Method adapts frozen models for few-shot tasks without training.
problem Deployment constraints limit model updates, necessitating new adaptation methods.
method Exponential tilting of latent distribution for inference.
result Method outperforms parameter-update methods across benchmarks.
Spatial Adapter adds structured spatial representation to frozen predictors.
problem Efficiently adding spatial structure to pre-trained models.
method Structured spatial decomposition and closed-form covariance for residual fields.
result Adapter improves spatial prediction and uncertainty quantification.
We define systems of pre-extremals for the energy functional of regular rheonomic Lagrange manifolds and show how they induce well-defined Hamilton orthogonal nets. Such nets have applications in the modelling of e.g. wildfire spread under time- and space-dependent conditions. The time function inherited from such a Ha…
New method finds compact strong lottery tickets in partially frozen networks.
problem Finding compact strong lottery tickets in randomly pruned networks.
method Freezing a random subset of initial weights in a partially frozen network.
result Better accuracy and compression achieved with frozen networks.
Develops a cross-lingual hate speech detection model using pre-trained Transformers.
problem Detecting hate speech in low-resource languages.
method Utilizes frozen Transformer language models and AXEL attention-based classification block for zero-shot and few-shot learning.
result Demonstrates highly competitive results on English and Spanish subsets of the HatEval challenge.
New method generates synthetic time series paths with more flexibility.
problem Restrictions in generating synthetic paths using Brownian reference.
method Introduces Triangular-Reference Schrödinger Bridges (TR-SBTS) for time series generation.
result Generates synthetic paths with more flexibility in stochastic volatility and correlated noise.
LDA improves image classification accuracy with fewer features.
problem Fine-grained image classification with pretrained features.
method Supervised dimensionality reduction with LDA before linear probing.
result LDA improves accuracy over full features in 11 out of 12 configurations.
For surfaces, we brush a reasonably sharp picture of the influence of the fundamental group upon the complexity of foliated-dynamics. A metaphor emerges with phase-changes through the solid-liquid-gaseous states. Groups of ranks 0 ≤ r ≤ 1 0\le r\le 1 0 ≤ r ≤ 1 are frozen with intransitivity reigning ubiquitously. When 2 ≤ r ≤ 3 2\le r \le 3 2 ≤ r ≤ 3 , th…
ZegOT uses optimal transport to zero-shot segment images with text prompts.
problem Zero-shot semantic segmentation with limited image-text alignment knowledge.
method ZegOT uses optimal transport to match multiple text prompts with frozen image embeddings.
result ZegOT achieves state-of-the-art performance in zero-shot semantic segmentation.
This paper presents a new interacting particle system and uses it as a spin model for financial market microstructure. The asymptotic analysis of this stochastic process exhibits a lower bound to the contemporaneous measurement of price and trading volume under the invariant measure in the `frozen' phase of the supercr…
Revises Bayesian model averaging for foundation models.
problem Ensemble pre-trained and lightly-finetuned foundation models for improved classification performance.
method Introduces trainable linear classifiers and computationally cheaper model averaging scheme (OMA).
result Ensembled models can better predict on various datasets.
A new method uses a frozen language model to improve sample efficiency in reinforcement learning.
problem Improving sample efficiency in reinforcement learning with partially observable environments.
method FROZEN Hopfield network and HELM (History Embedding Language Model) method.
result HELM achieves new state-of-the-art results on Minigrid and Procgen environments.
A relatively common sight in graphic designs is a planar arrangement of three gears in contact. However, since neighboring gears must rotate in opposite directions, none of the gears can move. We give a non-planar, and non-frozen, arrangement of three linked gears.
Model user preferences for conversational LLMs using weak rewards.
problem Lack of persistent user models in conversational LLMs leading to repeated user restatements.
method Vector-Adapted Retrieval Scoring (VARS) framework that updates user vectors online from weak scalar rewards.
result Full VARS agent achieves strongest overall performance, matches strong Reflection baseline in task success, and reduces user effort.
ChatGPT snapshots predict future stock returns.
problem Predicting future stock returns using pre-cutoff text.
method Extracted LLM outlook scores from OpenAI snapshots.
result Outlook scores positively correlate with future stock returns.
Simple fine-tuning of GANs with frozen discriminator outperforms existing methods.
problem Fine-tuning GANs requires numerous data and heavy computation.
method Freeze lower layers of the discriminator for fine-tuning.
result FreezeD significantly outperforms previous techniques on various datasets.
