Research
On-device research index

arXiv research

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.

168,657 papers · 148 categories

Trend · papers per month

92183275366 · May 202619922001200920172026
48 results for Dynamic Alignment Units

Conformal Alignment ensures trustworthy outputs from foundation models.

problem Ensuring outputs from foundation models align with human values in high-stakes tasks.
method A framework that trains an alignment predictor using reference data to select trustworthy outputs.
result Conformal Alignment accurately identifies trustworthy outputs via lightweight training over moderate reference data.

Training data-driven approaches for complex industrial system health monitoring is challenging. When data on faulty conditions are rare or not available, the training has to be performed in a unsupervised manner. In addition, when the observation period, used for training, is kept short, to be able to monitor the syste…

2019-07-15abs ↗pdf ↗

Partial soft-matching distance improves neural representation comparison by allowing some neurons to remain unmatched.

problem Neural representations are noisy and contain outliers, making traditional matching methods unreliable.
method Extends soft-matching distance to a partial optimal transport setting, allowing some neurons to remain unmatched.
result Partial soft-matching provides robust correspondences that are more reliable under noise and outliers.

Proposes GDTW for aligning time series on different, incomparable spaces.

problem Dynamic time warping requires comparable spaces, but time series can live on different, incomparable spaces.
method Gromov dynamic time warping (GDTW) considers intra-relational geometry to avoid comparability requirements.
result Demonstrates effectiveness of GDTW in aligning, combining, and comparing time series on incomparable spaces.

We study the question of how to imitate tasks across domains with discrepancies such as embodiment, viewpoint, and dynamics mismatch. Many prior works require paired, aligned demonstrations and an additional RL step that requires environment interactions. However, paired, aligned demonstrations are seldom obtainable an…

2019-09-30abs ↗pdf ↗

The study explains how neural networks align their kernels to target functions during training.

problem Understanding how neural networks align their kernels to target functions during training.
method Theoretical analysis of kernel evolution in toy models and deep networks.
result Kernel alignment naturally emerges during training to accelerate convergence and improve generalization.

Geometric approach improves motion alignment accuracy and efficiency.

problem Temporal alignment of human motion data for various applications.
method Geometric point of view, principal fiber bundle, reparameterization invariant projection, dynamic programming, keyframe correspondences.
result Temporal alignment procedures are more accurate and computationally efficient.

ELS framework improves safety alignment by dynamically steering LLMs towards helpful responses.

problem Over-Refusal in Aligned Large Language Models
method Fine-tuning free framework using an Energy-Based Model (EBM) to dynamically steer LLMs during inference.
result Extensive experiments show a significant reduction in false refusals (from 57.3% to 82.6%) while maintaining safety performance.

Consider an imitation learning problem that the imitator and the expert have different dynamics models. Most of the current imitation learning methods fail because they focus on imitating actions. We propose a novel state alignment-based imitation learning method to train the imitator to follow the state sequences in e…

2019-11-21abs ↗pdf ↗

SGD updates align with a low-rank subspace but do not lead to further loss reduction.

problem Understanding the training dynamics of deep neural networks, particularly the role of the dominant subspace.
method Exploring whether neural networks can be trained within the dominant subspace of the loss Hessian.
result SGD updates, when projected onto the dominant subspace, do not decrease the training loss further, suggesting spurious alignment.

SGD's training dynamics align with Hessian and gradient spectra in high-dimensional classification tasks.

problem Understanding the spectra of Hessian and gradient matrices in high-dimensional classification tasks.
method Rigorous analysis of SGD dynamics and spectra of Hessian and gradient matrices.
result SGD trajectory and emergent outlier eigenspaces align with a common low-dimensional subspace in multi-class high-dimensional mixtures and neural networks.

Paper addresses reward hacking in preference optimization, proposing POWER-DL to improve AI alignment.

problem Reward hacking problem in preference optimization, leading to undesired behaviors.
method POWER-DL combines robust reward maximization and dynamic label updates to mitigate reward hacking.
result POWER-DL consistently outperforms state-of-the-art methods on alignment benchmarks.

Many natural systems, such as neurons firing in the brain or basketball teams traversing a court, give rise to time series data with complex, nonlinear dynamics. We can gain insight into these systems by decomposing the data into segments that are each explained by simpler dynamic units. Building on switching linear dy…

2016-10-26abs ↗pdf ↗

Linear attention in Transformers can be interpreted as dynamic VAR models.

problem Misalignment between Transformers and autoregressive forecasting objectives.
method Interpreting linear attention as VAR, rearranging MLP, attention, and flow.
result SAMoVAR improves performance, interpretability, and efficiency.

