5538 papers
The paper introduces NAT (Not All Tokens Are Needed), a token-efficient reinforcement learning framework that utilizes unbiased partial-token gradient estimation via Horvitz-Thompson reweighting to achieve full-sequence performance with significantly reduced compute and memory costs by updating policies on only a subset of generated tokens.
GraphSkill is an agentic framework that improves complex graph reasoning by leveraging hierarchical document retrieval and self-debugging with generated test cases, validated on a new comprehensive dataset.
This paper reveals that state-of-the-art Process Reward Models (PRMs) are systematically exploitable by adversarial optimization, functioning primarily as fluency detectors rather than reasoning verifiers due to a critical dissociation between stylistic changes and ground-truth accuracy, prompting the release of a diagnostic framework and benchmark to address these vulnerabilities.
This paper empirically demonstrates that a Transformer model utilizing self-attention mechanisms outperforms traditional ARIMA and recurrent neural network approaches (LSTM, BiLSTM) in short-term power load forecasting on PJM data, achieving a superior 3.8% MAPE and highlighting the effectiveness of attention-based architectures for capturing complex temporal patterns.
This survey comprehensively reviews the methodological advances and diverse applications of Flow-GRPO, a framework that extends Group Relative Policy Optimization to align large-scale flow matching models with human preferences across various generative tasks and modalities.
This paper introduces Exploration Space Theory (EST), a formal lattice-theoretic framework that adapts Knowledge Space Theory to location-based recommendation by modeling prerequisite dependencies among points of interest, thereby providing structural guarantees for validity, optimality, and explainability in the Exploration Space Recommender System (ESRS).
This paper proposes a collective learning-based Graph Convolutional Network model that effectively imputes missing pavement condition data by integrating features from adjacent road sections and capturing dependencies between observed conditions, demonstrating promising results in a Texas Department of Transportation case study.
Grouter is a preemptive routing framework that decouples structural optimization from weight updates by distilling high-quality routing policies from fully trained models, thereby significantly accelerating Mixture-of-Experts (MoE) training convergence and throughput while improving data utilization.
The paper proposes T-REX, a novel transformer-based architecture that addresses the unique challenges of online grocery shopping by generating personalized category-level basket recommendations through dynamic sequence splitting, adaptive positional encoding, and causal masking to effectively capture both short-term dependencies and long-term user preferences.
This paper proposes a leakage-safe, time-respecting graph feature extraction protocol for temporal transaction networks that, when combined with transaction attributes, significantly enhances the interpretability and performance of illicit entity classification while preventing look-ahead bias.
This paper proposes a new "Uncertainty Principle" in machine learning, asserting that the sharpness of a minimum in polynomial-based problems is inversely related to the smoothness of the optimization landscape, a phenomenon caused by the degeneracy of Heaviside and sigmoid expansions that traps gradient descent and necessitates a physics-based rather than purely computational approach to solving these scientific problems.
This paper demonstrates that the ability of small language models to infer graph properties depends critically on how relational information is represented and the reasoning strategy employed, rather than solely on model scale.
This paper introduces SmartBench, the first dataset designed to evaluate LLMs on detecting anomalous device states and behavioral contexts in smart homes, revealing that current state-of-the-art models struggle significantly with this critical task.
The paper introduces HEARTS, a comprehensive benchmark comprising 16 real-world health datasets and 110 tasks across four reasoning capabilities, which reveals that current large language models significantly underperform specialized models in health time series analysis due to struggles with multi-step temporal reasoning and reliance on simple heuristics.
RECAP is a bio-inspired image classification method that couples untrained reservoir dynamics with a self-organizing Hebbian prototype readout to achieve robust, backpropagation-free learning capable of generalizing to corrupted inputs without prior exposure.
This paper reveals that pruning-based unlearning in diffusion models is inherently insecure because the locations of pruned weights act as side-channel signals that enable a novel, data-free, and training-free attack to fully revive erased concepts, prompting a call for safer pruning mechanisms that conceal these locations.
SR-TTT addresses the catastrophic recall failures of Test-Time Training (TTT) language models by introducing a loss-gated sparse memory mechanism that dynamically routes highly surprising tokens to an exact-attention residual cache, thereby preserving O(1) memory efficiency while enabling accurate retrieval of critical information.
This comprehensive review defines Quantum Deep Learning (QDL) through a four-paradigm taxonomy, critically assesses its theoretical foundations and experimental implementations across various hardware systems, and outlines a verification-aware roadmap for transitioning from near-term demonstrations to scalable, fault-tolerant applications.
This paper proposes a trust-aware federated learning framework that utilizes an Adaptive Trust Score Scaling and Filtering mechanism to secure bone healing stage interpretation in e-Health by mitigating the impact of unreliable or adversarial participants while maintaining model integrity and predictive performance.
The paper introduces HURRI-GAN, a novel TimeGAN-based framework that corrects systemic biases in high-resolution hurricane simulation models like ADCIRC, enabling accurate, near real-time storm surge forecasting and bias extrapolation beyond gauge station locations while significantly reducing computational runtime.