New method aligns states for better imitation learning.
problem Different dynamics models between imitator and expert.
method State alignment-based reinforcement learning.
result Superior performance on various imitation learning settings.
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.
168,742 papers · 148 categories
Trend · papers per month
48 results for “state alignment”
Survey of alignment techniques for large language models.
problem Ensuring large language models align with human values.
method Analysis of diverse alignment methods and training paradigms.
result Preference-based methods offer more flexibility for nuanced alignment.
Pair Hidden Markov Models (PHMMs) are probabilistic models used for pairwise sequence alignment, a quintessential problem in bioinformatics. PHMMs include three types of hidden states: match, insertion and deletion. Most previous studies have used one or two hidden states for each PHMM state type. However, few studies …
SHA improves fMRI alignment for cognitive state discovery.
problem Optimal functional alignment in MVP analysis for multi-subject fMRI data.
method Supervised Hyperalignment (SHA) method that maximizes correlation within same categories and minimizes between distinct categories.
result SHA achieves up to 19% better performance for multi-class problems.
Since the early days of digital communication, Hidden Markov Models (HMMs) have now been routinely used in speech recognition, processing of natural languages, images, and in bioinformatics. An HMM assumes observations to be conditionally independent given an "explanotary" Markov proc…
Bayesian HMM for protein alignment state estimation.
problem Estimating the MAP state sequence for a Bayesian HMM.
method Training data with Dirichlet priors, iterative algorithms for MAP path estimation.
result Bayesian setup outperforms frequentist estimation in protein alignment.
New statistical model improves protein alignment accuracy.
problem Improving accuracy in protein sequence alignment.
method Inferred a time-dependent Markov process from protein sequences.
result Developed a new optimal matrix (MMLSUM) for protein alignment.
Study improves stock return prediction by switching between economic states, outperforming traditional methods.
problem Improving stock return prediction across economic regimes.
method State-switching specification using the slope of the yield curve, with an Aligned Economic Index.
result The Aligned Economic Index outperforms traditional predictors, especially during market turbulence.
Improved text-to-image alignment using iterative VQA feedback.
problem Misalignment between text prompts and generated images, especially for complex inputs.
method Decompose complex prompts into assertions, evaluate each using VQA, combine scores iteratively.
result Significantly higher correlation with human ratings compared to CLIP, BLIP scores.
Graph-Relational Domain Adaptation (GRDA) adapts domains based on their graph structure.
problem Uniform alignment of domains ignores topological structures.
method Uses a domain graph to encode adjacency and a novel graph discriminator.
result Empirically shows improved generalization and domain information incorporation.
Hölder-DPO aligns models robustly with noisy human feedback.
problem No existing alignment methods can handle severe label noise.
method Proposes Hölder-DPO, a principled alignment loss with provable redescending property.
result Hölder-DPO enables scalable human feedback valuation and improves model alignment.
Study shows time-varying stock returns across economic states.
problem Equity premium predictability varies by economic state.
method State-switching predictive regression using yield curve slope.
result The Aligned Economic Index improves stock return prediction.
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.
Paper presents a method to align unpaired samples across different modalities.
problem Challenges in collecting paired samples for multimodal representation learning.
method Uses propensity score alignment based on Rubin's framework to estimate a common space for unpaired samples.
result Optimal transport matching significantly improves alignment in real-world data.
Deep neural networks, trained with large amount of labeled data, can fail to generalize well when tested with examples from a \emph{target domain} whose distribution differs from the training data distribution, referred as the \emph{source domain}. It can be expensive or even infeasible to obtain required amount of lab…
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…
SAIL improves online alignment of large language models with minimal feedback.
problem Offline RLHF methods often lead to sub-optimal performance due to fixed preference datasets.
method SAIL uses bilevel optimization and a single-level first-order method to iteratively refine model alignment.
result SAIL significantly improves alignment performance on open-sourced datasets with minimal computational overhead.
