703 papers recorded in this category. Newest first.
- PolicyIK: High-Precision Inverse Kinematics for Robot Arms with Reinforcement Learning
Inverse kinematics (IK) converts end-effector pose commands into joint motion, and many vision-language-action (VLA) policies rely on it to act on a given arm and to transfer acros…
2026-11-03
- GUILD: Guided Iterative Data Collection for Imitation Learning
Imitation learning policies in robotics are trained on datasets collected through costly real-world teleoperation. Often, the data-collection process is unguided, relying on the te…
2026-11-03
- Reading Why: Born-Measured Attention with Exact Word Evidence on Light and Qubits
When a language model answers, we can usually only estimate why. We build a transformer in which every step is a Born measurement - attention $|\langle q|k\rangle|^4$ normalised ov…
2026-11-03
- Agnostic Learning by Imitating
Given a class of machine learning models and sample access to a data distribution with binary labels, which computational task is harder: training a discriminative model that disti…
2026-11-03
- A Circuit for In-Context Learning
In-context learning (ICL) lets a pretrained language model perform a task specified by demonstrations in its prompt, with no parameter updates. With arbitrary labels the model must…
2026-11-03
- CATF: A Manager-Worker Framework for Context-Aware Time-Series Forecasting
We study context-aware time-series forecasting, in which a single target variable is predicted from its own history and a set of contextual variables, such as weather and calendar …
2026-11-03
- $Φ$asmaNet: A Staged Spectral Token-Refinement Architecture for Fast Gravitational-Wave Signal-to-Noise Ratio Prediction
Quantifying selection effects in gravitational-wave population studies requires millions of costly signal-to-noise ratio (SNR) calculations. We present $Φ$asmaNet, a compact neural…
2026-11-03
- Universal Hardness From Masking Channels
We prove a broad learning-theoretic generalization of the celebrated hardcore lemma concerning the average-case complexity of computing a Boolean function (Impagliazzo, 1995). Our …
2026-11-03
- GSBR: Geometric Support Behavior Regularization for Online RL
Regularizing online reinforcement learning (RL) toward a pretrained base policy can improve sample efficiency and learning stability, but regularization that is too restrictive lim…
2026-11-03
- Conformal Prediction at Performative Equilibrium: The Price of Performativity
Conformal prediction gives finite-sample coverage when calibration and test points are exchangeable, but exchangeability can fail when deployment changes the data distribution. We …
2026-11-03
- De Rham cohomological architectures for PINNs and PDEs with topological holes
We attempt to alleviate failure modes of classical physics-informed neural networks (PINNs) in scenarios of topological pathologies corresponding to punctures, holes, poles, and vo…
2026-11-03
- iGC: Antibody Optimization via Reinforcement Learning over a Learned Somatic Hypermutation Prior
Antibody affinity maturation is a natural optimization process in which B cells acquire mutations through somatic hypermutation (SHM), undergo selection for improved antigen bindin…
2026-11-03
- Stabilizing On-Policy Targeted Guidance in Agentic Reinforcement Learning
Naive on-policy RL is often bottlenecked by the capabilities of the base model --- insufficient coverage can result in an inability to learn from certain rewards. At the same time,…
2026-11-03
- Gaussian Partitioning for Reliable Learning of Multi-Index Models
We introduce Gaussian partitioning, an algorithmic primitive for distributions smooth with respect to a Gaussian. It partitions space into polyhedral regions so that almost all mas…
2026-11-03
- NovoCRF: Globally Normalized De Novo Peptide Sequencing on a Prefix-Mass Lattice
De novo peptide sequencing has moved from dynamic programming over hand-designed or generative scores to large transformers that learn the task end to end. We present NovoCRF, a co…
2026-11-03
