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.

168,742 papers · 148 categories

Trend · papers per month

4896144192 · Jun 202019922001200920172026
48 results for supervised finetuning

Vanishing gradients hinder reinforcement finetuning of language models.

problem Vanishing gradients impede the optimization of language models using reinforcement finetuning.
method The study identifies vanishing gradients as a fundamental optimization obstacle in reinforcement finetuning and proposes an initial supervised finetuning phase to mitigate this issue.
result An initial supervised finetuning phase is crucial for successful reinforcement finetuning of language models, as it helps prevent vanishing gradients and maximizes rewards.

Self-supervised learning improves ECG classification performance.

problem Label scarcity in clinical 12-lead ECG data.
method Adapted self-supervised methods to ECG domain, focusing on contrastive representations and latent forecasting.
result Contrastive predictive coding adaptation yields linear evaluation performance only 0.5% below supervised performance.

Study shows pretraining and finetuning can effectively tackle covariate shift in linear regression.

problem Linear regression under covariate shift where source and target distributions differ but conditional distribution remains similar.
method Pretraining on source data and finetuning on target data using online SGD.
result Transfer learning with O(N2)O(N^2) source data is as effective as supervised learning with NN target data.

Simplifies transfer learning with deep neural networks using ridge regression.

problem High computational cost of finetuning deep models for transfer learning.
method Leverage the low-rank property of deep neural networks' feature vectors in kernel ridge regression.
result Successful on supervised and semi-supervised transfer learning tasks.

Study improves cryptocurrency price prediction using unlabeled text data.

problem Predicting cryptocurrency returns from unlabelled text data.
method Introduced weak learning approach to finetune BERT on unlabeled text data.
result Finetuning pretrained NLP models with weak labels enhances forecast accuracy.

CERT improves language understanding by contrastively learning sentence-level semantics.

problem Lack of sentence-level semantics in existing pretraining tasks.
method Contrastive self-supervised learning at the sentence level using back-translation augmentations.
result CERT outperforms BERT on 7 out of 11 GLUE benchmark tasks, achieving the same performance as BERT on 2 tasks.

Deep model learns from labeled and unlabeled data for industrial soft sensing.

problem Lack of data limits soft sensor development in industrial processes.
method Hierarchical, generative deep latent variable model for semi-supervised multi-unit soft sensing.
result Model outperforms current methods for soft sensing in industrial processes.

This dissertation automates deep learning pipelines and uses meta-learning for better model selection and data augmentation.

problem Challenges in selecting and fine-tuning deep learning pipelines for new datasets.
method Meta-learning for DL pipeline selection and data augmentation, using synthetic data.
result Meta-learned approaches outperform traditional methods in automated DL pipeline selection and data augmentation.

Unified finetuning of all quantization degrees of freedom achieves state-of-the-art 4-bit quantization.

problem Achieving high accuracy in quantized neural networks while maintaining speed and resource constraints.
method Quantization-aware finetuning (QFT) that jointly optimizes all quantization degrees of freedom.
result 4-bit weight quantization results on-par with state-of-the-art (SoTA) within PTQ constraints.

LoRAs enable efficient adaptation of large models; this paper explores processing LoRA weights with machine learning.

problem Efficient processing of low-rank weight decompositions in large finetuned models.
method Developed symmetry-aware invariant and equivariant LoL models to process LoRA weights.
result LoL models can predict CLIP scores, finetuning data attributes, and accuracy on downstream tasks.

Pretraining models improves text classification accuracy, but diminishing returns are observed with large datasets.

problem Improving text classification accuracy with pretrained models.
method Examined the benefits of pretrained models on text classification tasks with varying amounts of training data.
result As the number of training examples grows into the millions, the accuracy gap between pretrained BERT-based models and vanilla LSTM narrows to within 1%.

This paper bridges offline and online RL by studying policy finetuning with a reference policy.

problem Sample-efficient reinforcement learning in online and offline settings.
method Design of policy finetuning algorithms and analysis of sample complexity.
result Theoretical analysis shows that the optimal policy finetuning algorithm is either offline reduction or purely online RL.

Ensembled neural networks improve MRI image quality.

problem Accelerated parallel MR imaging with high SSIM scores.
method Ensembled ΣΣ-net combining parallel coil and sensitivity networks, trained with supervised and semi-supervised methods.
result Ensembling models achieves visually sharp and textured images with robust SSIM scores.

New framework reduces LLM complexity by directly finetuning in Boolean domain.

problem Reducing the complexity of large language models (LLMs) while maintaining performance.
method Proposes a novel framework using multi-kernel Boolean parameters for direct finetuning in the Boolean domain.
result Significantly reduces complexity during both finetuning and inference, outperforming recent techniques.

BERT model improves cross-lingual document retrieval.

problem Improving cross-lingual information retrieval between English queries and foreign documents.
method Introduced a deep relevance matching model based on BERT, trained with weak supervision using CLIR data.
result Model outperforms competitive baseline approaches in retrieving Lithuanian documents against short English queries.

