Tabular in-context learners perform well on biomolecular tasks, but performance depends on the representation used.
problem Predicting biomolecular properties from limited labeled data.
method Evaluating tabular in-context learners on protein fitness regression and small-molecule classification tasks.
result Tabular in-context learners are competitive for protein fitness regression but not for small-molecule classification.
GAMformer bridges tabular models and interpretability, offering a single-pass approach.
problem Lack of interpretability in tabular foundation models like TabPFN.
method In-context learning for GAM shape functions, training on synthetic data.
result GAMformer performs comparably to other leading GAMs across various classification benchmarks.
TTT improves transformer models for in-context learning.
problem Improving transformer models for efficient in-context learning.
method Gradient-based TTT method for linear transformers, with theoretical and empirical analysis.
result TTT significantly reduces the sample size required for in-context learning.
Transformers fine-tuned on synthetic data boost tabular data classification performance.
problem Improving tabular data classification accuracy.
method Fine-tuning ICL-transformers on synthetic datasets with complex decision boundaries.
result Fine-tuned ICL-transformers outperform regular neural networks on real-world datasets.
TabPFN learns to approximate functions on tabular data.
problem TabPFN tackles function approximation on tabular data.
method Treated as a black-box function approximator generator, observed behavior on varied datasets.
result Observed behavior that is both brilliant and baffling.
Orion-Bix combines biaxial attention and meta-learning for tabular few-shot learning.
problem Scaling and generalizing tabular models with mixed numeric and categorical fields, weak feature structure, and limited labeled data.
method Orion-Bix uses biaxial attention and meta-learned in-context reasoning to efficiently capture local and global dependencies.
result Orion-Bix outperforms gradient-boosting baselines and state-of-the-art tabular models on public benchmarks.
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.
Improving in-context learning for latent space Bayesian optimization by adapting pretraining on molecular latent space.
problem Improving in-context learning for latent space Bayesian optimization.
method Adapting pretraining on molecular latent space.
result Achieving strong performance on held-out molecular optimization benchmarks.
TabPFN doesn't outperform GLM and XGBoost for motor insurance pricing.
problem Improving insurance pricing models using Tabular Foundation Models (TFMs).
method Pre-training on synthetic datasets and in-context learning for inference.
result TabPFN does not consistently outperform established baselines, has longer inference times, and is sensitive to training set size.
TabDPT combines ICL and self-supervised learning to train tabular models on real data.
problem Slow generalization of tabular foundation models to unseen datasets.
method In-Context Learning (ICL) combined with self-supervised learning, using real data for pre-training.
result TabDPT achieves strong performance on regression and classification benchmarks.
Transformers can implement reinforcement learning algorithms from data without updates.
problem Training reinforcement learning algorithms from data without parameter updates.
method Design a teacher-mimicking training procedure for transformers to implement policy-improvement methods.
result Gradient flow converges to an optimal parameter manifold corresponding to the desired RL update.
Drift-Resilient TabPFN learns to adapt to changing data distributions.
problem Real-world data often shifts over time, degrading model performance.
method In-Context Learning with a Prior-Data Fitted Network, using structural causal models.
result Significant performance improvements across various datasets.
TabPFN models achieve state-of-the-art performance on tabular data tasks.
problem Lack of interpretability in TabPFN models.
method Adaptations of interpretability methods specifically designed for TabPFN, leveraging in-context learning and LOCO.
result Improved interpretability of TabPFN models through efficient computations and scalable data valuation methods.
TabPFN model shows strong robustness to noisy data.
problem TabPFN tackles robustness to noisy and imperfect tabular data.
method Empirical robustness analysis of TabPFN's attention mechanisms under various perturbations.
result TabPFN maintains high predictive performance and coherent internal behavior under noisy and imperfect data.
In-context learning solves PU classification without iterative optimization.
problem Binary classification with only labeled positives and unlabeled samples.
method Pretrained transformer (PUICL) that learns from synthetic PU datasets.
result Outperforms four standard PU learning baselines on 20 benchmarks.
Pipeline combines ETF preprocessing with tabular model for cross-modal inference.
problem Transferability of tabular models across different modalities.
method Fixed comparison object, ETF preprocessing, in-context inference.
result Pipeline is broadly competitive, runs faster, and produces well-calibrated probabilities.