- Pretraining Data Scale Reverses the Muon-AdamW Fine-Tuning Gap
Muon has recently emerged as a promising optimizer for pretraining large language models, offering a speedup over AdamW in minimizing pretraining loss. However, it remains unclear …
2026-11-02
- Not All Reasoning Generalizes: A Case Study on Learning Generalizable Reasoning Strategies in RLVR
Reinforcement learning with verifiable rewards (RLVR) can enable generalizable improvement for large language model (LLM) reasoning. This paper studies how to incentivize such gene…
2026-11-02
- FADE: Factored Ability--Difficulty Filtering for Online RLVR Scheduling
Group-based reinforcement learning with verifiable rewards (RLVR) learns only from prompts whose sampled completions disagree: all-pass and all-fail groups produce zero relative ad…
2026-11-02
- Thought-deciphering via hierarchical EEG-to-text alignment
Communication is important for our well-being, but it can be impaired by disabilities, such as locked-in syndrome (LIS), cerebral palsy (CP), and dysarthria. Non-invasive brain-to-…
2026-11-02
- Benchmark Prediction with Sparse and Unpaired Cached Responses
Evaluating a generative model on all queries from all available benchmark tasks is prohibitively expensive. As such, models are often evaluated on different subsets of tasks and/or…
2026-11-02
- Efficient Closure Learning in Dynamical Systems: A Comparison of Data-Assimilated and Embedded Approaches
Increased computing power has transformed computational science and improved predictive capabilities for complex systems, but many phenomena still exceed current simulation capabil…
2026-11-02
- Should We Combine Our Data? Algorithms and Limits for Privately Assessing Data Sharing
In this paper, we study when two parties should pool their data to train a machine learning model. Two agents, Alice and Bob, each hold a sensitive labeled dataset and want to trai…
2026-11-02
- Structured Visual Landscape: Generating Preferred Representations in Biological and Artificial Neural Networks
Understanding how neurons respond to visual stimulus is an important question in both deep learning and neuroscience. It has significant implications for enhancing the interpretabi…
2026-11-02
- DynaSolver: A Neural Operator for Autoregressive 4D Flow Prediction with Dynamic Boundaries
Neural operators provide efficient surrogates for computational fluid dynamics (CFD), but most are designed for static geometries and are not equipped to model unsteady flows induc…
2026-11-02
- A Scaling Theory of Multi-Epoch Pretraining: Late-Time Overfitting and Ensembling
In the near future language model pretraining will become bound by total data rather than total compute. Such a regime requires revisiting scaling laws and scaling law theory. Moti…
2026-11-02
- BISECT: Bilevel Spectral Decomposition for Low-Rank Continual Learning
Exemplar-free continual learning on pre-trained Vision Transformers increasingly relies on Low-Rank Adaptation (LoRA), yet prevailing methods govern the low-rank update space throu…
2026-11-02
- Nonparametric Intensity Estimation for Covariate-Driven Poisson Processes Using Deep Learning
We consider nonparametric maximum likelihood estimation of the intensity function of a Poisson process, allowing the intensity to depend on observed covariates. Such models describ…
2026-11-02
- Can LLM Agents Improve Imperfect Earth System Model Parameterizations?
Earth system models (ESMs) rely on parameterizations to represent unresolved processes such as convection, cloud microphysics, and turbulence. However, translating advances in phys…
2026-11-02
- MIRA: Mutual Information guided calibration for Reliable Test-Time Adaptation
Test-time adaptation (TTA) updates a deployed model using only unlabeled target data, but standard entropy-based methods often rely on deterministic confidence and can reinforce ov…
2026-11-01
- Seeing Why: Exact Evidence Maps for Quantum and Optical Image Classifiers
When an image classifier decides, we can usually only estimate why. For quantum and all-optical classifiers that act linearly on amplitude-encoded pictures up to the measurement, w…
