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.

168,982 papers · 148 categories

Trend · papers per month

81161242322 · Jun 202019922001200920172026
48 results for target contexts

TL-ANDI distills context from source data to improve transfer learning for TFMs.

problem Limited transfer learning due to context-size constraints and distribution shifts.
method TL-ANDI uses posterior-aware distillation to construct a compact source context and locally distills labels.
result Improves transfer performance by addressing context-size and distribution shifts.

Scarce data is a major challenge to scaling robot learning to truly complex tasks, as we need to generalize locally learned policies over different "contexts". Bayesian optimization approaches to contextual policy search (CPS) offer data-efficient policy learning that generalize over a context space. We propose to impr…

2016-12-06abs ↗pdf ↗

Transformers learn low-dimensional target functions efficiently in-context.

problem Efficiently learning nonlinear target functions in-context using transformers.
method Nonlinear MLP layer in transformers optimized by gradient descent, focusing on single-index target functions.
result Transformers can learn target functions with low-dimensional structures efficiently in-context.

Mamba efficiently learns low-dimensional targets in-context via feature extraction.

problem Learning low-dimensional targets in context for computational efficiency.
method Test-time feature learning of a single-index model using Mamba's pretrained linear-time sequence model.
result Mamba achieves efficient in-context learning of low-dimensional targets via feature extraction.

Improved LID for multilingual speakers using context-aware models.

problem Low accuracy for languages spoken by multilingual speakers, especially with accented speech.
method Coarser-grained acoustic model and integration with interaction context signals.
result Average 97% accuracy across all language combinations, 60% improvement in worst-case accuracy.

Improves sample efficiency in reinforcement learning by controlling task distribution.

problem Learning and generalization of behaviors across related tasks in intelligent robots.
method Introduces a novel relative entropy reinforcement learning algorithm that allows the agent to control the intermediate task distribution.
result The proposed curriculum learning scheme drastically improves sample efficiency and enables learning in challenging scenarios.

ContextBench benchmarks methods for generating linguistically fluent inputs that activate specific latent features in language models.

problem Identifying inputs that trigger specific behaviours or latent features in language models.
method Context modification and benchmarking methods like Evolutionary Prompt Optimisation (EPO) with LLM-assistance and diffusion model inpainting.
result Enhanced methods achieve state-of-the-art performance in balancing elicitation effectiveness and fluency.

Transformers can approximate posterior predictive distributions through in-context learning.

problem Bayesian prediction tasks, especially beyond point predictions.
method Gradient descent algorithm targeting posterior predictive mean and variance, followed by nonlinear mappings.
result Transformers can implement algorithms to approximate posterior predictive distributions.

LangDA improves domain adaptation for semantic segmentation by learning context-aware scene descriptions.

problem Improving domain adaptation for semantic segmentation with dense prediction tasks.
method LangDA learns contextual relationships between objects via VLM-generated scene descriptions and aligns image features with text representation.
result LangDA sets new state-of-the-art across three DASS benchmarks, outperforming existing methods.

Efficiently combines autoregressive and set-based models for joint distributions.

problem Joint distributions over multiple predictions from set-based models.
method Causal autoregressive buffer that caches context and captures dependencies.
result Up to 20x faster joint sampling and density evaluation, up to 7x lower memory usage.

JoLT uses LLMs to make probabilistic predictions on tabular data.

problem Making probabilistic predictions on tabular data efficiently and without preprocessing.
method JoLT leverages LLMs' in-context learning to define joint distributions over tabular data.
result JoLT outperforms other methods on tabular classification and regression tasks.

Out-of-vocabulary word translation is a major problem for the translation of low-resource languages that suffer from a lack of parallel training data. This paper evaluates the contributions of target-language context models towards the translation of OOV words, specifically in those cases where OOV translations are der…

2018-01-26abs ↗pdf ↗

Improves NMT by sampling context from predicted sequence during training.

problem Error accumulation and overcorrection in NMT due to mismatched training and inference contexts.
method Samples context words from both ground truth and predicted sequences during training.
result Significant improvements on multiple datasets, including Chinese->English and WMT'14 English->German.

The paper uncovers symmetries in large language models through layer-peeled optimization.

problem Understanding geometric structure in large language model weights and context embeddings.
method Constrained layer-peeled optimization program to analyze symmetries in next-token distributions.
result Symmetries in target next-token distributions are transferred to optimal model weights and context embeddings.

This research improves online learning by correcting for target shift in machine learning.

problem Online learning struggles with distributional shift, especially in target values.
method Derives closed-form expressions for online and offline learning, and target correction.
result Online kernel-based learning can learn the same predictor as offline learning with target correction.

