2385 papers
This paper analyzes gender bias in audio deepfake detection using the ASVspoof 5 dataset and a ResNet-18 classifier, demonstrating that while aggregate metrics like Equal Error Rate may suggest low disparity, fairness-aware evaluation reveals significant gender-specific error distributions that necessitate more equitable and robust detection systems.
This paper introduces CMA-ES-IG, an algorithm that enhances robot preference learning by generating perceptually distinct and informative queries, thereby improving scalability, robustness, and user experience compared to existing state-of-the-art methods.
Meissa is a lightweight, 4B-parameter offline medical multi-modal agent that achieves state-of-the-art performance across diverse clinical benchmarks by employing novel trajectory modeling and stratified supervision to distill frontier model capabilities, thereby offering a cost-effective, low-latency, and privacy-preserving alternative to API-dependent systems.
This paper proposes "AI phenomenology" as a research framework that prioritizes users' first-person lived experiences over traditional performance metrics to better understand and guide the bidirectional alignment between humans and AI systems, offering a set of methodological tools, design concepts, and a research agenda derived from three empirical studies.
The paper introduces MEMO, a memory-augmented self-play framework that optimizes inference-time context through structured memory retention and uncertainty-aware prompt exploration, significantly improving the win rates and run-to-run stability of multi-agent LLMs in long-horizon, imperfect-information games.
This paper introduces Pichay, a demand paging system that treats LLM context windows as a memory hierarchy rather than a static cache, successfully reducing context consumption by up to 93% in production by evicting stale content and dynamically reloading it only when needed.
This paper presents an automated pipeline leveraging Large Language Models to detect and diagnose flaky tests in quantum software, successfully expanding an existing dataset by 54% and demonstrating that models like Google Gemini can achieve high accuracy (F1-scores up to 0.9643) in classifying flakiness and identifying root causes.
PlayWorld introduces a fully autonomous pipeline that trains high-fidelity, physically consistent video world models from unsupervised robot self-play, outperforming human-collected data in predicting complex interactions and significantly boosting real-world reinforcement learning success rates.
This paper introduces WS-Net, a deep unmixing framework that combines state-space modeling, wavelet-fused encoding, and a specialized weak signal attention mechanism to effectively recover weak spectral signals and significantly improve abundance estimation accuracy in hyperspectral images under low signal-to-noise conditions.
This paper proposes a conservative toolkit for evaluating language model agent identity by applying Stack Theory's temporal gap to separate mere behavioral consistency from genuine structural organization, yielding persistence scores that distinguish between agents that merely talk like a stable self and those actually organized as one.
The paper introduces EPOCH, a unified engineering protocol that structures multi-round autonomous system optimization into baseline construction and iterative self-improvement phases with role-constrained stages to ensure stability, reproducibility, and traceability across heterogeneous environments.
The paper introduces Sentinel, an autonomous AI agent that achieves reliable, scalable clinical triage for remote patient monitoring by outperforming individual clinicians in sensitivity and consistency while maintaining a clinically defensible overtriage profile at a negligible cost.
The paper proposes Sim2Act, a robust simulation-to-decision framework that enhances policy reliability in mission-critical domains by combining an adversarial calibration mechanism to align simulation fidelity with decision impact and a group-relative perturbation strategy to stabilize learning without overly conservative constraints.
This paper introduces Doki, a text-native interface that enables users of varying expertise to author generative videos by defining assets, scenes, and edits directly within a freeform text document, thereby shifting video creation from specialized tools to a natural writing process.
GST-VLA introduces a novel framework that enhances Vision-Language-Action models by converting visual observations into anisotropic 3D Gaussian spatial tokens and employing 3D Depth-Aware Chain-of-Thought reasoning to achieve state-of-the-art performance on precision-demanding robotic manipulation tasks.
This study demonstrates that integrating sentiment scores derived from a finetuned Qwen3 model analyzing English and Chinese news significantly enhances aluminum price forecasting accuracy and economic utility, particularly during periods of high market volatility, compared to traditional tabular data models.
This paper proposes a unified taxonomy and evaluation framework for latent world models in automated driving, organizing design choices by latent representations and structural priors while identifying key internal mechanics and research directions to enhance robustness, generalization, and deployability.
This paper proposes a transformer-based framework for skin cancer case retrieval that effectively combines reference images and textual descriptors by learning hierarchical representations and performing joint global-local alignment, thereby achieving state-of-the-art performance on the Derm7pt dataset to support clinical decision-making.
VIVID-Med introduces a novel framework that leverages a frozen large language model as a structured semantic teacher to pretrain lightweight, deployable medical Vision Transformers via a Unified Medical Schema and Structured Prediction Decomposition, achieving state-of-the-art performance across diverse medical imaging tasks with significantly reduced data requirements compared to existing vision-language models.
The paper introduces PM-Nav, a novel framework that leverages priori-semantic maps and hierarchical chain-of-thought prompting to overcome the challenges of language-driven navigation in functional buildings with highly similar features, achieving substantial performance improvements over existing methods in both simulation and real-world environments.