2026-11-01
- Large-Scale Bayesian Optimisation Using Uncertainty-Calibrated Product-of-Experts Gaussian Process Models with Trust Regions
The use of collections of independent local Gaussian processes (GP-ind) combined with trust regions is a widely adopted approach for large-scale and high-dimensional Bayesian optim…
2026-11-01
- OC-OPD: Observation-coordinated Supervision for On-Policy Distillation
Reverse and forward Kullback--Leibler (KL) divergences provide complementary supervision in on-policy distillation: reverse KL refines the student's active token rankings, and forw…
2026-11-01
- Direct Knowledge Transfer for Offline Q-Learning
Data-driven sequential decision making in marketing and healthcare can benefit from observations collected in related environments, particularly when data in the environment of int…
2026-11-01
- ReWY: Faster Gradient Computation for Delta-Rule Attention Family
Delta-rule linear attention underlies language models such as Kimi Linear and Qwen3-Next. Chunkwise implementations expose matrix parallelism, but their backward passes compute unn…
2026-11-01
- Watch Your Step: Adam's Margin Maximization Bias Depends on the Learning Rate Schedule
We study the implicit bias of Adam and its similarity to sign gradient descent on homogeneous models in binary classification tasks. Perhaps surprisingly, we uncover that these dep…
2026-11-01
- Machine Learning Beyond Statistical Consistency for Hybrid AI
We propose a new definition of machine learning, according to which a machine learns a function when it computes the function successfully, that is, when the value it returns for e…
2026-11-01
- Robust Remote ECG Monitoring under Energy Constraints: Anomaly Filtering versus Predictive Uncertainty
Machine learning for remote electrocardiogram monitoring must handle noise and diseases absent from training under tight resource constraints. We investigate whether upstream unsup…
2026-11-01
- Efficient Lempel-Ziv Prediction with the Run-Length BWT
Lempel-Ziv Plurality (LZP) is an algorithm of Kosoy that predicts the next symbol of a string by using its Lempel-Ziv factorization, and makes at most $O(z\log n)$ mistakes on ever…
2026-11-01
- A Self-Generated Floor on Adam's $\varepsilon$: Evidence from Power-Law Matrix Sensing
In nonconvex Burer--Monteiro low-rank matrix sensing of $U^\ast \in \mathbb{R}^{V \times D}$ under power-law covariance $Σ= \mathrm{diag}(j^{-s})_{j=1}^V$, the precision-wall appro…
2026-11-01
- The (Butter)fly Dream: Linear Separability of World-Model Rollouts in a Connectome-Constrained Visual Model
Zhuangzi dreamt he was a butterfly and, on waking, could not tell which was the dream. We ask a version of his question of a model of the fly brain: placed inside a world generated…
2026-11-01
- Quantizing Recurrent Language Models Is Easier Than You Think
Linear recurrences are becoming an increasingly common building block in large language models, replacing the growing KV cache of softmax attention with a fixed-size recurrent stat…
2026-11-01
- Privacy-Preserving ECG-HRV Emotion Classification for Mood Swing Detection using Federated Learning on Constrained Edge Devices
This paper presents a privacy-preserving mood monitoring framework that classifies emotional states from ECG-derived heart rate variability (HRV) features. The framework is evaluat…
2026-11-01
- Missingness-Aware Prior-Data Fitted Network for Irregular Clinical Time-Series
Clinical time series are irregularly observed with laboratory measurements recorded at uneven intervals and observation patterns often reflecting patient state, clinical concern, a…
2026-11-01
- ReFrame: Silence-Aware Compute Reclamation for Full-Duplex Speech Models
Full-duplex speech models execute dense model inference for every audio frame throughout a live interaction. This uniform framewise schedule creates sustained GPU load across dialo…
2026-11-01
- When Does Latent Prediction Error Support Physical Surprise Claims in Video World Models?