The study examines how language models learn to represent the world, identifying conditions for ecological veridicality.
problem Understanding when language models learn to represent the world accurately and how this learning process can fail.
method Analyzes the Bayes-optimal next-token cross-entropy decomposition and the role of training ecology in shaping model representations.
result The minimum-complexity zero-excess solution is the quotient partition by training equivalence, and this solution is not preserved in in-context learning or per-task adaptation.
CausalLongPFN predicts counterfactual outcomes from time-series data.
problem Predicting future outcomes under varying treatments in time-series data with confounding and heterogeneity.
method Prior-fitted network pretrained on synthetic episodes of temporal structural causal models.
result CausalLongPFN outperforms domain-trained models on factual and counterfactual prediction tasks.
Backpropagation-free trunk training improves model performance on various benchmarks.
problem Memory inefficiency and noisy gradient estimates in deep network training.
method Split Forward Gradient (Split-FG) method that splits network into trunk and head, estimating only trunk gradient.
result Split-FG achieves better performance than pure forward-gradient training and backpropagation on various benchmarks.
Generative model downgrades coarse satellite images to fine resolution.
problem Reconstructing fine resolution satellite images from coarse scale inputs.
method Combines U-Net transfer encoder with diffusion-based generative model.
result Excellent performance (R2 = 0.65 to 0.94) across seasonal regional splits.
Martingale Doppelgänger-Eval benchmarks VLMs on candlestick evidence vs. trend extrapolation
problem Auditing whether VLMs use chart evidence or trend extrapolation
method Proving formal limitations and designing controlled mechanisms
result Identifying regression coefficients for evidence vs. trend
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.
The paper develops methods to reduce deployment risk under dynamic covariate shifts.
problem Reduction of deployment risk under dynamic covariate shifts.
method Time-domain Poincare inequality and Jacobian-velocity theorem to identify and control directional tangent energy.
result Drift-aligned tangent regularization (DTR) reduces risk volatility and directional gain in low-rank drift regimes.
Deleting refusal directions from models leads to systematically more optimistic decisions.
problem The impact of removing refusal directions from models on decision-making outcomes.
method Ablation study using a frozen pipeline of 21,600 weekly equity decisions.
result Ablation of refusal directions makes models more optimistic and justifies themselves more, but also reduces confidence.
FEET protocol evaluates foundation models across three scenarios.
problem Lack of standardized evaluation protocols for foundation models.
method Structured evaluation protocol across three use cases: frozen, few-shot, and fine-tuned embeddings.
result Demonstrates comprehensive assessment of foundation models' effectiveness.
We perform an average case analysis of the generalization dynamics of large neural networks trained using gradient descent. We study the practically-relevant "high-dimensional" regime where the number of free parameters in the network is on the order of or even larger than the number of examples in the dataset. Using r…
S-GAI initializes MLPs using spectral geometry from data, improving performance.
problem Lack of guidance on initial weights encoding data geometry.
method S-GAI uses SVD to estimate spectral class geometry, initializing MLPs from training data.
result S-GAI-initialized MLPs start from a more informative hidden state and achieve comparable accuracy.
Method calibrates local volatility and stochastic short rate models for equity-rate dynamics.
problem Joint calibration of local volatility and stochastic short rate models.
method Iterative approach using semimartingale optimal transport.
result Demonstrated performance on market data using European SPX options and cap interest rate options.
New method enhances model fine-tuning with minimal data.
problem Improving model performance on new tasks with limited data.
method Introducing α α α -LoRA, a reparameterization method for fine-tuning. result Enhanced generalization ability of fine-tuned models.
Study loop corrections in random feature models affecting training and test errors.
problem Analyzing loop corrections in random feature models to understand training and test errors.
method Statistical physics and effective field theory approach to study loop corrections.
result Derived loop corrections to training error, test error, and generalization gap.
Large and stable indices of the world wide stock markets such as NYSE and SP 500 together with NASDAQ -- the index representing markets of new trends, and WIG -- the index of the local stock market of Eastern Europe, are considered. Due to the relation between artificial insymmetrised patterns (AIP) and time series, st…
Study on how adversarial training affects neural network kernels and robustness.
problem Understanding and improving adversarial robustness in neural networks.
method Empirical study of the evolution of the empirical Neural Tangent Kernel (NTK) under standard and adversarial training.
result Adversarial training leads to a new kernel that provides robustness, even when non-robust training is performed on top of it.
ISAAC audits deep models for drug-target interactions, revealing structural differences.
problem Deep models for DTI often use irrelevant features, making them hard to evaluate.
method ISAAC uses intervention-based structural auditing to evaluate model sensitivity.
result ISAAC reveals significant structural differences in DTI models' reasoning.
