A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Fine-tuning LLMs improves capability but harms safety, study finds.
Reward hacking exploits misspecified rewards, affecting agent capabilities and true performance.
RLVR maintains safety while improving reasoning capabilities in LLMs.
Paper examines LLM capability benchmarks through construct validity, favoring nomological account.
The study uncovers latent capabilities of language models via causal representation learning.
ML Compass helps organizations choose AI models that balance utility, cost, and compliance.
The paper uses geometry to understand how neural networks learn.
Much of the analysis of economic growth has focused on the study of aggregate output. Here, we deviate from this tradition and look instead at the structure of output embodied in the network connecting countries to the products that they export.We characterize this network using four structural features: the negative r…
A new framework ensures model safety by retaining old model capabilities while improving new tasks.
BIG-bench benchmarks language models, revealing their strengths and weaknesses.
When building a unified vision system or gradually adding new capabilities to a system, the usual assumption is that training data for all tasks is always available. However, as the number of tasks grows, storing and retraining on such data becomes infeasible. A new problem arises where we add new capabilities to a Con…
New framework transfers latent knowledge from weak to strong models.
Process capability index (PCI) is a commonly used statistic to measure ability of a process to operate within the given specifications or to produce products which meet the required quality specifications. PCI can be univariate or multivariate depending upon the number of process specifications or quality characteristi…
LLMs struggle with arithmetic tasks unless they use high numerical precision.
Transformers can scale both context and task, but MLPs can only scale task.
AI enhances financial services but humans are irreplaceable for empathy, presence, and ethics.
DNNs generalize object recognition in novel orientations via neurons tuned to common features.
TIR expands LLM capabilities by enabling problem-solving strategies.
LaTRO optimizes latent reasoning in LLMs without external reward.
Paper proposes a new financial fraud detection system using improved RF and GBM.
Due to the growing demand for improving surveillance capabilities in smart cities, systems need to be developed to provide better monitoring capabilities to competent authorities, agencies responsible for strategic resource management, and emergency call centers. This work assumes that, as a complementary monitoring so…
Experts predict significant adoption of decentralized finance by 2034, with traditional finance adapting.
The ever-increasing demand from mobile Machine Learning (ML) applications calls for evermore powerful on-chip computing resources. Mobile devices are empowered with heterogeneous multi-processor Systems-on-Chips (SoCs) to process ML workloads such as Convolutional Neural Network (CNN) inference. Mobile SoCs house sever…
Bio-inspired neuromorphic hardware is a research direction to approach brain's computational power and energy efficiency. Spiking neural networks (SNN) encode information as sparsely distributed spike trains and employ spike-timing-dependent plasticity (STDP) mechanism for learning. Existing hardware implementations of…
New approach extracts AI model representations for steering and monitoring.
Predicts language model performance from public models without training.
A new method learns complex dynamical systems from data efficiently.
Layout design with complex constraints is a challenging problem to solve due to the non-uniqueness of the solution and the difficulties in incorporating the constraints into the conventional optimization-based methods. In this paper, we propose a design method based on the recently developed machine learning technique,…
Designing a deep neural network (DNN) with good generalization capability is a complex process especially when the weights are severely quantized. Model averaging is a promising approach for achieving the good generalization capability of DNNs, especially when the loss surface for training contains many sharp minima. W…
The DoD needs a robust process to evaluate AI/ML model performance and robustness.
Information-theoretic bounded rationality describes utility-optimizing decision-makers whose limited information-processing capabilities are formalized by information constraints. One of the consequences of bounded rationality is that resource-limited decision-makers can join together to solve decision-making problems …
New method predicts language model scaling risks with limited data.
HeteroFL trains diverse clients with varying capabilities efficiently.
LLMs improve financial analysis by processing large data sets.
Chronos-2 forecasts multivariate and covariate data without task-specific training.
SYNTHONY selects tabular synthesizers based on stress profiling and user intent.
Robust loss minimization is an important strategy for handling robust learning issue on noisy labels. Current robust loss functions, however, inevitably involve hyperparameter(s) to be tuned, manually or heuristically through cross validation, which makes them fairly hard to be generally applied in practice. Besides, t…
We present Manifold Alignment Determination (MAD), an algorithm for learning alignments between data points from multiple views or modalities. The approach is capable of learning correspondences between views as well as correspondences between individual data-points. The proposed method requires only a few aligned exam…
We present a comprehensive study on the use of autoencoders for modelling text data, in which (differently from previous studies) we focus our attention on the following issues: i) we explore the suitability of two different models bDA and rsDA for constructing deep autoencoders for text data at the sentence level; ii)…
Neuromorphic column performs online unsupervised clustering.
As research into community finding in social networks progresses, there is a need for algorithms capable of detecting overlapping community structure. Many algorithms have been proposed in recent years that are capable of assigning each node to more than a single community. The performance of these algorithms tends to …
We evaluate the distribution learning capabilities of generative adversarial networks by testing them on synthetic datasets. The datasets include common distributions of points in space and images containing polygons of various shapes and sizes. We find that by and large GANs fail to faithfully recreate point dat…
Recursive KalmanNet generalizes well in noisy, out-of-distribution scenarios.
Research into automated systems for detecting and classifying marine mammals in acoustic recordings is expanding internationally due to the necessity to analyze large collections of data for conservation purposes. In this work, we present a Convolutional Neural Network that is capable of classifying the vocalizations o…
Proposes a framework to identify and correct model-form errors in nonlinear systems.
The Interaction-Transformation (IT) is a new representation for Symbolic Regression that restricts the search space into simpler, but expressive, function forms. This representation has the advantage of creating a smoother search space unlike the space generated by Expression Trees, the common representation used in Ge…
Wind energy forecasting helps to manage power production, and hence, reduces energy cost. Deep Neural Networks (DNN) mimics hierarchical learning in the human brain and thus possesses hierarchical, distributed, and multi-task learning capabilities. Based on aforementioned characteristics, we report Deep Belief Network …
Transformers learn to play games in-context, proving Nash equilibrium.