Meta-learning techniques like MAML and Reptile fail to generalize well to out-of-distribution tasks compared to simple finetuning.

problem Generalization of meta-learning techniques in low-data scenarios.
method Investigation of MAML, Reptile, and finetuning on various tasks.
result MAML and Reptile specialize for fast adaptation but fail to generalize to out-of-distribution tasks.

Two CSSL-based methods improve graph classification with limited labeled data.

problem Limited labeled data for graph classification leads to overfitting.
method Contrastive self-supervised learning (CSSL) for graph encoders pretraining and regularization.
result CSSL methods reduce overfitting and improve graph classification accuracy.

ConMeZO speeds up zeroth-order optimization for large language models.

problem Slow convergence in high-dimensional parameter spaces of large language models.
method Adaptive directional sampling in a cone centered around a momentum estimate.
result Achieves the same convergence rate as MeZO but up to 2X faster.

Vision transformers benefit from non-smooth components in adaptation.

problem Understanding the role of non-smoothness in vision transformer adaptation.
method Theoretical analysis and extensive experiments on large-scale vision transformers.
result High plasticity of attention modules and feedforward layers leads to better finetuning performance.

Paper introduces RiskEmbed, a finetuned model for financial risk management.

problem Improving retrieval accuracy in financial question-answering systems.
method Curated dataset and finetuned BERT model for financial domain.
result RiskEmbed significantly outperforms general-purpose and financial embedding models.

BioFinBERT analyzes sentiment of biotech press releases and financial text around inflection points.

problem Analyzing sentiment of biotech press releases and financial text around inflection points.
method Finetuning BioBERT on financial datasets to create BioFinBERT for sentiment analysis.
result BioFinBERT accurately analyzes sentiment of biotech press releases and financial text around inflection points.

Physen-Noise2Noise tackles defocus deblurring in low-light conditions with physics-guided self-supervised learning.

problem Defocus deblurring in low-light conditions with complex biased noise.
method Physics-guided self-supervised deblurring framework that leverages noisy multi-frame observations and a learnable noise bias parameter.
result Physen-Noise2Noise consistently outperforms state-of-the-art methods in defocus deblurring with complex biased noise.

WebGUM learns web navigation from multimodal data, outperforming previous methods.

problem Limited generalization from domain-specific models in web navigation.
method Instruction-following multimodal agent trained on vision-language foundation models.
result Significant improvement in web navigation performance on benchmarks.

Improves retrieval accuracy for hierarchical documents, especially for distant matches.

problem Limited expressive power of dual encoder models in hierarchical retrieval.
method Proves feasibility of DEs for HR, introduces pretrain-finetune recipe to improve long-distance retrieval.
result Pretrain-finetune boosts recall on long-distance pairs from 19% to 76%.

Semi-supervised learning lately has shown much promise in improving deep learning models when labeled data is scarce. Common among recent approaches is the use of consistency training on a large amount of unlabeled data to constrain model predictions to be invariant to input noise. In this work, we present a new perspe…

2019-04-29abs ↗pdf ↗

Qwen3-8B outperforms classical models in financial text classification.

problem Financial text classification for trading systems and sentiment analysis.
method Noisy Embedding Instruction Finetuning and Rank-stabilized Low-Rank Adaptation.
result Qwen3-8B achieves better classification accuracy and fewer training epochs.

INFUSER improves reasoning by self-evolving with a generator and solver that co-learn from unstructured documents.

problem Improving reasoning through self-evolution
method INFUSER uses a generator and solver co-evolving in a document pool to improve reasoning.
result INFUSER outperforms strong self-evolution baselines on Olympiad and SuperGPQA benchmarks.

G1 uses RL to enhance LLMs' graph reasoning, improving performance on diverse tasks.

problem Limited graph reasoning abilities of LLMs, especially in synthetic graph-theoretic tasks.
method Curated synthetic graph dataset, RL training on LLMs.
result Significant improvements in graph reasoning, zero-shot generalization to unseen tasks.

We introduce a pretraining technique called Selfie, which stands for SELFie supervised Image Embedding. Selfie generalizes the concept of masked language modeling of BERT (Devlin et al., 2019) to continuous data, such as images, by making use of the Contrastive Predictive Coding loss (Oord et al., 2018). Given masked-o…

2019-06-07abs ↗pdf ↗

MPP trains a transformer to predict multiple physical systems, improving accuracy across various tasks.

problem Training models for specific physical systems is inefficient and requires fine-tuning.
method MPP trains a shared transformer on multiple heterogeneous physical systems, projecting fields into a shared embedding space.
result A single MPP-pretrained transformer outperforms task-specific models on all pretraining sub-tasks and downstream tasks.

Proposes a new algorithm for efficient online model selection of LLMs considering the increasing-then-converging trend.

problem Balancing cost and performance in choosing the best LLM among a diverse set of models.
method Introduces a time-increasing bandit algorithm (TI-UCB) that predicts model performance increases and balances exploration and exploitation.
result Achieves a logarithmic regret upper bound, indicating a fast convergence rate in model selection.

CFA improves model's ability to generalize across unseen domain-class combinations.

problem Challenges in real-world machine learning applications due to data distribution shifts and limited training data.
method Developed Compositional Feature Alignment (CFA) technique to improve CG ability of pretrained models.
result CFA outperforms common finetuning techniques in compositional generalization.