9683 papers
This paper proposes a systematic approach to Chalmers' "easy problems" of consciousness by demonstrating how an executable cognitive system, grounded in Kantian conceptual knowledge, can computationally derive abilities such as discrimination, attention, and reportability through its learning, emotional, and information-manipulation mechanisms.
This paper introduces AMV-L, a value-driven memory lifecycle framework for long-running LLM agents that replaces age-based retention with utility-based tiering to bound retrieval workloads, thereby achieving significantly improved tail-latency control and throughput compared to traditional TTL and LRU policies.
The paper introduces vLLM Semantic Router, a signal-driven decision framework that composes heterogeneous request features and neural classifiers into configurable policies to intelligently route queries across diverse Mixture-of-Modality models while enforcing privacy, safety, and cost constraints in production environments.
SkillNet is an open infrastructure that addresses the lack of systematic skill accumulation in AI agents by providing a unified ontology, a repository of over 200,000 skills, and evaluation tools to create, connect, and assess skills, thereby significantly enhancing agent performance and efficiency across diverse tasks.
This research proposes an explainable ensemble learning framework that integrates structured clinical and cognitive data with advanced preprocessing and hybrid class balancing techniques to achieve accurate and transparent Alzheimer's disease prediction, demonstrating that optimized ensemble models outperform deep learning while providing actionable clinical insights through SHAP analysis.
This paper proposes MPBMC, a hybrid approach that leverages Graph Neural Network embeddings and runtime design statistics to functionally cluster properties, thereby significantly accelerating multi-property Bounded Model Checking verification on HWMCC benchmarks compared to state-of-the-art methods.
This paper introduces the Non-Classical Network (NCnet), a classical neural architecture that exhibits quantum-like non-classical statistical behaviors through gradient competitions and implicit inter-task correlations, revealing that the resulting CHSH statistic serves as a novel indicator for understanding internal network dynamics and generalization performance across different resource regimes.
This study introduces a unified, end-to-end framework for developing combustion-specialized Large Language Models, featuring a massive multimodal knowledge base, a rigorous evaluation benchmark, and a three-stage knowledge-injection pathway that demonstrates the necessity of moving beyond standard retrieval-augmented generation to structured knowledge graphs and continued pretraining to overcome performance ceilings caused by context contamination.
This paper introduces a novel attack method that induces numerical instability in multimodal large language models by optimizing a specific loss function to generate images, causing significant performance degradation across state-of-the-art models and datasets that is distinct from traditional adversarial perturbations.
This paper demonstrates that rewriting user queries to reduce ambiguity using answer-free grounding context, rather than simply prepending that context, significantly boosts language model accuracy on challenging benchmarks like Humanity's Last Exam, with gains that cannot be replicated through inference-time prompting alone.
This paper proposes a distributed auction framework for repeated spectrum allocation in heterogeneous networks where user equipments utilize large language models as reasoning agents to strategically adapt their bidding and association decisions over time, resulting in superior channel access and budget efficiency compared to traditional static policies.
This paper argues that as embodied AI crosses critical thresholds in dexterity, generalization, and reliability, it will trigger a phase transition in economic geography by dismantling the century-old Fordist paradigm of centralized mega-factories and replacing labor-driven site selection with a new topology defined by demand-proximal micro-manufacturing and machine-optimal environmental conditions.
This paper proposes a novel, parameter-free Heterogeneous Attribute Reconstruction and Representation (HARR) learning paradigm that unifies numerical and categorical attributes into homogeneous spaces with learnable metrics to effectively adapt to various clustering tasks while guaranteeing convergence.
This paper presents the first multi-dimensional evaluation of 31 LLM safety benchmarks, revealing that while they do not outperform non-benchmark papers in academic influence, there is a critical misalignment where neither author prominence nor paper impact correlates with code quality, highlighting a significant need for improved repository readiness and ethical standards.
VSPrefill is a lightweight, training-efficient sparse attention mechanism that leverages vertical-slash structural patterns and adaptive thresholding to achieve linear complexity during long-context prefilling, delivering a 4.95x speedup while preserving 98.35% of full attention accuracy on 128k context lengths.
This paper introduces MAD-SmaAt-GNet, a multimodal, advection-guided neural network that extends the SmaAt-UNet architecture by integrating multiple weather variables and physics-based advection to significantly improve the accuracy and physical consistency of short-term precipitation nowcasting.
This paper investigates how large language models process conflicting demonstrations in in-context learning, revealing a two-phase computational structure where early layers encode both correct and incorrect rules while late layers commit to predictions, and identifies specific attention heads responsible for this vulnerability that can be mitigated through targeted ablation to significantly improve performance.
This study proposes an interpretable LSTM-based model for predicting ship trajectories in inland waterways that incorporates trained ship domain parameters to analyze attention mechanisms, revealing that while the model achieves competitive accuracy, its attention weights do not fully align with expected causal relationships between interacting vessels.
This paper proposes a propagation dynamics model and a non-intrusive genealogy-graph-based governance layer to identify, model, and effectively mitigate error cascades in LLM-based multi-agent systems, significantly improving defense success rates against error amplification without altering existing collaboration architectures.
This paper presents a circular dilated convolutional neural network (CDCNN) for real-time activity recognition using multi-modal smart insole sensor data, which achieves 86.42% accuracy in a subject-independent four-class classification task, demonstrating that inertial sensors are the primary contributors to performance while remaining suitable for embedded deployment.