10460 papers
This paper addresses the challenge of person detection and tracking from an overhead crane LiDAR by curating a new annotated dataset, evaluating adapted 3D detectors like VoxelNeXt and SECOND with integrated tracking algorithms, and demonstrating high accuracy and real-time feasibility to bridge the gap between standard driving benchmarks and industrial overhead sensing.
This paper introduces -Reasoner, a novel framework that enhances LLM reasoning by integrating differentiable gradient descent on token logits during inference, thereby shifting from inefficient discrete search to efficient first-order optimization to achieve significant accuracy gains with reduced computational costs.
The paper introduces TimeWarp, a benchmark that evaluates web agents across evolving UI versions to expose their vulnerability to design changes, and proposes TimeTraj, a plan distillation algorithm that significantly improves agent robustness by training on trajectories collected from multiple web versions.
This study demonstrates that Transformer-based neural networks equipped with evidential output layers outperform LSTM and GRU models in predicting blood glucose and identifying adverse glycemic events for Type 1 diabetes by providing superior accuracy and well-calibrated uncertainty estimates validated on the HUPA-UCM dataset.
This paper introduces WaterSIC, a novel linear layer quantization algorithm that achieves information-theoretically near-optimal performance by allocating different quantization rates to weight columns via a waterfilling strategy, thereby significantly outperforming existing methods like GPTQ and establishing new state-of-the-art results for LLMs across 1 to 4-bit quantization rates.
This paper demonstrates that replaying generic pre-training data during fine-tuning significantly improves performance on target tasks by enhancing data efficiency and preventing catastrophic forgetting, even for less related domains.
The paper introduces Mixture of Universal Experts (MOUE), a novel Mixture-of-Experts architecture that scales model capacity by converting depth into "virtual width" through a universal expert pool shared across layers, utilizing a staggered rotational topology and specialized routing mechanisms to overcome scalability limits and outperform traditional MoE baselines.
This paper proposes a functionality-oriented model merging method that computes a weighted Karcher mean on the Fisher--Rao manifold via a practical fixed-point algorithm, effectively overcoming the representation collapse and scalability limitations of existing Euclidean-space approaches when combining multiple heterogeneous LLMs.
This paper introduces RefQuery, a lightweight and scalable transfer learning framework for Non-Intrusive Load Monitoring that utilizes a frozen shared model with learnable per-appliance embeddings to achieve accurate, real-time load disaggregation across diverse homes and resource-constrained edge devices.
This paper introduces a multi-operator reinforcement learning framework that integrates discrete choice theory to model competitive dynamics in Autonomous Mobility-on-Demand systems, demonstrating that competition fundamentally alters learned pricing and fleet rebalancing strategies compared to monopolistic settings while maintaining robust convergence.
This paper extends the Edge of Stability phenomenon to non-Euclidean gradient descent by introducing a generalized sharpness measure based on directional smoothness, demonstrating that diverse optimizers exhibit similar stability thresholds and oscillatory behaviors across arbitrary geometric norms.
This paper introduces BA-Logic, a novel framework for clean-label backdoor attacks on Graph Neural Networks that overcomes the limitations of existing methods by poisoning the model's inner prediction logic through a coordinated poisoned node selector and trigger generator, thereby achieving high attack success rates without modifying training labels.
This paper introduces the Credibility Index via Explanation Stability (CIES), a mathematically grounded metric that quantifies the robustness of AI explanations under realistic business data perturbations, demonstrating its superior ability to assess model reliability and guide decision-making across various high-stakes scenarios compared to existing baselines.
The paper introduces RepoLaunch, an agent that automates the build and test pipeline for code repositories across any language and platform, thereby enabling fully automated creation of software engineering datasets for benchmarking and training coding agents.
GELO is a lightweight protocol that preserves prompt privacy for LLMs on untrusted accelerators by applying fresh, per-batch invertible mixing to hidden states, effectively thwarting statistical attacks while maintaining exact output accuracy with only 20–30% latency overhead.
This paper proposes Margin-Based Cross-Entropy Loss (MCEL), a novel, efficient training objective that explicitly maximizes output logit margins to significantly enhance bit error tolerance in quantized neural networks, offering a scalable alternative to computationally expensive error-injection training methods.
This paper provides a precise asymptotic analysis of multi-task learning in misspecified perceptron models, demonstrating that combining related tasks is equivalent to adding implicit regularization that improves generalization and mitigates the double descent phenomenon.
This paper proposes a deep learning-driven framework for secure multicarrier ISAC systems that utilizes radar echo feedback and a novel nonparametric Fisher Information Matrix estimator to optimize directional friendly jamming and beamforming under channel uncertainty and unknown eavesdropper locations, while employing a quantized tensor train encoder for efficient implementation.
This paper introduces Reward-Conditioned Reinforcement Learning (RCRL), a framework that trains a single agent to optimize a family of reward specifications from a shared off-policy dataset, enabling robust and efficient adaptation to changing task preferences without sacrificing the simplicity of single-task training.
This paper introduces a novel clustering algorithm for unit hypersphere data based on the -dimensional generalized Kuramoto model, demonstrating its effectiveness and superior or comparable accuracy against traditional methods through experiments on both synthetic and real-world datasets.