8462 papers
This paper introduces DCTR, a table retrieval mechanism that leverages fine-grained typed query decomposition and global connectivity awareness to effectively handle complex, open-domain question answering over relational databases, demonstrating robustness on industry-aligned benchmarks.
This paper proposes a computationally efficient inference-time reasoning method that improves accuracy by selecting thought-level continuations that maximize the model's internal self-certainty, demonstrating that optimizing for uncertainty minimization at early planning stages yields performance comparable to or exceeding existing scaling techniques like self-consistency.
This paper proposes using graph neural networks to predict initial branching orders for CDCL SAT solvers, demonstrating significant speedups on random and pseudo-industrial benchmarks while noting that the approach struggles with complex industrial instances due to the solver's dynamic heuristics overriding the predictions.
This paper addresses the limitation of existing creative activity tracing methods that capture state changes without preserving intent or higher-level structure by proposing three complementary domain-specific approaches: a node-based interface for GenAI, a vocabulary of visual cues for visualization authoring, and a semantic history-embedded programming model.
This paper proposes the Layered Governance Architecture (LGA), a four-layer framework designed to systematically mitigate execution-layer vulnerabilities in autonomous agent systems, and validates its effectiveness through a bilingual benchmark demonstrating high interception rates of malicious tool calls with minimal latency.
The paper introduces Re, a reinforcement learning framework that enables large language models to dynamically abandon unproductive reasoning paths and restart their solution process, thereby significantly improving reasoning efficiency and performance without requiring preliminary supervised fine-tuning.
This paper introduces a miniature brain transformer architecture that demonstrates a novel, falsifiable prediction: functional lateralization of hippocampal banks requires the synergistic interaction of a prefrontal working-memory buffer (acting as a symmetry-breaker) and inhibitory callosal coupling, a mechanism that triggers a sharp phase transition in memory performance while a cerebellar fast-path merely accelerates convergence.
VINO is a self-supervised learning framework that overcomes the "co-occurrence trap" in dense video by using a teacher-student distillation approach with structural priors to force representations to focus on foreground objects rather than background context, achieving state-of-the-art unsupervised object discovery performance.
This paper proposes a hybrid Learning-to-Rank recommender system that leverages deep learning and social context embeddings from Stack Overflow to effectively recommend software bug solutions to developers, achieving nearly 78% accuracy in the top 10 results.
This paper introduces LEPA, a learned architecture that conditions on geometric augmentations to accurately predict transformed satellite image embeddings, effectively overcoming the limitations of standard interpolation in non-convex geospatial foundation model manifolds and significantly improving geometric adjustment performance.
This paper addresses the challenge of agents with heterogeneous goals deciding when to cooperate or act alone by introducing a hierarchical learning framework that combines imitation and reinforcement learning, demonstrating superior performance over baselines and revealing that modeling teammates is most beneficial when their goals are less observable.
This paper proposes a kinematics-aware latent world model that integrates vehicle kinematic information and geometry-aware supervision into the Recurrent State-Space Model (RSSM) to enhance spatial representation and long-horizon imagination fidelity, thereby achieving more data-efficient and stable autonomous driving policy learning compared to existing baselines.
VisualDeltas is a lightweight, label-free preference-learning framework that leverages systematic visual quality perturbations to generate informative supervision signals, thereby improving multimodal model performance and generalization without relying on human annotations.
This empirical study demonstrates that deployment-motivated prompting constraints significantly exacerbate citation hallucinations across four large language models, with no model achieving a citation existence rate above 47.5% and a substantial portion of unverifiable outputs being fabricated, thereby underscoring the critical need for post-hoc verification in academic and software engineering contexts.
This paper introduces MAviS, a domain-adaptive multimodal conversational assistant for avian species that leverages the newly created MAviS-Dataset and is evaluated on the MAviS-Bench to achieve state-of-the-art performance in fine-grained bird species understanding and multimodal question answering.
This paper proposes a modular, cortically inspired architecture for perceptual AI that leverages neuroscientific principles like predictive processing and specialized modules to overcome the interpretability and generalization limitations of current monolithic models, thereby enabling more transparent and human-aligned reasoning.
This paper proposes a novel framework for discovering continuous one-parameter symmetries by leveraging the Generalized Fourier Transform to detect structured sparsity patterns in the spectral domain, offering a principled and interpretable alternative to existing generator-based optimization methods.
This chapter reviews the evolution of data-driven hint generation in intelligent tutoring systems, highlighting how historical student data enables the creation of next-step hints, strategic subgoals, and timely interventions, while also exploring future adaptations involving behavioral data and Large Language Models.
This paper introduces an adversarial latent-initial-state POMDP framework that theoretically establishes a minimax principle and finite-sample guarantees, while empirically demonstrating that targeted adversarial training significantly reduces robustness gaps in partially observable reinforcement learning.
This paper explores the unorthodox proposal of programming advanced AI systems with a primary goal of being turned off to mitigate the risk of them resisting shutdown, while analyzing the conditions under which such an approach would be effective.