Fine-tuning normalization layers can reconstruct smaller networks.
problem Understanding the expressive power of fine-tuning normalization layers.
method Random ReLU networks and sparsified networks were fine-tuned to reconstruct target networks.
result Fine-tuning normalization layers can reconstruct networks that are O ( e x t w i d t h ) O(\sqrt{ ext{width}}) O ( e x t w i d t h ) times smaller. Efficient RL algorithm for MDPs with linear Q π Q^π Q π realizability, achieving optimal regret bound.
problem Efficient reinforcement learning under linear Q π Q^π Q π realizability assumption for MDPs with stochastic dynamics. method Frozen Policy Iteration algorithm that uses high-confidence data and freezes policy for well-explored states.
result Achieves optimal regret bound of O ~ ( d 2 H 6 T ) \widetilde{O}(\sqrt{d^2H^6T}) O ( d 2 H 6 T ) for linear (contextual) bandits. New neural networks learn single-index models efficiently.
problem Learning low-dimensional structure in high-dimensional data.
method Shallow neural networks with frozen biases, studied via gradient flow.
result Generalization guarantees match near-optimal sample complexity.
Training-free looped transformers improve model performance without additional training.
problem Improving model performance without additional training or fine-tuning.
method A lightweight inference-time wrapper loops a contiguous mid-stack block of layers of a frozen checkpoint without additional fine-tuning.
result Our method improves model performance across various model families.
Investigates ways to train larger models with fewer resources, finding that test loss depends only on the actual number of trainable parameters.
problem Training larger models for cheaper under hardware constraints.
method Emulates an increase in effective parameters using frozen random parameters or fast structured transforms.
result Scaling laws cannot be deceived by spurious parameters; test loss depends only on the actual number of trainable parameters.
We study mirror symmetry of type II strings on manifolds with the exceptional holonomy groups G 2 G_2 G 2 and Spin(7). Our central result is a construction of mirrors of Spin(7) manifolds realized as generalized connected sums. In parallel to twisted connected sum G 2 G_2 G 2 manifolds, mirrors of such Spin(7) manifolds can be fou…
The paper analyzes how data augmentation affects the test error in regression models.
problem Understanding the impact of data augmentation on the test error in regression models.
method Characterizes the test error in terms of population quantities and augmentation statistics.
result Provides a tight characterization of the test error in mean squared error.
Paper tackles class-incremental time series classification with dual-stream feature extraction.
problem Class-incremental continual learning for multivariate time series data.
method Dual-stream feature extraction pipeline combining deep temporal embedding features and statistical features.
result Competitive average accuracy across multiple datasets with low forgetting rates.
GAPA method provides efficient uncertainty quantification for pretrained networks.
problem Reliable uncertainty estimates for pretrained models are challenging.
method Post-hoc Gaussian Process Activations (GAPA) method that shifts Bayesian modeling from weights to activations.
result GAPA method provides efficient uncertainty quantification without altering the backbone's predictions.
We introduce a novel method that enables parameter-efficient transfer and multi-task learning with deep neural networks. The basic approach is to learn a model patch - a small set of parameters - that will specialize to each task, instead of fine-tuning the last layer or the entire network. For instance, we show that l…
We analyze generalization in deep learning models using random matrix theory.
problem Understanding the generalization error in deep learning models with random feature representations.
method Applying Random Matrix Theory to derive asymptotic generalization error formulas for various architectures.
result Linear ESNs are equivalent to ridge regression with exponentially time-weighted input covariance, revealing an inductive bias towards recent inputs.
In this letter, we introduce a distributed Nesterov method, termed as A B N \mathcal{ABN} A B N , that does not require doubly-stochastic weight matrices. Instead, the implementation is based on a simultaneous application of both row- and column-stochastic weights that makes this method applicable to arbitrary (strongly-connected…
CARV reduces compute cost for downstream pipelines using diffusion models.
problem High variance in Monte Carlo estimators from diffusion models limits compute efficiency.
method CARV uses hierarchical MC estimation with amortized upstream computation and stratified-inverse-CDF.
result CARV delivers 2-3x effective compute multipliers without changing the objective.
DistillKac generates images quickly using damped wave equations.
problem Generating high-quality images efficiently.
method Uses damped wave equations and Kac dynamics for finite speed transport.
result Fast image generation with high quality and numerical stability.
Method learns diverse models to resist spurious correlations.
problem Models learn spurious correlations in i.i.d. training data.
method Multiple models with minimized conditional total correlation.
result Framework significantly outperforms baseline on distribution shift.