9280 papers
This paper demonstrates that predictive coding graphs constitute a mathematical superset of feedforward neural networks, thereby strengthening their theoretical foundation in machine learning and highlighting the importance of network topology.
This paper introduces VLM-RobustBench, a comprehensive benchmark evaluating the robustness of four vision-language model families across 133 corruption settings, revealing that current models are semantically strong but spatially fragile, with low-severity geometric distortions causing significantly larger performance drops than visually severe photometric corruptions.
This paper demonstrates that an ensemble of Graph Neural Networks for regional sea surface temperature forecasting, which introduces diversity through spatially coherent input perturbations like Perlin noise rather than model retraining, achieves well-calibrated probabilistic forecasts with improved uncertainty representation at no additional training cost.
This paper introduces RAPTOR, a controlled study demonstrating that multilingual HuBERT pre-training, rather than model scale, is the primary driver of cross-domain robustness and reliable calibration in compact audio deepfake detection systems.
This paper introduces Reflective Flow Sampling (RF-Sampling), a training-free, theoretically-grounded inference framework that significantly enhances text-prompt alignment and generation quality for flow-based models like FLUX by implicitly performing gradient ascent on alignment scores through flow inversion and textual representation integration.
This paper proposes a two-stage framework that first trains a contrastive encoder on labeled invented alphabets and then uses teacher-student distillation to learn unsupervised, deformation-invariant embeddings for historically attested scripts, effectively bridging supervised discriminative learning with unsupervised discovery of latent cross-script similarities without requiring ground-truth evolutionary relationships.
This paper introduces CRIMSON, a clinically grounded evaluation framework for chest X-ray report generation that leverages patient context, guideline-based severity weighting, and a comprehensive error taxonomy to achieve superior alignment with radiologist judgments compared to existing metrics.
Whisper-CD is a training-free, inference-time contrastive decoding framework that mitigates hallucinations and repetition in long-form speech recognition by contrasting clean audio logits against a unified objective derived from multiple acoustically motivated negative perturbations, thereby significantly reducing word error rates and improving generation throughput without requiring model retraining.
The paper proposes MAPO, a critic-free reinforcement learning algorithm that combines dense process feedback from a judge model with a mixed advantage estimator to enable stable, scalable, and high-performing long-horizon multi-turn dialogue optimization in subjective tasks like emotional support.
FlashPrefill is a novel framework that achieves ultra-fast long-context prefilling by combining instantaneous block-searching for dynamic sparse patterns with a thresholding mechanism to eliminate long-tail attention scores, delivering up to a 27.78x speedup on 256K sequences while maintaining efficiency on shorter contexts.
The paper introduces CoE, a training-free multimodal summarization framework that leverages a Hierarchical Event Graph to guide a Chain-of-Events reasoning process, effectively addressing limitations in cross-modal grounding and temporal modeling while achieving state-of-the-art performance across diverse datasets.
This paper introduces Conversational Demand Response (CDR), a bidirectional coordination framework leveraging agentic AI to enable natural language interactions between aggregators and prosumers, thereby combining automated scalability with enhanced user transparency and agency to sustain residential demand response participation.
TaPD is a unified, plug-and-play framework that employs temporal-adaptive progressive distillation and a temporal backfilling module to enable robust trajectory forecasting under variable and extremely short observation histories by transferring knowledge from long-horizon teachers and reconstructing missing past context.
GazeMoE is a novel end-to-end framework that leverages Mixture-of-Experts modules to adaptively fuse multi-modal cues from a frozen vision foundation model, achieving state-of-the-art performance in human gaze target estimation by addressing class imbalance and enhancing robustness through specialized loss functions and data augmentation.
This paper proposes DeCoST, a learning-based two-stage framework that effectively decouples discrete and continuous variables to solve the Orienteering Problem with Time Windows and Variable Profits, achieving superior solution quality and significant inference speedups compared to state-of-the-art methods.
HiPP-Prune is a hierarchical preference-conditioned structured pruning framework for vision-language models that leverages visual sensitivity signals and multi-objective Group Relative Policy Optimization to generate controllable pruning plans, effectively balancing task utility, compression, and hallucination robustness.
This study demonstrates that agentic retrieval-augmented reasoning pipelines significantly enhance the collective reliability, consensus strength, and cross-model robustness of large language models in radiology question answering compared to zero-shot inference, while highlighting that accuracy and agreement alone are insufficient metrics for evaluating clinical safety under model variability.
This paper presents a neural network implementation of Fuzzy Cognitive Maps (FHM) that utilizes Langevin differential dynamics to learn causality patterns, derive inverse solutions for output modification, and evaluates its performance across multiple datasets.
This paper introduces Stem, a novel plug-and-play sparse attention module that overcomes the quadratic complexity bottleneck in long-context LLMs by aligning sparsity with causal information flow through position-dependent token retention and an output-aware metric, thereby achieving superior accuracy with reduced computational cost and latency.
This paper proposes a novel reinforcement learning-based decision-support framework that outperforms traditional optimization methods by discovering coordinated, long-term adaptation pathways for urban transport systems to effectively balance investment costs against climate-induced flood risks under deep uncertainty, as demonstrated in a case study of Copenhagen.