6987 papers
This paper proposes an AI-driven framework that improves 5G/6G traffic demand prediction accuracy and spatial generalization by employing a context-aware two-stage splitting strategy and residual error correction to mitigate neighborhood leakage, as validated by experiments across five Canadian cities.
This paper proposes a hierarchical Graph Attention Network (HR-GAT) model that leverages public deployment records to accurately estimate fine-grained spectrum demand across multiple cities, significantly outperforming existing baselines and providing regulators with actionable insights for efficient spectrum sharing and allocation.
This paper introduces a risk-aware evaluation framework for Large Language Models in financial services, featuring a domain-specific taxonomy, an automated multi-round red-teaming pipeline, and a Risk-Adjusted Harm Score (RAHS) metric to better capture and quantify severe, operationally actionable security failures that traditional domain-agnostic benchmarks miss.
This paper proposes Nurture-First Development (NFD), a paradigm that shifts AI agent creation from static engineering to a continuous, conversational co-evolution process with domain experts, utilizing a Knowledge Crystallization Cycle to progressively transform tacit operational dialogue into structured, reusable expertise.
This paper introduces MCCOP, a framework that leverages a pretrained diffusion model within a joint sequence-structure latent space to generate minimal, biologically plausible protein mutations that flip predictive model outcomes to desired states, thereby bridging the gap between deep learning predictions and actionable protein engineering.
This paper evaluates the weak speaker verification capabilities of existing speech-aware large language models and proposes a lightweight augmentation method using frozen ECAPA-TDNN embeddings and LoRA adapters to significantly enhance speaker discrimination while preserving natural language interfaces.
This paper introduces BALD-SAM, a principled framework that adapts Bayesian Active Learning by Disagreement to spatial prompt selection in interactive segmentation, enabling a lightweight uncertainty estimation head on frozen foundation models to significantly outperform human and oracle prompting across diverse domains.
This paper critiques the instability and ambiguity of current cue-conflict benchmarks for measuring neural network shape-texture bias and introduces REFINED-BIAS, a new framework with balanced cue pairs and ranking-based metrics to enable reliable, interpretable, and fair cross-model comparisons.
This paper introduces a novel, low-complexity Human Presence Detection system for commodity laptops that utilizes the built-in Wi-Fi hardware and a new Range-Filtered Doppler Spectrum technique to achieve privacy-preserving, calibration-free occupancy sensing without requiring external sensors or infrastructure.
The paper introduces EvoKernel, a self-evolving agentic framework that leverages value-driven memory and reinforcement learning to overcome data scarcity in NPU kernel synthesis, significantly improving model correctness and achieving substantial speedups through automated drafting and iterative refinement.
This paper introduces a Semantic Landmark Particle Filter (SLPF) that enhances robot localisation in vineyards by integrating trunk and pole detections with LiDAR and GNSS to overcome perceptual aliasing caused by parallel crop rows, achieving significantly lower pose errors and improved row correctness compared to existing geometry-only, vision-based, and GNSS-only baselines.
The paper proposes , a novel method that dynamically fuses a Generalist Value Model's prior with sparse RL rollouts via real-time statistical testing to minimize baseline estimation error, thereby achieving faster convergence and over 10% performance gains on mathematical reasoning benchmarks compared to GRPO and DAPO.
This paper introduces GRACE, a unified 2D simulator and benchmark that enables transparent, reproducible comparisons of multi-robot path planning algorithms across grid, roadmap, and continuous environments by standardizing task instantiation, execution, and evaluation protocols.
This paper introduces a large bilingual (English/German) corpus of catalog records annotated with the Integrated Authority File (GND) and a machine-actionable GND taxonomy to enable ontology-aware multi-label classification and agent-assisted cataloging, aiming to develop transparent, authority-anchored AI tools that enhance the efficiency and scalability of subject indexing in digital libraries.
This paper introduces a parameter-efficient Diffusion Transformer (DiT) with a 2D CNN encoder that generates high-quality, cell-type-specific synthetic regulatory DNA sequences with significantly faster convergence, reduced memorization, and enhanced regulatory activity compared to existing U-Net-based models.
This paper introduces Dynamics-Predictive Sampling (DPS), a method that models prompt solving progress as a dynamical system to predict and select informative training samples via online Bayesian inference, thereby significantly reducing the computational overhead of extensive rollouts while accelerating and improving the reinforcement learning finetuning of large reasoning models.
This paper introduces PharmGraph-Auditor, a hybrid framework that combines a Virtual Knowledge Graph-based pharmaceutical knowledge base with a Chain of Verification reasoning paradigm to enable reliable, evidence-grounded, and traceable prescription auditing by transforming Large Language Models into transparent reasoning engines.
LookaheadKV is a lightweight KV cache eviction framework that achieves fast and accurate long-context inference by using parameter-efficient modules to predict future token importance without the computational overhead of explicit draft generation, thereby outperforming existing methods in both accuracy and speed.
This paper demonstrates that LoRA fine-tuning of compact LLM backbones significantly enhances voice cloning performance in terms of perceptual quality, speaker fidelity, and signal-to-noise ratio, provided the training data possesses sufficient acoustic diversity.
This paper introduces Historical Consensus Training, an iterative method that eliminates posterior collapse in Variational Autoencoders by progressively refining Gaussian Mixture Model priors to create a stable parameter barrier that prevents the degeneration of latent variables, achieving robust representations without relying on specific architectural constraints or hyperparameter tuning.