MALI aligns distinct domains using labeled data.
problem Aligning multi-domain data for machine learning.
method MALI learns manifold structure via diffusion and uses labeled data to guide alignment.
result MALI outperforms state-of-the-art methods across multiple datasets.
The infinite Viterbi alignment is the limiting maximum a-posteriori estimate of the unobserved path in a hidden Markov model as the length of the time horizon grows. For models on state-space satisfying a new ``decay-convexity'' condition, we develop an approach to existence of the infinite Viterbi ali…
Network alignment is a critical task to a wide variety of fields. Many existing works leverage on representation learning to accomplish this task without eliminating domain representation bias induced by domain-dependent features, which yield inferior alignment performance. This paper proposes a unified deep architectu…
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.
Geometric approach for unsupervised word embedding alignment.
problem Learning alignment between word embeddings of source and target languages.
method Formulates alignment as domain adaptation on the manifold of doubly stochastic matrices, employing Riemannian conjugate gradient algorithm.
result Empirically outperforms state-of-the-art methods on bilingual lexicon induction tasks.
New approach speeds up DNA sequence alignment.
problem Efficiently estimating alignment scores for large sets of reads.
method Rank-one crowdsourcing models and multi-armed bandit algorithm.
result Adaptive algorithm identifies pairs with large alignment scores.
Aligns attention distributions for improved accuracy and robustness.
problem Improving the accuracy and robustness of neural networks using attention mechanisms.
method Alignment attention that encourages key and query distributions to match within each head.
result Alignment attention leads to better accuracy, uncertainty estimation, and robustness across various tasks.
String similarity models are vital for record linkage, entity resolution, and search. In this work, we present STANCE --a learned model for computing the similarity of two strings. Our approach encodes the characters of each string, aligns the encodings using Sinkhorn Iteration (alignment is posed as an instance of opt…
Unsupervised domain adaptation aims to transfer and adapt knowledge learned from a labeled source domain to an unlabeled target domain. Key components of unsupervised domain adaptation include: (a) maximizing performance on the target, and (b) aligning the source and target domains. Traditionally, these tasks have eith…
DFA trains deep networks by aligning weights then memorizing data.
problem Understanding why DFA works for some networks but not others.
method Two-step learning process: alignment followed by memorization.
result DFA aligns weights to maximize gradient alignment, breaking degeneracy.
A new framework improves ASR alignment accuracy via optimal transport.
problem Peaky behavior and alignment inaccuracies in E2E ASR models.
method Differentiable alignment framework based on 1D optimal transport.
result Significant improvement in ASR alignment performance compared to CTC.
The classical isoperimetric inequality in the Euclidean plane states that for a simple closed curve of the length , enclosing a region of the area , one gets \begin{align*} L_{M}^2\geqslant 4πA_{M}. \end{align*} In this paper we present the improved isoperimetric inequality, which state…
AOT aligns LLMs on distributional preferences via optimal transport.
problem Current LLM alignment techniques lack distributional level alignment.
method Alignment via Optimal Transport (AOT) aligns LLMs on unpaired preference data.
result AOT enables alignment by penalizing reward distribution violations.
A new method for drone-based geo-localization using style and spatial alignment.
problem Geo-localization of drone-view images with satellite-view images using pre-annotated GPS tags.
method Orientation-based method to align patterns, new branch to extract aligned partial features, style alignment strategy.
result The proposed method outperforms state-of-the-art alternatives in geo-localization accuracy.
We introduce BilBOWA (Bilingual Bag-of-Words without Alignments), a simple and computationally-efficient model for learning bilingual distributed representations of words which can scale to large monolingual datasets and does not require word-aligned parallel training data. Instead it trains directly on monolingual dat…
Paper develops a new unsupervised scoring function for cross-lingual document alignment.
problem Aligning documents across different languages for NLP tasks.
method Uses cross-lingual sentence embeddings to compute semantic distances and guides document alignment.
result The proposed scoring function outperforms current methods by 7-22% on various language pairs.