Although deep convolutional networks have achieved improved performance in many natural language tasks, they have been treated as black boxes because they are difficult to interpret. Especially, little is known about how they represent language in their intermediate layers. In an attempt to understand the representatio…

2019-02-18abs ↗pdf ↗

NTK-SAP improves neural network pruning by aligning training dynamics.

problem Improving neural network pruning to reduce training time and memory.
method Prune connections based on the spectrum of the Neural Tangent Kernel (NTK), using multiple random weight realizations and random inputs.
result Empirically, NTK-SAP achieves better performance than all baselines on multiple datasets.

Set-Sequence model learns cross-sectional dynamics directly from time series data.

problem Predicting large cross-sections of time series data with latent cross-sectional dynamics.
method A model that learns cross-sectional structure directly, enhancing expressivity and eliminating manual feature engineering.
result Significantly outperforms strong baselines in equity portfolio optimization and loan risk prediction.

We study alignment in linear neural networks and its relation to gradient descent.

problem Understanding alignment in linear neural networks and its impact on training.
method Defined alignment for fully connected networks, analyzed alignment under gradient descent, and compared gradient descent to projected gradient descent for layer-constrained networks.
result Gradient descent can converge linearly to a global minimum when alignment is invariant, and alignment is impossible with large datasets in layer-constrained networks.

The paper solves a new Minkowski problem involving convex bodies and curvature measures.

problem Finding convex bodies with specific curvature measures.
method Solving Monge-Ampère type equations using variational and Gaussian curvature flow methods.
result Existence and uniqueness of solutions for the LpL_p-Gauss dual Minkowski problem.

SONA improves conditional generation by balancing authenticity and alignment.

problem Challenges in balancing authenticity and conditional alignment in conditional generative models.
method SONA integrates unconditional discrimination, matching-aware supervision, and adaptive weighting to balance authenticity and alignment.
result SONA achieves superior sample quality and conditional alignment compared to state-of-the-art methods.

Language evolves over time in many ways relevant to natural language processing tasks. For example, recent occurrences of tokens 'BERT' and 'ELMO' in publications refer to neural network architectures rather than persons. This type of temporal signal is typically overlooked, but is important if one aims to deploy a mac…

2019-09-08abs ↗pdf ↗

Enhances thematic investing with stock embeddings from textual data.

problem Challenges in constructing thematic portfolios due to overlapping sector boundaries and evolving market dynamics.
method Introduces THEME, a framework that fine-tunes embeddings using hierarchical contrastive learning, aligning themes and stocks using their hierarchical relationship and incorporating stock returns.
result Theme-aligned portfolios demonstrate compelling performance, significantly outperforming large language models in thematic asset retrieval.

Early alignment in neural networks leads to sparse representations but hinders convergence.

problem The implicit bias of gradient descent during early training phases.
method Quantitative description of early alignment phase in small initialisation, one hidden layer networks.
result Early alignment induces a sparse representation but also hinders convergence to global minima.

New framework for estimating treatment effects in experiments with network interference.

problem Network interference biases traditional treatment effect estimations in randomized experiments.
method Causal message-passing framework based on high-dimensional approximate message passing.
result Practical algorithm to estimate total treatment effect in multi-period experiments.

GrokAlign aligns Jacobians to accelerate grokking in deep networks.

problem Accelerating the training dynamics of deep networks to avoid delayed generalisation and robustness.
method Aligning the Jacobians of a deep network with the training data to ensure grokking under a low-rank assumption.
result GrokAlign regularizes Jacobians to induce grokking sooner than conventional methods.

Analyzes learning dynamics of RNNs under locality constraints.

problem Understanding learning dynamics in RNNs with locality constraints.
method Dynamical systems theory applied to data-aligned linear RNNs.
result RFLO solutions are restricted to low-rank perturbations of initial parameters.

DPA aligns LLMs with multi-objective rewards for diverse user preferences.

problem Fine-grained control over LLMs for diverse user needs.
method Integrates multi-objective reward modeling and directional preference control.
result DPA offers better performance trade-offs and intuitive user control over LLM generation.

Graph alignment problem solved with convex relaxations for correlated matrices.

problem Recovering hidden vertex permutations from correlated Gaussian matrices.
method Convex relaxations of the quadratic assignment problem over doubly stochastic matrices.
result The solution of the convex relaxation concentrates around the ground-truth permutation matrix for certain correlation parameters.