4779 papers
This paper proposes a conservative toolkit for evaluating language model agent identity by applying Stack Theory's temporal gap to separate mere behavioral consistency from genuine structural organization, yielding persistence scores that distinguish between agents that merely talk like a stable self and those actually organized as one.
The paper introduces EPOCH, a unified engineering protocol that structures multi-round autonomous system optimization into baseline construction and iterative self-improvement phases with role-constrained stages to ensure stability, reproducibility, and traceability across heterogeneous environments.
The paper introduces Sentinel, an autonomous AI agent that achieves reliable, scalable clinical triage for remote patient monitoring by outperforming individual clinicians in sensitivity and consistency while maintaining a clinically defensible overtriage profile at a negligible cost.
The paper proposes Sim2Act, a robust simulation-to-decision framework that enhances policy reliability in mission-critical domains by combining an adversarial calibration mechanism to align simulation fidelity with decision impact and a group-relative perturbation strategy to stabilize learning without overly conservative constraints.
This paper introduces Doki, a text-native interface that enables users of varying expertise to author generative videos by defining assets, scenes, and edits directly within a freeform text document, thereby shifting video creation from specialized tools to a natural writing process.
GST-VLA introduces a novel framework that enhances Vision-Language-Action models by converting visual observations into anisotropic 3D Gaussian spatial tokens and employing 3D Depth-Aware Chain-of-Thought reasoning to achieve state-of-the-art performance on precision-demanding robotic manipulation tasks.
This study demonstrates that integrating sentiment scores derived from a finetuned Qwen3 model analyzing English and Chinese news significantly enhances aluminum price forecasting accuracy and economic utility, particularly during periods of high market volatility, compared to traditional tabular data models.
This paper proposes a unified taxonomy and evaluation framework for latent world models in automated driving, organizing design choices by latent representations and structural priors while identifying key internal mechanics and research directions to enhance robustness, generalization, and deployability.
This paper proposes a transformer-based framework for skin cancer case retrieval that effectively combines reference images and textual descriptors by learning hierarchical representations and performing joint global-local alignment, thereby achieving state-of-the-art performance on the Derm7pt dataset to support clinical decision-making.
VIVID-Med introduces a novel framework that leverages a frozen large language model as a structured semantic teacher to pretrain lightweight, deployable medical Vision Transformers via a Unified Medical Schema and Structured Prediction Decomposition, achieving state-of-the-art performance across diverse medical imaging tasks with significantly reduced data requirements compared to existing vision-language models.
The paper introduces PM-Nav, a novel framework that leverages priori-semantic maps and hierarchical chain-of-thought prompting to overcome the challenges of language-driven navigation in functional buildings with highly similar features, achieving substantial performance improvements over existing methods in both simulation and real-world environments.
DexHiL is the first integrated human-in-the-loop framework for dexterous Vision-Language-Action models that combines coordinated arm-hand teleoperation with intervention-aware data sampling to significantly improve post-training performance and reliability in complex manipulation tasks.
The paper proposes QUSR, a novel diffusion-based image super-resolution model that combines an Uncertainty-Guided Noise Generation module to adaptively perturb high-uncertainty regions and a Quality-Aware Prior leveraging Multimodal Large Language Models to guide restoration, thereby achieving high-fidelity results in real-world scenarios with unknown and non-uniform degradations.
This paper models multi-LLM deliberation committees as random dynamical systems and demonstrates that even under deterministic temperature settings, factors like role differentiation and model heterogeneity induce chaotic instability characterized by positive empirical Lyapunov exponents, thereby establishing stability auditing as a critical requirement for reliable AI governance.
This paper proposes a Probability of Necessity and Sufficiency (PNS)-based regularization method for Class-Incremental Learning that utilizes a dual-scope counterfactual generator to mitigate feature collisions caused by intra-task shortcut reliance and inter-task semantic confusion, thereby ensuring both the causal completeness and separability of task-specific representations.
This paper introduces a novel agentic framework for Deep Tabular Research (DTR) that addresses the challenges of complex, unstructured tables by formalizing tabular reasoning as a closed-loop decision-making process, utilizing hierarchical meta-graphs for path planning, expectation-aware selection policies, and a siamese structured memory for continual experience-driven refinement.
This paper introduces DataFactory, a collaborative multi-agent framework that overcomes the context, hallucination, and reasoning limitations of existing TableQA systems by orchestrating specialized agents for structured and relational reasoning, thereby achieving significant accuracy improvements across multiple benchmarks.
TrustBench is a dual-mode framework that intervenes between action formulation and execution to verify autonomous agent safety in real-time, utilizing domain-specific plugins to reduce harmful actions by 87% with sub-200ms latency.
RubiCap introduces a novel reinforcement learning framework that leverages LLM-generated rubrics to create structured, multi-faceted reward signals for dense image captioning, thereby overcoming the limitations of supervised distillation and deterministic checkers to achieve state-of-the-art performance and superior word efficiency across various benchmarks.
This paper proposes a cost-effective framework that leverages structurally informative but functionally imperfect LLM-generated RTL to train netlist representation models, effectively overcoming data scarcity and outperforming methods reliant on scarce high-quality labeled datasets.