This research compares masked diffusion models to autoregressive language models, focusing on architectural differences.
problem Comparing masked diffusion models to autoregressive language models due to architectural differences.
method Equitably compare MDMs within a decoder-only framework, investigating architectural influences.
result Decoder-only MDMs can achieve significant speedups and comparable perplexity with temperature annealing.
The paper defines and analyzes quandles of knotoids and linkoids.
problem Tackling the invariant properties of knotoids and linkoids.
method Defining fundamental quandles and pointed quandles, proving invariance, and introducing new invariants.
result Fundamental pointed quandles enhance the fundamental quandle and distinguish 1-linkoids.
Paper uses news data to model asset correlations without market data.
problem Traditional risk models rely on market data; this paper offers an alternative.
method Uses encoder-only language models to embed news data, then calculates asset return distributions and covariance through Energy Distance.
result Established connections between distributional differences and excess returns co-movements using Energy Distance.
The paper analyzes the dynamics of tokens in transformer models at moderate interaction levels.
problem Understanding the evolution of tokens in transformer models at moderate interaction levels.
method Modeling transformer models as a system of particles interacting in a mean-field way and studying the corresponding dynamics.
result Characterization and convergence of the limiting dynamics in different phases of the system.
Method learns representations invariant to task-irrelevant details in reinforcement learning tasks.
problem Learning representations that are invariant to task-irrelevant details in reinforcement learning.
method Uses bisimulation metrics to learn robust latent representations that encode only task-relevant information.
result Demonstrates SOTA performance in modified visual MuJoCo tasks and a first-person driving task.
Paper proposes active learning for mining conflict dynamics from textual data.
problem Lack of detailed information on conflict dynamics in existing datasets.
method Active learning with a large, encoder-only language model.
result Performance similar to human coding with reduced human annotation.
New method identifies physical constants from video data alone.
problem Identifying physical constants from video data.
method Proves level-set slope-coverage condition ensures local affine mapping to true physical state, enabling exact parameter recovery.
result Underdamped systems identifiable from a single video clip, other regimes require three diverse trajectories.
EbC learns equivariant embeddings from unlabeled group actions.
problem Learning equivariant embeddings from unlabeled group actions.
method Equivariance by Contrast (EbC) method to learn equivariant embeddings from observation pairs (y,g⋅y). result High-fidelity equivariance in latent space for diverse groups.
Determinantal point processes (DPPs) have attracted substantial attention as an elegant probabilistic model that captures the balance between quality and diversity within sets. DPPs are conventionally parameterized by a positive semi-definite kernel matrix, and this symmetric kernel encodes only repulsive interactions …
Event-based cameras are bio-inspired novel sensors that asynchronously record changes in illumination in the form of events, thus resulting in significant advantages over conventional cameras in terms of low power utilization, high dynamic range, and no motion blur. Moreover, such cameras, by design, encode only the re…
VDA improves disentanglement of latent representations in complex signals.
problem Learning disentangled and interpretable representations in nonstationary, high-dimensional time-evolving signals.
method Variational decomposition autoencoding (VDA) framework, incorporating signal decomposition, contrastive self-supervised task, and variational prior approximation.
result DecVAEs surpass state-of-the-art VAE-based methods in disentanglement quality and generalization.
This paper fine-tunes LLMs for stock return prediction using financial news.
problem Improving stock return forecasting accuracy using LLMs.
method Fine-tuning LLMs with text and forecasting modules, comparing encoder-only and decoder-only models, and integrating token-level representations.
result LLMs' aggregated token-level embeddings enhance return predictions for long-only and long-short portfolios.
Conditional generative models have achieved considerable success in the past few years, but usually require a lot of labeled data. Recently, ClusterGAN combines GAN with an encoder to achieve remarkable clustering performance via unsupervised conditional generation. However, it ignores the real conditional distribution…
VAE with noise model learns smoothed densities without seeing noisy data.
problem Learning smoothed densities with noisy data.
method Imaginary noise model in variational autoencoders (σ-VAE).
result All σ-VAEs are equivalent via β-VAE expansion.
A method to approximate causal models using information theory.
problem Inferring causal direction and effect between discrete variables.
method Embedding distributions into a higher dimensional space and solving a linear optimization problem.
result Information-theoretic approximation (IACM) can be used for causal discovery in bivariate, discrete cases.
The cumulative distribution network (CDN) is a recently developed class of probabilistic graphical models (PGMs) permitting a copula factorization, in which the CDF, rather than the density, is factored. Despite there being much recent interest within the machine learning community about copula representations, there h…
Paper proposes SERT model for US stock pricing, outperforming standard models during market shocks.
problem Capturing patterns of temporal sparsity in asset pricing during market fluctuations.
method Introduces SERT model based on pre-trained Transformer, compares with standard models in three periods.
result SERT model achieves highest out-of-sample R2 (11.94\% and 11.47\%) during extreme market fluctuations. Language models fail to process hallucinated responses, and this study diagnoses the failure.
problem Language models fail to process hallucinated responses, leading to over-concentration or diffuse attention.
method The study uses forced scoring of benchmark-labeled responses to compute attention shapes and analyze the symmetric component of the degree-normalized attention operator.
result The study proves that every transpose-invariant spectral diagnostic of the attention operator is orientation-blind and bounds the sensitivity of any Lipschitz diagnostic by the asymmetry coefficient \(G\).