📚 Research & Papers

[2603.24343] Enhancing Efficiency and Performance in Deepfake Audio Detection through Neuron-level Dropin & Neuroplasticity Mechanisms

Abstract page for arXiv paper 2603.24343: Enhancing Efficiency and Performance in Deepfake Audio Detection through Neuron-level Dropin & Neuroplasticity Mechanisms

[2603.16179] 360° Image Perception with MLLMs: A Comprehensive Benchmark and a Training-Free Method

Abstract page for arXiv paper 2603.16179: 360° Image Perception with MLLMs: A Comprehensive Benchmark and a Training-Free Method

[2603.11687] SemBench: A Universal Semantic Framework for LLM Evaluation

Abstract page for arXiv paper 2603.11687: SemBench: A Universal Semantic Framework for LLM Evaluation

[2603.11583] UtilityMax Prompting: A Formal Framework for Multi-Objective Large Language Model Optimization

Abstract page for arXiv paper 2603.11583: UtilityMax Prompting: A Formal Framework for Multi-Objective Large Language Model Optimization

[2603.11560] Theory of Dynamic Adaptive Coordination

Abstract page for arXiv paper 2603.11560: Theory of Dynamic Adaptive Coordination

[2603.11413] Evaluation format, not model capability, drives triage failure in the assessment of consumer health AI

Abstract page for arXiv paper 2603.11413: Evaluation format, not model capability, drives triage failure in the assessment of consumer health AI

[2603.16673] When Should a Robot Think? Resource-Aware Reasoning via Reinforcement Learning for Embodied Robotic Decision-Making

Abstract page for arXiv paper 2603.16673: When Should a Robot Think? Resource-Aware Reasoning via Reinforcement Learning for Embodied Robotic Decision-Making

[2603.10030] The DMA Streaming Framework: Kernel-Level Buffer Orchestration for High-Performance AI Data Paths

Abstract page for arXiv paper 2603.10030: The DMA Streaming Framework: Kernel-Level Buffer Orchestration for High-Performance AI Data Paths

[2603.06663] Graph-of-Mark: Promote Spatial Reasoning in Multimodal Language Models with Graph-Based Visual Prompting

Abstract page for arXiv paper 2603.06663: Graph-of-Mark: Promote Spatial Reasoning in Multimodal Language Models with Graph-Based Visual Prompting

[2603.14294] Seeking Physics in Diffusion Noise

Abstract page for arXiv paper 2603.14294: Seeking Physics in Diffusion Noise

[2601.07325] Robust Bayesian Inference via Variational Approximations of Generalized Rho-Posteriors

Abstract page for arXiv paper 2601.07325: Robust Bayesian Inference via Variational Approximations of Generalized Rho-Posteriors

[2512.22854] ByteLoom: Weaving Geometry-Consistent Human-Object Interactions through Progressive Curriculum Learning

Abstract page for arXiv paper 2512.22854: ByteLoom: Weaving Geometry-Consistent Human-Object Interactions through Progressive Curriculum Learning

[2512.05245] STAR-GO: Improving Protein Function Prediction by Learning to Hierarchically Integrate Ontology-Informed Semantic Embeddings

Abstract page for arXiv paper 2512.05245: STAR-GO: Improving Protein Function Prediction by Learning to Hierarchically Integrate Ontology-Informed Semantic Embeddings

[2601.12910] SciCoQA: Quality Assurance for Scientific Paper--Code Alignment

Abstract page for arXiv paper 2601.12910: SciCoQA: Quality Assurance for Scientific Paper--Code Alignment

[2601.09600] Information Access of the Oppressed: A Problem-Posing Framework for Envisioning Emancipatory Information Access Platforms

Abstract page for arXiv paper 2601.09600: Information Access of the Oppressed: A Problem-Posing Framework for Envisioning Emancipatory Information Access Platforms

[2511.14427] Self-Supervised Multisensory Pretraining for Contact-Rich Robot Reinforcement Learning

Abstract page for arXiv paper 2511.14427: Self-Supervised Multisensory Pretraining for Contact-Rich Robot Reinforcement Learning

[2601.08881] TAG-MoE: Task-Aware Gating for Unified Generative Mixture-of-Experts

Abstract page for arXiv paper 2601.08881: TAG-MoE: Task-Aware Gating for Unified Generative Mixture-of-Experts

[2511.04454] Fitting Reinforcement Learning Model to Behavioral Data under Bandits

Abstract page for arXiv paper 2511.04454: Fitting Reinforcement Learning Model to Behavioral Data under Bandits

[2601.06394] Context Matters: Peer-Aware Student Behavioral Engagement Measurement via VLM Action Parsing and LLM Sequence Classification

Abstract page for arXiv paper 2601.06394: Context Matters: Peer-Aware Student Behavioral Engagement Measurement via VLM Action Parsing and LLM Sequence Classification

[2511.01464] Split-Flows: Measure Transport and Information Loss Across Molecular Resolutions

Abstract page for arXiv paper 2511.01464: Split-Flows: Measure Transport and Information Loss Across Molecular Resolutions