UnmaskingTrees improves tabular data imputation and generation using gradient-boosted decision trees.
problem Traditional methods outperform advanced deep learning techniques on tabular data imputation benchmarks.
method UnmaskingTrees employs gradient-boosted decision trees to incrementally unmask features for imputation and generation.
result UnmaskingTrees outperforms state-of-the-art methods on tabular imputation and generation benchmarks.
LLMs are vulnerable to task-irrelevant data changes, limiting their use for data fitting.
problem LLMs' sensitivity to task-irrelevant variations in data representation.
method Analysis of LLMs' performance and attention patterns under various data manipulations.
result LLMs are sensitive to task-irrelevant variations, leading to significant prediction errors.
TabPFN quickly classifies small tabular data without tuning.
problem Efficiently classifying small tabular datasets.
method Transformer-based model that learns in-context.
result Competitive performance with state-of-the-art methods.
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.
STOIC improves energy demand forecasting with reliable uncertainty estimates.
problem Accurate point forecasts alone are insufficient for energy systems; reliable uncertainty estimates are needed.
method Integrates graph-based forecasting with tabular foundation models for zero-shot calibration of spatial-temporal residuals.
result STOIC delivers more reliable and robust uncertainty estimates for complex graph-structured energy time series.
Transformers learn to make decisions in new contexts from offline data.
problem Understanding when and how transformers can perform in-context reinforcement learning.
method Theoretical framework analyzing supervised pretraining for ICRL, including algorithm distillation and decision-pretrained transformers.
result Transformers can efficiently approximate optimal reinforcement learning algorithms for various environments.
Foundation models leak sensitive data in synthetic tabular data generation, especially LLaMA 3.3 70B.
problem Privacy leakage in synthetic tabular data generation using foundation models.
method Benchmarked three foundation models (GPT-4o-mini, LLaMA 3.3 70B, TabPFN v2) against four baselines on 35 real-world tables.
result Foundation models, especially LLaMA 3.3 70B, have the highest privacy risk in synthetic tabular data generation.
Generative AI can solve in-context learning problems using a martingale perspective.
problem Estimating when a conditional generative model can solve an in-context learning problem.
method Bayesian interpretation, ancestral sampling, generative predictive p-value.
result Developed a method to assess the suitability of CGMs for ICL problems using generative predictive p-values.
Enhances neural processes to learn from multiple related datasets.
problem Improving predictions from datasets with shared similarities.
method Developed the in-context in-context learning pseudo-token TNP (ICICL-TNP) to condition on both sets of datapoints and sets of datasets.
result Demonstrated the importance and effectiveness of in-context in-context learning.
This work introduces a method to decompose uncertainty in in-context learning for large language models.
problem Understanding the sources of uncertainty in in-context learning for large language models.
method Variational uncertainty decomposition framework without sampling from latent parameter posterior.
result Quantitative and qualitative validation of decomposed epistemic and aleatoric uncertainties.
TabPFN's internal geometry topology correlates with dataset reliability.
problem Understanding TabPFN's behavior on structurally difficult tabular geometries.
method Using zigzag persistent homology, studying TabPFN's internal representations on synthetic tabular tasks with known topology.
result Topology of TabPFN's internal representation geometry is strongly associated with dataset-level reliability.
MLPs can approximate any function in context, challenging the importance of in-context universality.
problem Understanding why transformers are more effective than classical models.
method Proved MLPs with trainable activation functions are universal in context.
result Transformer success is likely due to factors other than in-context universality.
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.
Transformers show better in-context learning resilience under distribution shifts than simple MLPs.
problem Understanding in-context learning under varying distribution shifts.
method Comparing transformers and set-based MLPs on linear regression tasks.
result Transformers better emulate OLS performance and exhibit better resilience to mild distribution shifts.
LLMs learn probability density functions in-context, showing distinct learning trajectories.
problem Density estimation of time series data in LLMs.
method Intensive Principal Component Analysis (InPCA) to visualize and analyze LLMs' learning dynamics.
result LLMs follow similar learning trajectories in a low-dimensional InPCA space, distinct from traditional methods.
Transformers learn to play games in-context, proving Nash equilibrium.
problem Understanding in-context game-playing capabilities of pre-trained transformers.
method Theoretical guarantees and constructional results for transformer architecture in multi-agent games.
result Pre-trained transformers can learn Nash equilibrium in-context for two-player zero-sum games.