We present a model that can automatically learn alignments between high-dimensional data in an unsupervised manner. Our proposed method casts alignment learning in a framework where both alignment and data are modelled simultaneously. Further, we automatically infer groupings of different types of sequences within the …
Improved algorithm for network alignment with binary diffing application.
problem Network alignment problem and binary diffing.
method Inspired by Bayati et al. [2], the algorithm uses message passing with modifications for speed and convergence.
result Our model outperforms state-of-the-art solvers in experiments.
A novel method for comparing graphs of different sizes using Wasserstein distance.
problem Comparing non-aligned graphs of varying sizes.
method Optimal transport in graph comparison framework, solving a one-to-many assignment problem.
result Significant improvements in graph alignment and classification tasks.
LLM trading agents show risk feedback can improve alignment without fine-tuning.
problem Aligning LLM trading agents with financial risk.
method TradeArena testbed, risk reports, execution simulation, memory replay.
result Risk feedback can improve alignment without fine-tuning, but not universally.
DHGAK aligns substructures for better graph kernel performance.
problem Limited performance of traditional graph kernels due to missing substructure similarities.
method Hierarchically aligns relational substructures in deep embedding space, assigning same feature maps in RKHS.
result DHGAK outperforms state-of-the-art graph kernels on various benchmarks.
Federated edge learning improves with CSIT-free model aggregation using RIS.
problem Lack of CSIT in federated edge learning systems.
method Use RIS to align channel coefficients for model aggregation without CSIT, optimize RIS and receiver jointly.
result Achieves similar learning accuracy as CSIT-based methods without CSIT.
Multivariate Pattern (MVP) classification can map different cognitive states to the brain tasks. One of the main challenges in MVP analysis is validating the generated results across subjects. However, analyzing multi-subject fMRI data requires accurate functional alignments between neuronal activities of different sub…
The paper improves alignment methods for deep neural networks using geometric and spectral analysis.
problem Improving alignment methods for deep neural networks.
method Geometric and spectral analysis of residual Jacobian chains.
result Deterministic and margin-verified results on the transport of dominant singular subspaces across layers.
Proposes using Wasserstein barycenter for better multilingual alignment.
problem Finding word-to-word translations between multiple languages without parallel data.
method Uses Wasserstein barycenter as a more informative pivot language, minimizing pairwise transportation costs.
result Demonstrates state-of-the-art performances on standard benchmarks.
Proposes a robust algorithm for aligning large language models with human preferences.
problem Misspecification in preference models, reference policies, and reward functions.
method Doubly robust preference optimization algorithm.
result Superior and more robust performance compared to state-of-the-art algorithms.
Phylogenetic tree reconstruction is traditionally based on multiple sequence alignments (MSAs) and heavily depends on the validity of this information bottleneck. With increasing sequence divergence, the quality of MSAs decays quickly. Alignment-free methods, on the other hand, are based on abstract string comparisons …
Objective: This paper targets a major challenge in developing practical EEG-based brain-computer interfaces (BCIs): how to cope with individual differences so that better learning performance can be obtained for a new subject, with minimum or even no subject-specific data? Methods: We propose a novel approach to align …
Proposes a method to align language and image data.
problem Aligning language and image data for better understanding.
method Uses triplet loss to learn consistent embeddings of language and images.
result Outperforms four baselines across multiple metrics.
MFMs enable efficient reward alignment for generative models.
problem Computational bottleneck in controlling generative models.
method Meta Flow Maps (MFMs) extend consistency models and flow maps to stochastic regime for efficient value function estimation.
result MFMs enable inference-time steering and unbiased, off-policy fine-tuning to general rewards efficiently.
Multi-subject fMRI data analysis is an interesting and challenging problem in human brain decoding studies. The inherent anatomical and functional variability across subjects make it necessary to do both anatomical and functional alignment before classification analysis. Besides, when it comes to big data, time complex…