Build accurate DNN models requires training on large labeled, context specific datasets, especially those matching the target scenario. We believe advances in wireless localization, working in unison with cameras, can produce automated annotation of targets on images and videos captured in the wild. Using pedestrian an…

2018-09-22abs ↗pdf ↗

Fine-tuning harms in-context learning, but restricting updates to the value matrix improves zero-shot performance.

problem Fine-tuning harms in-context learning, reducing zero-shot performance on unseen tasks.
method Theoretical analysis of linear attention models, identifying conditions for degraded few-shot performance.
result Restricting updates to the value matrix improves zero-shot performance while preserving in-context learning.

Bayesian methods detect significant IIA violations in similarity choice data.

problem Detecting IIA violations in similarity choice data complicates classical models.
method Proposed two statistical methods: classical goodness-of-fit test and Bayesian PPC.
result Significant IIA violations confirmed in both datasets, driven by context effects.

We introduce a new representation learning algorithm suited to the context of domain adaptation, in which data at training and test time come from similar but different distributions. Our algorithm is directly inspired by theory on domain adaptation suggesting that, for effective domain transfer to be achieved, predict…

2014-12-15abs ↗pdf ↗

BiHermitian geometry, discovered long ago by Gates, Hull and Rocek, is the most general sigma model target space geometry allowing for (2,2) world sheet supersymmetry. In this paper, we work out supersymmetric quantum mechanics for a biHermitian target space. We display the full supersymmetry of the model and illustrat…

2006-11-28abs ↗pdf ↗

Active testing for large language models is made more efficient and accurate.

problem Efficient evaluation of large language models with limited labels.
method Cost-saving measures and in-context learning for constructing a surrogate model.
result Significantly more accurate evaluations of LLM performance compared to random data acquisition.

New split rules improve subpopulation targeting in policy-making.

problem Improving binary classification for subpopulation targeting in policy-making.
method MDFS, PFS, wEFS for maximizing distance and penalizing final splits.
result Proposed methods target more vulnerable subpopulations than classic CART/KD-CART.

We compress large neural networks for quick adaptation to specific contexts.

problem How to quickly adapt a pretrained large neural network to specific contexts.
method Propose a Bayesian hypernetwork framework to compress the network and encourage sparsity.
result Generated compressed networks are significantly smaller than baseline methods.

One way to solve lasso problems when the dictionary does not fit into available memory is to first screen the dictionary to remove unneeded features. Prior research has shown that sequential screening methods offer the greatest promise in this endeavor. Most existing work on sequential screening targets the context of …

2016-08-21abs ↗pdf ↗

A Kernel Adaptive Metropolis-Hastings algorithm is introduced, for the purpose of sampling from a target distribution with strongly nonlinear support. The algorithm embeds the trajectory of the Markov chain into a reproducing kernel Hilbert space (RKHS), such that the feature space covariance of the samples informs the…

2013-07-19abs ↗pdf ↗

Develops a universal waveform selection scheme for radar tracking.

problem Optimal waveform selection for target tracking in active sensors.
method Uses reinforcement learning and universal source coding techniques.
result Achieves optimal waveform selection for any radar scene modeled as a Markov process.

Study shows targeting students with intermediate predicted outcomes is most effective for financial aid renewal.

problem Determining which students to target for financial aid renewal to maximize effectiveness.
method Used causal forest to estimate heterogeneous treatment effects and targeted students accordingly; compared targeting low vs high predicted probability outcomes.
result Targeting students with intermediate predicted outcomes yields the highest effectiveness in financial aid renewal.

Meta-learning approach improves CNN architectures for concrete defect classification.

problem Challenging task of recognizing defects in concrete infrastructure.
method Two reinforcement learning based meta-learning approaches (MetaQNN and NAS) for finding suitable CNN architectures.
result Learned architectures have fewer parameters and better multi-target accuracy.

The paper shows how ignoring temporal context in recommender systems evaluation leads to false confidence, proposing a method to embed temporal context.

problem The discrepancy between offline and online recommender system performance evaluation.
method Proposes a training procedure to embed temporal context into recommender systems and validates its advantage using multi-objective optimization.
result Including temporal context in recommender systems evaluation can improve recall@20 by up to 20%.

Transformers enable in-context learning with guarantees for a wide range of tasks.

problem How to enable in-context learning with transformers for various tasks.
method Developed a universal approximation theory integrating Barron's function approximation with transformer capabilities.
result Transformers can approximate any target function with vanishingly small risk using a few in-context examples.