Prediction errors from video world models are often treated as physical surprise, but they can also reflect appearance, static content, motion, or ordinary prediction difficulty. W…
2026-11-01
- Domain-Aware Hierarchical Federated Learning for UAV Swarms Across Heterogeneous Environments
Hierarchical federated learning (HFL) enables communication-efficient training in unmanned aerial vehicle (UAV) swarms, but performance degrades under changing and heterogeneous en…
2026-11-01
- Learning AI Agents, Market Makers, and Stress in Automated Markets
Automated markets increasingly route order flow from learning trading agents through automated market makers (AMMs). We model trader archetypes as AI agents defined by their reward…
2026-11-01
- Detection Instead of Inversion: T1-T2 Microstructure Quantification With Detection Transformers
T1-T2 correlation MRI has strong potential to quantify microstructural compartments without imposing a biological model. Traditionally, full T1-T2 spectra per voxel are reconstruct…
2026-11-01
- Latent Reasoning in Continuous Space for Unified Multimodal Models
Unified Multimodal Models (UMMs) achieve remarkable success on diverse multimodal understanding and generation tasks, yet they still struggle to effectively leverage language-based…
2026-10-30
- Counting on Dummies: Privacy Amplification with Observable Counts and Truncated Batches
In many practical deployments of Differentially Private Stochastic Gradient Descent (DP-SGD), the server processes data in batches. Randomly sampling these batches allows for bette…
2026-10-30
- A Better Critic Matters for Distribution Matching Distillation
Distribution Matching Distillation (DMD) trains a few-step student using the difference between a teacher's score and an online critic's estimate of the student distribution's scor…
2026-10-30
- Instance-dependent sequential limits as an exact information ledger
Instance-dependent limits for bandit regret, sequential tests, best-arm identification and Markov decision processes are proved by one chain. It runs from a divergence decompositio…
2026-10-30
- Physiological Trajectories and Observation Patterns in ICU Mortality Prediction: Transportability Under Changing Measurement Conditions
Objective: To distinguish the transferable predictive value of physiological trajectories from that of observation patterns in ICU mortality prediction, and to assess whether measu…
2026-10-30
- Gradient Descent on Two ReLU Neurons: Global Landscape and Bifurcation Dynamics
Understanding how gradient descent learns features remains a central challenge in neural network theory. We study this question in a minimal multi-index setting that already exhibi…
2026-10-30
- Fast Privacy Loss Accounting for Random Allocation via Multiscale FFT
In the random allocation sampling scheme each user's data is used in $k$ steps chosen randomly and uniformly from a sequence of $t$ steps. This scheme is known to improve on Poisso…
2026-10-30
- SATFRONT: Detecting Atmospheric Fronts with Satellite Data using Machine Learning
Atmospheric fronts are associated with much of the high-impact weather in the mid-latitudes, yet their identification and classification remain largely manual and subjective. Exist…
2026-10-30
- Regret-Optimal Wasserstein-Robust Linear Regression
Distributionally robust optimization (DRO) minimizes worst-case risk under distributional uncertainty, but its decisions can be suboptimal in terms of their excess risk, or regret.…
2026-10-30
- Hard Constraint Projection in a Physics Informed Neural Network (Burgers)
Physics informed machine learning provides a framework to study and simulate fluid dynamics, potentially at a fraction of the computational cost of traditional numerical methods, w…
2026-10-30
- Hyperbolic Inverse Reinforcement Learning
Inverse reinforcement learning (IRL) seeks to infer the reward function underlying observed behavior, but its predictive accuracy and interpretability depend on how that reward is …
2026-10-30
- Towards Understanding the Impact of Plasticity Loss on Reinforcement Learning in Stochastic Environments
Deep reinforcement learning (RL) is a powerful framework for sequential decision-making. Despite many high-profile successes in recent years, deep RL is known to be brittle. An eme…
2026-10-30
- Cost-Aware Stopping for Freeze-Thaw Bayesian Optimization: When Does One-Step Lookahead Suffice?
