arXiv Machine Learning
22h ago
OraclePhys: A Systematic Framework for LLM Fine-Tuning on Structural Mechanics
arXiv:2608. 17162v1 Announce Type: new Abstract: What a language model internalizes from fine-tuning is usually diagnosed after the fact.
Benchmarks and evaluation
Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv AI
22h ago
Towards Unified World Models for Visual Navigation via Memory-Augmented Planning and Foresight
arXiv:2510. 08713v3 Announce Type: replace Abstract: Enabling embodied agents to imagine future states is essential for robust and generalizable visual navigation.
arXiv AI
22h ago
Exploring Efficient Open-Vocabulary Segmentation in the Remote Sensing
arXiv:2509. 12040v3 Announce Type: replace-cross Abstract: Open-Vocabulary Remote Sensing Image Segmentation (OVRSIS), an emerging task that adapts Open-Vocabulary Segmentation (OVS) to the remote sensing (RS) domain, remains underexplored due to the absence of a unified evaluation benchmark and the domain gap between natural and RS images.
arXiv AI
22h ago
Q-Learning With World Models
arXiv:2608. 17163v1 Announce Type: cross Abstract: Off-policy reinforcement learning (RL) has become increasingly sample-efficient, enabling applications such as RL fine-tuning of Vision-Language-Action models into reliable, high-performing policies.
arXiv AI
22h ago
TabularQGAN: A quantum generative model for tabular data synthesis
arXiv:2505. 22533v2 Announce Type: replace-cross Abstract: In this paper, we introduce a novel quantum generative model for synthesizing tabular data.
arXiv AI
22h ago
Multi-Scale Spectral Attention Module-based Hyperspectral Segmentation in Autonomous Driving Scenarios
arXiv:2506. 18682v3 Announce Type: replace-cross Abstract: Recent advances in autonomous driving (AD) have highlighted the potential of hyperspectral imaging (HSI) for enhanced environmental perception, particularly in challenging weather and lighting conditions.
arXiv AI
22h ago
SOD: Step-wise On-policy Distillation for Small Language Model Agents
arXiv:2605. 07725v3 Announce Type: replace-cross Abstract: Tool-integrated reasoning (TIR) is difficult to scale to small language models due to instability in long-horizon tool interactions and limited model capacity.
arXiv AI
22h ago
Supporting Calibrated Reliance in Human-AI Collaboration: Different Strategies for Different Tasks
arXiv:2604. 03237v2 Announce Type: replace-cross Abstract: As AI systems increasingly support human decision making, a central challenge is determining what information helps people recognize when to rely on AI predictions and when to question or override them.
arXiv Machine Learning
22h ago
Mr.Dec: Daily-Scale Longitudinal Multimodal Modeling for 30-Day Readmission Prediction
arXiv:2608. 16929v1 Announce Type: new Abstract: Predicting 30-day hospital readmission is essential for assessing patient stability and optimizing healthcare resources.
arXiv AI
22h ago
SurgicalMamba: Dual-Path SSD with State Regramming for Online Surgical Phase Recognition
arXiv:2605. 14889v4 Announce Type: replace-cross Abstract: Online surgical phase recognition must commit to a prediction at every frame of a procedure that runs for hours, from past frames alone and at a per-frame cost that does not grow with elapsed length.
arXiv Machine Learning
22h ago
Certified but Private: Scalable Zero-Knowledge Proofs for Neural Network Guarantees
arXiv:2608. 17070v1 Announce Type: new Abstract: With the growing deployment of machine learning models, formal guarantees of the robustness and fairness of these models have become increasingly important in safety-critical and legal-compliance settings.
arXiv Machine Learning
22h ago
RoBell-RVFL: A Robust Generalized Bell Random Vector Functional Link Network
arXiv:2608. 16965v1 Announce Type: new Abstract: The dominance of majority classes in real-world datasets poses a fundamental challenge to randomized neural networks, often biasing decision boundaries and overlooking critical minority samples.
arXiv Machine Learning
22h ago
SCENARIODIFF: A Scenario-level Guidance Framework for Multimodal Time Series Forecasting--Extended Version
arXiv:2608. 17164v1 Announce Type: new Abstract: Textual context such as news, reports, and logs can provide valuable signals for time series forecasting, especially when future dynamics are driven by external events that are not yet visible in historical values.
arXiv Machine Learning
22h ago
Repetition as Reinforcement: Enhancing Sample Efficiency via Instant Episode Repetition in Reinforcement Learning
arXiv:2608. 17347v1 Announce Type: new Abstract: Repetition is a fundamental mechanism in human learning, where revisiting successful experiences strengthens memory, consolidates skills, and improves future performance.
arXiv Machine Learning
22h ago
Temporal Leakage in Financial News NLP: A Multi-Architecture Audit with a Regime-Specific M&A Signal
arXiv:2608. 17223v1 Announce Type: cross Abstract: Financial-news direction prediction has become a popular NLP benchmark, yet reported gains depend critically on whether the train-test split is chronological or random, i.
arXiv AI
22h ago
When to Review: Spaced Repetition for Continual Pre-Training of Language Models
arXiv:2608. 17530v1 Announce Type: new Abstract: Continual pre-training of large language models must acquire new information without erasing old knowledge.
arXiv Machine Learning
22h ago
TokEval: A Tokenizer Evaluation Suite
arXiv:2608. 18062v1 Announce Type: cross Abstract: Language model tokenizers are typically selected with minimal evaluation, despite the fact that their design choices directly impact model capabilities.
arXiv Machine Learning
22h ago
Neural Operator-Based Nonlinear Nudging for Chaotic Dynamical Systems
arXiv:2508. 05778v2 Announce Type: replace Abstract: Nudging is an empirical data assimilation technique that incorporates an observation-driven control term into the model dynamics.
arXiv Machine Learning
22h ago
One Pipeline, Many Transformers: Pattern-Specific Imputation Specialists for Tabular Missing Data
arXiv:2510. 02625v5 Announce Type: replace Abstract: Missing data in tabular datasets forces practitioners into a hard choice: deploy a general-purpose imputer that may perform poorly for the problem at hand, or wait for someone to design a specialized algorithm.
arXiv AI
22h ago
ChannelFlow-Tools: A Configuration-Driven Pipeline for Generating Machine-Learning-Ready Datasets of 3D Obstructed Channel Flows
arXiv:2509. 15236v2 Announce Type: replace-cross Abstract: Data-driven surrogate models are increasingly used in computational fluid dynamics, and their reliability depends on the quality of the training data.