6222 papers
The paper introduces NEXTPP, a dual-channel framework that unifies discrete event marks and continuous-time dynamics through cross-interaction mechanisms to significantly improve the prediction of irregularly spaced event sequences with discrete marks.
The paper proposes SAGE, a stage-adaptive reliability modeling framework that dynamically calibrates audio-visual confidence based on interaction stages to improve continuous valence-arousal estimation in noisy real-world environments.
This paper introduces a neuro-symbolic VLM agent framework called Knowledge-Guided TSED, which utilizes a novel Event Logic Tree representation to bridge natural language event descriptions with multivariate time series data, enabling accurate, zero-shot event detection and explainable reasoning while mitigating hallucinations in high-stakes domains.
The paper introduces \textsc{INFACT}, a comprehensive diagnostic benchmark with 9,800 QA instances and fine-grained taxonomies that evaluates Video-LLMs on faithfulness and factuality under various induced degradation modes, revealing that high base accuracy does not guarantee robustness against hallucinations and that many models struggle significantly with temporal sensitivity.
The paper proposes SPEGC, a Continual Test-Time Adaptation framework for medical image segmentation that mitigates error accumulation and domain shift by integrating a semantic prompt enhancement mechanism with a differentiable graph clustering solver to refine structural representations and guide robust model adaptation.
OrthoEraser is a novel concept erasure method for text-to-image models that utilizes sparse autoencoders and coupled-neuron detection to perform analytical orthogonal projection, effectively removing harmful content while preserving benign attributes by decoupling sensitive and non-sensitive feature subspaces.
This paper introduces KEPo, a novel poisoning attack method specifically designed to exploit the graph-based retrieval mechanism of GraphRAG systems by fabricating toxic knowledge evolution paths that manipulate the knowledge graph structure to force Large Language Models into generating harmful responses, thereby achieving state-of-the-art attack success rates where conventional RAG attacks fail.
This paper introduces Gen-Fab, a variation-aware conditional generative adversarial network that accurately predicts diverse, high-resolution fabrication outcomes for nanophotonic devices by modeling process-induced uncertainties, outperforming existing deterministic and probabilistic baselines in both accuracy and distribution alignment.
This paper introduces MADA, a Large Language Model-powered multi-agent framework that automates complex design workflows on High Performance Computing systems to iteratively refine and optimize scientific simulations, specifically demonstrated through the suppression of Richtmyer-Meshkov Instability in Inertial Confinement Fusion.
This paper introduces FBCIR, a method to diagnose and address focus imbalances in composed image retrieval models by identifying their tendency to over-attend to one modality, and proposes a data augmentation workflow with curated hard negatives to enforce balanced cross-modal reasoning and improve robustness in challenging scenarios.
The paper proposes EReCu, a unified unsupervised framework for camouflaged object detection that integrates a Multi-Cue Native Perception module, Pseudo-Label Evolution Fusion, and Local Pseudo-Label Refinement to overcome noisy label limitations and achieve state-of-the-art performance in detail perception and boundary alignment.
This paper introduces Expert Threshold (ET) routing, a fully causal mechanism that dynamically allocates computation and balances load across experts without auxiliary losses by independently routing tokens based on score thresholds, thereby outperforming traditional Token-choice Mixture-of-Experts in autoregressive language modeling.
ReHARK is a training-free framework that achieves state-of-the-art one-shot vision-language adaptation by addressing the stability-plasticity dilemma through a synergistic pipeline of hybrid prior construction, support set augmentation, adaptive distribution rectification, and multi-scale RBF kernels within a Reproducing Kernel Hilbert Space.
This paper introduces an agentic AI framework featuring a central Supervisor that dynamically orchestrates specialized tools across text, image, audio, video, and document modalities to achieve significant reductions in response time, conversational rework, and costs while maintaining accuracy parity compared to hierarchical baselines.
This paper introduces MANSION, a language-driven framework that generates realistic, multi-floor 3D building environments and the MansionWorld dataset to address the limitations of current single-floor benchmarks in evaluating long-horizon robotic tasks requiring complex spatial reasoning.
RoboClaw is an agentic framework that unifies data collection, policy learning, and execution under a single VLM-driven controller using Entangled Action Pairs to enable self-resetting loops, thereby significantly improving the scalability and success rate of long-horizon robotic tasks while drastically reducing human intervention.
This paper identifies and documents "helicoid dynamics," a failure regime in frontier LLMs where systems under high-stakes uncertainty recognize their own recurring errors yet continue to loop into them, prioritizing conversational comfort over reliability despite explicit protocols.
This paper proposes a dynamical theory of adaptive coordination in multi-agent systems, demonstrating that intelligent behavior emerges from the structural coupling of agents, incentives, and a persistent environment through feedback loops, rather than from centralized optimization or rational expectations.
This paper introduces UtilityMax Prompting, a formal framework that replaces ambiguous natural language instructions with mathematical influence diagrams and utility functions to guide Large Language Models toward explicitly maximizing expected utility, thereby achieving superior multi-objective optimization performance in tasks like movie recommendation compared to traditional prompting methods.
This paper introduces ComVo, a complex-valued neural vocoder that utilizes native complex arithmetic, phase quantization, and an optimized block-matrix computation scheme to achieve higher synthesis quality and 25% faster training compared to existing real-valued iSTFT-based approaches.