Transformers learn to perform logistic regression in-context.
problem Understanding how transformers learn to perform specific tasks in-context.
method Constructed multi-layer transformers that perform in-context logistic regression through normalized gradient descent.
result Transformers can be trained to perform in-context logistic regression effectively.
Adapts attention to supervised learning for personalized predictions.
problem Personalized predictions for each data point with model simplicity.
method Local model fitting with attention weighting for tabular data.
result Attention weighting improves predictive performance and preserves interpretability.
Continuum transformers learn operators in context via gradient descent.
problem Generalizing transformers to handle infinite-dimensional inputs for in-context learning.
method Gradient descent in an operator RKHS, leveraging generalized representer theorems and gradient flows.
result Operator learned in context is Bayes Optimal Predictor in infinite depth limit.
Transformers forecast time series in-context, improving efficiency and performance.
problem Overfitting and limited performance in time series forecasting.
method Reformulate time series forecasting as input tokens, aligning with in-context learning mechanisms.
result Consistently better performance across various settings (full-data, few-shot, zero-shot).
New method for uncertainty analysis in TabPFN, a state-of-the-art tabular transformer.
problem No method for uncertainty decomposition in TabPFN.
method Casted as a Bayesian predictive inference problem, derived variance estimators using predictive CLT.
result Fast to compute credible bands that target epistemic uncertainty and achieve near-nominal frequentist coverage.
Transformers can adaptively select and perform various machine learning tasks in context.
problem Transformers' ability to perform multiple machine learning tasks without explicit prompting.
method Statistical theory and efficient implementation of in-context gradient descent, enabling transformers to implement various algorithms and tasks.
result Transformers can implement a broad class of standard machine learning algorithms in context, including algorithm selection.
ICEE learns new RL tasks in less time with a Transformer model.
problem Efficient in-context policy learning for reinforcement learning.
method In-context Exploration-Exploitation (ICEE) algorithm that optimizes efficiency without explicit Bayesian inference.
result ICEE solves Bayesian optimization problems as efficiently as Gaussian process biased methods but in significantly less time.
New framework shows cross-attention improves multi-modal in-context learning.
problem Understanding multi-modal in-context learning in neural networks.
method Mathematical framework and linearized cross-attention mechanism.
result Cross-attention mechanism is provably optimal for multi-modal in-context learning.
New analysis shows transformer models can't learn effectively.
problem Transformer models learning in context can't achieve general predictive accuracy.
method Empirical evidence and mathematical analysis of transformer architecture limitations.
result Transformers cannot achieve general predictive accuracy due to architectural limitations.
New model uses attention for in-context learning of categorical data.
problem Learning from categorical data in context.
method Attention-based network with self-attention and cross-attention layers, using functional gradient descent.
result Model can perform multi-step inference for categorical observations.
Transformers learn new tasks from few examples via optimal approximation.
problem Learning new tasks from limited examples using large language models.
method Developed approximation and generalization error bounds for transformers trained on nonparametric regression tasks.
result Transformers achieve minimax optimal estimation risk in context.
LLMs perform well in financial sentiment analysis without fine-tuning.
problem Challenges in financial terminology, emotions, and ambiguous expressions.
method In-context learning methods for financial document-sentiment pairs.
result LLMs can generalize in-context demonstrations to new financial documents.
Paper presents a Transformer model for automatic domain adaptation.
problem Challenges in selecting or designing domain adaptation algorithms.
method Transformer model approximates and selects domain adaptation algorithms.
result Transformers can approximate and automatically select domain adaptation algorithms.
Study on neural scaling laws for solving linear systems in-context.
problem Theoretical guarantees for solving linear systems using a linear transformer architecture.
method Neural scaling laws and task diversity for in-domain and out-of-domain generalization.
result Novel notion of task diversity for necessary and sufficient condition of generalization under task shifts.
Bayesian analysis reveals epistemic uncertainty as a key diagnostic for delayed generalization in in-context learning.
problem Delayed generalization in in-context learning from few examples.
method Bayesian perspective, modular arithmetic tasks, approximate Bayesian techniques, spectral mechanism analysis.
result Epistemic uncertainty collapses sharply when the model groks, indicating a practical diagnostic of generalization.
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.