptive optimizer inspired by the DMRG method from many-body physics. Our results demonstrate that integrating this approach with AdamW enhances optimization performance for a specified target rank.

Marketing Mix Modeling (MMM) is a statistical technique used to estimate the impact of marketing activities on business outcomes such as sales, revenue, or customer visits. Traditional MMM approaches often rely on linear regression or Bayesian hierarchical models that assume independence between marketing channels and struggle to capture complex temporal dynamics and non-linear saturation effects [@Chan2017; @Hanssens2005; @Ng2021Bayesian]. **DeepCausalMMM** is a Python package that addresses these limitations by combining deep learning, causal inference, and advanced marketing science. The package uses Gated Recurrent Units (GRUs) to automatically learn temporal patterns such as adstock (carryover effects) and lag, while simultaneously learning statistical dependencies and potential causal structures between marketing channels through Directed Acyclic Graph (DAG) learning [@Zheng2018NOTEARS; @Gong2024CausalMMM]. Additionally, it implements Hill equation-based saturation curves to model diminishing returns and optimize budget allocation. Key features include: (1) a data-driven design where hyperparameters and transformations (e.g., adstock decay, saturation curves) are learned or estimated from data with sensible defaults, rather than requiring fixed heuristics or manual specification, (2) multi-region modeling with both shared and region-specific parameters, (3) robust statistical methods including Huber loss and advanced regularization, (4) comprehensive response curve analysis for understanding channel saturation.

The prevalence of Large Language Models (LLMs) for generating multilingual text and source code has only increased the imperative for machine-generated content detectors to be accurate and efficient across domains. Current detectors, predominantly utilizing zero-shot methods, such as Fast DetectGPT or GPTZero, either incur high computational cost or lack sufficient accuracy, often with a trade-off between the two, leaving room for further improvement. To address these gaps, we propose the fine-tuning of encoder-only Small Language Models (SLMs), in particular, the pre-trained models of RoBERTA and CodeBERTa using specialized datasets on source code and other natural language to prove that for the task of binary classification, SLMs outperform LLMs by a huge margin whilst using a fraction of compute. Our encoders achieve AUROC $= 0.97$ to $0.99$ and macro-F1 $0.89$ to $0.94$ while reducing latency by $8$-$12\times$ and peak VRAM by $3$-$5\times$ at $512$-token inputs. Under cross-generator shifts and adversarial transformations (paraphrase, back-translation; code formatting/renaming), performance retains $\geq 92%$ of clean AUROC. We release training and evaluation scripts with seeds and configs; a reproducibility checklist is also included.