8799 papers
This paper introduces a systematic framework for Large Audio-Language Models that reformulates ambiguous emotion recognition as a distributional reasoning problem, utilizing an ambiguity-aware objective and structured chain-of-thought supervision to significantly improve performance on standard benchmarks.
This paper investigates the continuation-triggered jailbreak phenomenon in large language models, revealing through mechanistic interpretability analysis that its root cause lies in the inherent competition between the model's intrinsic continuation drive and its safety alignment defenses, while also identifying distinct behavioral patterns in safety-critical attention heads across different architectures.
This study leverages the MICCAI 2024 UWF4DR dataset to benchmark state-of-the-art deep learning models, including CNNs, Vision Transformers, and foundation models, in both spatial and frequency domains for image quality assessment, referable diabetic retinopathy detection, and diabetic macular edema identification using ultra-widefield imaging, demonstrating that feature-level fusion and frequency-domain representations yield robust and explainable results.
This paper introduces Fibration Policy Optimization (FiberPO), a unified framework that bridges trust-region theory and compositional algebraic structures to enable principled, multi-scale stability control in large language model training through the novel Aggregational Policy Censoring Objective and Fiber Bundle Gating mechanism.
The paper introduces FinToolBench, the first real-world, runnable benchmark that evaluates LLM agents on 760 executable financial tools using a novel framework assessing timeliness, intent, and regulatory compliance, alongside a proposed finance-aware baseline named FATR to advance trustworthy agentic AI in finance.
This paper proposes a cost-effective approach to detecting bias in financial language models by leveraging cross-model patterns to identify bias-revealing inputs early, demonstrating that up to 73% of a model's biased behaviors can be uncovered using only 20% of the input pairs when guided by another model's outputs.
SAIL is a test-time scaling framework that enhances one-shot robot imitation learning by reframing trajectory generation as an iterative refinement process guided by Monte Carlo Tree Search, an automated retrieval archive, and a vision-language model-based scoring mechanism, thereby significantly improving success rates across diverse manipulation tasks.
The paper proposes SCL-GNN, a novel framework that enhances the generalization of Graph Neural Networks on both IID and OOD graphs by utilizing the Hilbert-Schmidt Independence Criterion to identify and mitigate spurious correlations through an efficient bi-level optimization strategy.
This study utilizes a massive 172-billion-token evaluation across diverse models, context lengths, and hardware to reveal that while model selection is the primary determinant of accuracy, hallucination rates in document Q&A rise significantly with context length and vary non-linearly with temperature, highlighting that grounding ability and fabrication resistance are distinct capabilities.
The paper proposes AdaCultureSafe, a framework that addresses the lack of correlation between cultural safety and knowledge in Large Language Models by constructing a novel dataset of culturally grounded queries and introducing a knowledge-integrated method to significantly enhance adaptive cultural safety.
The paper proposes TA-RNN-Medical-Hybrid, a time-aware and interpretable deep learning framework that integrates continuous-time encoding, SNOMED-based disease representations, and a hierarchical dual-level attention mechanism to accurately predict ICU mortality risk while providing clinically meaningful explanations.
This paper evaluates LLM-based grant proposal reviews using structured perturbations on six quality axes, finding that a section-by-section analysis approach outperforms other architectures but that current models still struggle with clarity detection and holistic assessment, suggesting they are best suited as supplementary tools rather than replacements for human reviewers.
This paper presents BladeChain, a blockchain-based system that integrates multi-stakeholder endorsement, automated scheduling, and AI model provenance to provide immutable, auditable traceability for aircraft engine blade inspections across the entire component life cycle.
This paper reveals that Sharpness-Aware Minimization (SAM) exhibits depth-dependent implicit biases in linear diagonal networks, where -SAM's convergence becomes initialization-sensitive and unstable at depth , while -SAM displays "sequential feature amplification" that prioritizes minor features early in training, demonstrating that infinite-time implicit bias analyses fail to capture SAM's critical finite-time dynamics.
This paper systematically reviews recent advancements in Multimodal Mathematical Reasoning by proposing a unified Perception-Alignment-Reasoning paradigm, categorizing existing approaches around four fundamental questions regarding information extraction, representation, reasoning, and evaluation, while outlining future research challenges.
This paper proposes Graph-Instructed Neural Networks (GINNs) as a robust and scalable alternative to classical reduced order methods for efficiently simulating parametric partial differential equations with varying boundary conditions by learning the direct mapping between domain descriptions and PDE solutions.
This paper proposes a retrieval-augmented framework for text-to-CT generation that leverages a 3D vision-language encoder to retrieve semantically related clinical cases and their anatomical annotations as structural proxies, thereby enhancing image fidelity and spatial controllability in a realistic inference setting without requiring ground-truth annotations.
This paper introduces a concept-guided fine-tuning framework that enhances Vision Transformer robustness against distribution shifts by automatically generating and aligning model attention with fine-grained semantic concepts rather than spurious background correlations.
This paper presents a large-scale comparative study using the Epic ReduAct dataset and over 3,000 human participants to demonstrate that while humans rely on sparse, semantically critical cues for egocentric action recognition, state-of-the-art AI models degrade more gradually by depending on contextual and low-level features, revealing fundamental divergences in how humans and machines process spatial and spatiotemporal information.
CORE-Acu is a neuro-symbolic framework for acupuncture clinical decision support that integrates structured reasoning traces, a knowledge graph-based safety verification system, and a specialized loss function to ensure interpretable, hallucination-free, and strictly safe treatment recommendations, outperforming standard LLMs with zero observed safety violations.