The Upper Confidence Bounds For Trees (UCT) algorithm is not agnostic to the reward scale of the game it is applied to. For zero-sum games with the sparse rewards of $\{-1,0,1\}$ at the end of the game, this is not a problem, but many games often feature dense rewards with hand-picked reward scales, causing a node's Q-value to span different magnitudes across different games. In this paper, we evaluate various strategies for adaptively choosing the UCT exploration constant $λ$, called $λ$-strategies, that are agnostic to the game's reward scale. These $λ$-strategies include those proposed in the literature as well as five new strategies. Given our experimental results, we recommend using one of our newly suggested $λ$-strategies, which is to choose $λ$ as $2 \cdot σ$ where $σ$ is the empirical standard deviation of all state-action pairs' Q-values of the search tree. This method outperforms existing $λ$-strategies across a wide range of tasks both in terms of a single parameter value and the peak performances obtained by optimizing all available parameters.

A key barrier to interpreting large language models is polysemanticity, where neurons activate for multiple unrelated concepts. Sparse autoencoders (SAEs) have been proposed to mitigate this issue by transforming dense activations into sparse, more interpretable features. While prior work suggests that SAEs promote monosemanticity, no quantitative comparison has examined how concept activation distributions differ between SAEs and their base models. This paper provides the first systematic evaluation of SAEs against base models through activation distribution lens. We introduce a fine-grained concept separability score based on the Jensen-Shannon distance, which captures how distinctly a neuron's activation distributions vary across concepts. Using two large language models (Gemma-2-2B and DeepSeek-R1) and multiple SAE variants across five datasets (including word-level and sentence-level), we show that SAEs reduce polysemanticity and achieve higher concept separability. To assess practical utility, we evaluate concept-level interventions using two strategies: full neuron masking and partial suppression. We find that, compared to base models, SAEs enable more precise concept-level control when using partial suppression. Building on this, we propose Attenuation via Posterior Probabilities (APP), a new intervention method that uses concept-conditioned activation distributions for targeted suppression. APP achieves the smallest perplexity increase while remaining highly effective at concept removal.

Knowledge graph embedding (KGE) models are often used to predict missing links for knowledge graphs (KGs). However, multiple KG embeddings can perform almost equally well for link prediction yet suggest conflicting predictions for certain queries, termed \textit{predictive multiplicity} in literature. This behavior poses substantial risks for KGE-based applications in high-stake domains but has been overlooked in KGE research. In this paper, we define predictive multiplicity in link prediction. We introduce evaluation metrics and measure predictive multiplicity for representative KGE methods on commonly used benchmark datasets. Our empirical study reveals significant predictive multiplicity in link prediction, with $8\%$ to $39\%$ testing queries exhibiting conflicting predictions. To address this issue, we propose leveraging voting methods from social choice theory, significantly mitigating conflicts by $66\%$ to $78\%$ according to our experiments.

One of the most important promises of decentralized systems is scalability, which is often assumed to be present in robot swarm systems without being contested. Simple limitations, such as movement congestion and communication conflicts, can drastically affect scalability. In this work, we study the effects of congestion in a binary collective decision-making task. We evaluate the impact of two types of congestion (communication and movement) when using three different techniques for the task: Honey Bee inspired, Stigmergy based, and Division of Labor. We deploy up to 150 robots in a physics-based simulator performing a sampling mission in an arena with variable levels of robot density, applying the three techniques. Our results suggest that applying Division of Labor coupled with versioned local communication helps to scale the system by minimizing congestion.

In this article we will work with an image dataset to train an Image classifier using a custom CNN built with TensorFlow. PS: For those who don't already know what is Deep learning or CNN this article may be difficult to understand and unfortunately there is no easier way around this. This article is not meant to be a tutorial about Computer Vision or Deep Learning, For those familiar with these concepts please read on. We will work with a dataset provided here. This dataset is a curated nicely, cleaned and arranged collection of roasted coffee beans in train and test folders.

This line of code is used to define the transformations that the training DataGenerator will apply on all the images to augment the size of the dataset. For the validation DataGenerator, we only specify the scaling factor. The other transformations are not required because we are not training the model on this data. Next, we define the Model. We set layer.trainable False for each layer of the VGG model, as we are using the pre-trained weights of the model.

We performed an integrative analysis on 7 independent datasets across 5 institutions totaling 1,194 NSCLC patients (age median 68.3 years [range 32.5–93.3], Using external validation in computed tomography (CT) data, we identified prognostic signatures using a 3D convolutional neural network (CNN) for patients treated with radiotherapy (n 771, age median 68.0 years [range 32.5–93.3], We then employed a transfer learning approach to achieve the same for surgery patients (n 391, age median 69.1 years [range 37.2–88.0], We found that the CNN predictions were significantly associated with 2-year overall survival from the start of respective treatment for radiotherapy (area under the receiver operating characteristic curve [AUC] 0.70 [95% CI 0.63–0.78], The CNN was also able to significantly stratify patients into low and high mortality risk groups in both the radiotherapy (p 0.001) and surgery (p 0.03) datasets.