Freeze-thaw Bayesian optimization (BO) evaluates candidates in resumable increments but usually stops at a budget or convergence test. We maximize a budget-free utility, the best o…
2026-10-30
- Differentially Private Synthetic Data from Sliced Chebyshev Moments
Research on practical differentially private (DP) synthetic data has largely focused on methods that approximately preserve low-dimensional marginals of a target distribution, and …
2026-10-30
- RAMA: Retrieval-Augmented Multi-Agent Routing with Episodic Memory for LEO Satellite Networks
Low-Earth orbit (LEO) satellite networks present a challenging routing environment due to rapidly changing topology, traffic, and link conditions. Existing deep reinforcement learn…
2026-10-30
- Exact Theory and Optimal Stepsizes for Stochastic Gradient Descent in Smooth Convex Minimization
This work considers the design of stepsize schedules for stochastic gradient descent in smooth convex optimization. Throughout, we assume that gradient noise is conditionally zero-…
2026-10-30
- A richness-sensitive Acoustic Biodiversity Index from species-level detections: classifier benchmarking, false-positive control and validation against standard soundscape indices in an African savanna and an urban zoo
Acoustic indices are widely used as rapid proxies for biodiversity, but they summarise the distribution of sound energy rather than the species producing it and often track richnes…
2026-10-30
- Empirical Evaluation of Quantum Kernel Methods for Classification: A Comparative Study with Classical Kernels
Quantum kernel methods are the most concrete near-term proposal for quantum machine learning on classical data, yet published benchmarks disagree on whether they outperform tuned c…
2026-10-30
- Propose-Filter-Release: Scaling Noise to Typical Sensitivity via Private Filtering
An estimator can be accurate and stable on typical data, yet sensitive to a few possible records. Differentially private mechanisms commonly scale their noise to the worst-case inf…
2026-10-29
- Adaptive Scenario Generation for KL-DRO Around a Learned Density Model
Distributionally robust optimization (DRO) hedges data-driven two-stage stochastic programs against error in the distribution estimated from a finite record, and standard ambiguity…
2026-10-29
- world2vec: Mechanistic world models through latent dynamics learning
World models can achieve strong control performance without faithfully capturing the dynamics of their environment, limiting their potential for mechanistic interpretability and sc…
2026-10-29
- An ODE-based Sampler for Discrete Diffusion Models
The marginals of a continuous diffusion model can be reproduced by a deterministic ordinary differential equation (ODE), known as the probability flow ODE, which provides a foundat…
2026-10-29
- Difficulty Calibration Across Time for Membership Inference in Diffusion Models
Modern diffusion models are trained on massive datasets that often include copyrighted or private images. Membership inference attacks (MIAs) address this by testing whether a give…
2026-10-29
- Training Foundation Models with a Single Algorithm
Foundation models are typically trained in stages: pretraining, midtraining, supervised fine-tuning (SFT), and reinforcement learning (RL), with changes in both data and learning a…
2026-10-29
- Machine Learning-Based Detection of Mobile Money Scan Messages in Ghana: A Comparative Evaluation of Naive Bayes, Support Vector Machine, and Randon Forest Classifiers
Mobile money (MoMo) is Ghana's preferred retail payment channel, recording GHC518.4 billion in transactions in December 2025 and over 26.7 million active accounts (Graphic Online, …
2026-10-29
- TRACER, a time-to-event EHR foundation model for disease detection across health systems
Foundation models trained on longitudinal electronic health records (EHRs) can predict clinical diagnoses years in the future, making them a potential tool for disease screening. W…
2026-10-29
- Homebrewed SLMs: Autoregressive and Masked Diffusion Language Models Built at Home for Portuguese
Building a language model of one's own no longer requires a data centre. This tutorial trains one from scratch, tokenizer included, on one consumer GPU, and shows how to tell wheth…
2026-10-29
- NEOPIC: A Neural Operator Framework for Particle-based Kinetic Plasma Simulations
We introduce NEOPIC, a framework for learning the field operator in particle-based methods applied to kinetic plasma simulations. Its key novelty is a neural operator that acts dir…
2026-10-29
- How I Aligned Your Model: Scaling Up Multilingual Safety Training with Templates
Safety alignment for Large Language Models is heavily focused on English with limited multilingual representation, particularly damaging low-resource language performance. Related …
2026-10-29
- Discovering Interpretable Acoustic Features in Autoregressive Voice-Cloning TTS Models
Voice-cloning TTS models synthesize an unseen speaker's voice from brief speech prompts, but it remains unclear which acoustic properties they represent and use. We introduce a fea…
2026-10-29
- Numerical Integration on Bounded Domains via Learned Reflected Diffusions
We study high-dimensional integration on bounded convex domains. Given a non-negative integrand $r$, the goal is to estimate $Z=\int_{D}r(x)\,\mathrm dx$ on $D\subset\mathbb R^d$. …
2026-10-29
- Fast and accurate neural triage decoding of ultra-high-rate quantum LDPC codes
Quantum error correction is essential for fault-tolerant quantum computing. High-rate quantum low-density parity-check (qLDPC) codes have emerged as a promising approach to reducin…
2026-10-29