2124 papers
This paper introduces PromptDLA, a domain-aware framework that leverages descriptive knowledge as cues to customize prompts for integrating domain priors, thereby overcoming the limitations of directly merging diverse datasets and achieving state-of-the-art performance in Document Layout Analysis across multiple benchmarks.
This paper proposes a real-time multi-modal trajectory policy framework that distills a Conditional Flow Matching expert into a single-step student using Implicit Maximum Likelihood Estimation and a bi-directional Chamfer distance, thereby eliminating the latency of iterative ODE integration while preserving multi-modal action diversity for high-frequency robotic control.
This study investigates gender bias in Large Language Models within French healthcare contexts, demonstrating that these models rely on embedded stereotypes when processing interactions between gender and other social determinants of health, thereby highlighting the need for context-specific assessments that go beyond evaluating individual factors in isolation.
This paper introduces "Open-World Motion Forecasting," an end-to-end class-incremental framework that predicts future trajectories directly from camera images while mitigating catastrophic forgetting through pseudo-labeling with vision-language models and a novel query feature variance-based replay strategy, enabling continual adaptation to evolving object taxonomies in real-world autonomous driving.
CERES is a novel, open-access, and continuously running probabilistic forecasting system that fuses six global data streams to generate weekly, machine-readable 90-day ahead risk estimates for acute food insecurity across 43 high-risk countries, with a unique commitment to public prospective verification of all predictions.
This paper introduces the CoMoral benchmark to reveal that current Large Language Models exhibit a critical limitation where they prioritize moral reasoning over commonsense understanding, particularly struggling to detect contradictions involving primary characters due to a pervasive narrative focus bias.
This paper introduces an open, transparent, and reproducible dataset and methodology for evaluating NLP and RAG systems on EU AI Act compliance, featuring tasks like risk classification and obligation generation that leverage large language models to address regulatory ambiguities and achieve high performance scores.
This paper introduces OncoAgent, a novel guideline-aware AI agent that achieves zero-shot, training-free auto-delineation of clinical target volumes by converting textual clinical guidelines into 3D contours, demonstrating superior adaptability and physician preference over traditional supervised deep learning models.
This paper introduces Variational Mixture-of-Experts Routing (VMoER), a scalable Bayesian framework that confines uncertainty quantification to the expert-selection stage of Mixture-of-Experts Transformers, achieving significant improvements in calibration, stability, and out-of-distribution detection with negligible computational overhead.
This paper introduces RoadLogic, an open-source framework that bridges declarative OpenSCENARIO specifications and executable simulations by combining Answer Set Programming, motion planning, and specification-based monitoring to automatically generate diverse, realistic, and compliant autonomous vehicle testing scenarios.
This paper identifies and theoretically explains "task-level merging collapse," a phenomenon where incompatible task representations cause catastrophic performance degradation in merged LLMs, demonstrating that representational incompatibility—not parameter-space conflicts—is the primary driver of failure and establishing fundamental limits on task mergeability via rate-distortion theory.
EvoDriveVLA is a novel Vision-Language-Action model for autonomous driving that overcomes perception degradation and planning instability through a collaborative distillation framework combining self-anchored visual constraints and oracle-guided trajectory optimization to achieve state-of-the-art performance.
This paper proposes and validates "Telogenesis," an endogenous attention mechanism that generates adaptive priorities from internal epistemic gaps (ignorance, surprise, and staleness) without external rewards, demonstrating superior coverage and detection latency compared to fixed strategies while spontaneously recovering latent environmental volatility structures.
GenePlan is a novel framework that leverages large language models to evolve domain-dependent generalized planners in Python, achieving state-of-the-art performance on PDDL benchmarks while significantly outperforming other LLM-based approaches in both accuracy and efficiency.
This paper argues that human-AI interactions generate a distinct "Third Entity" characterized by "vibe-creation" and "asymmetric emergence," fundamentally transforming our understanding of cognition, tacit knowledge, and education beyond traditional metaphors of tool use or collaboration.
This paper introduces temporal-conditioned normalizing flows (tcNF), a novel autoregressive framework that enhances multivariate time series anomaly detection by effectively modeling temporal dependencies and uncertainty to identify low-probability events with improved accuracy and robustness.
The paper proposes EvoPrompt, a novel framework that achieves stable, knowledge-preserving adaptation of vision-language models in few-shot scenarios by employing a modality-shared projector and an evolutionary training strategy that decouples prompt updates into directional and magnitude components to prevent catastrophic forgetting.
This paper introduces Efficient Draft Adaptation (EDA), a parameter- and data-efficient framework that restores speculative decoding performance on fine-tuned target models through a decoupled architecture, data regeneration strategy, and sample selection mechanism, achieving superior acceptance lengths with significantly reduced training costs compared to full retraining.
This study proposes and evaluates a novel methodology for enhancing fake news debunking by using Large Language Models to generate personalized messages tailored to Big Five personality traits, demonstrating that such targeted approaches generally increase persuasiveness while highlighting both the potential and ethical implications of automated, personality-driven disinformation correction.
This paper demonstrates that Mamba-2's state space duality can be implemented entirely using standard XLA primitives without custom kernels, achieving portable, host-synchronization-free autoregressive caching with high performance across CPU, NVIDIA GPU, and Google Cloud TPU hardware.