This paper proposes a Bayesian Optimization-based framework for multipath QUIC (MPQUIC) scheduling that jointly considers maximum upload completion time and total LTE usage, identifying Pareto-efficie…

This paper introduces Audio-Dependency Filtering (ADF) pipeline for Audio-Dependent Question Answering (ADQA) task in DCASE~2026, achieving top overall and sub-10B accuracy.

The PopQuiz Attack is a novel black-box membership inference attack that successfully tests whether large language models memorize specific training data by framing the target data as multiple-choice…

The paper demonstrates that while distilling large language models for medical QA can significantly improve final answer accuracy, this gain often comes at the cost of factual accuracy and detailed re…

The paper introduces MechVQA, a comprehensive dataset and benchmark for mechanical drawing understanding, and proposes the MechVL model, which significantly improves Multimodal LLMs' performance on th…

This paper introduces phase-to-primitive decomposition to enable Monte Carlo tree search (MCTS) on in-memory computing (IMC) systems, achieving significant energy efficiency and performance improvemen…

The authors identify confusion patterns in a large audio-language model and use them to curate diagnostic data for fine-tuning, achieving higher accuracy than the baseline.

The paper introduces MedPMC, a framework that transforms permissively licensed literature into high-fidelity infrastructure for medical multimodal models, resulting in improved performance on various…

This paper proposes CertifiedCacheMPC, a caching system for Model Predictive Control in hierarchical quadruped controllers, ensuring primal feasibility and cost suboptimality.

This paper analyzes direction-of-arrival estimation using a tunable receive-side lossless reciprocal MiLAC combiner for antenna arrays and shows it can achieve the digital Cramér-Rao bound with fewer…

The paper introduces OmniMatBench, a comprehensive, human-calibrated multimodal reasoning benchmark covering 19 materials science subfields, revealing that current multimodal language models (MLLMs) h…

The paper introduces CA-AC-MPC, a CUDA-accelerated variant of Actor-Critic Model Predictive Control, which significantly reduces the training and inference latency of AC-MPC while maintaining state-of…

CRAFTQA introduces a novel adaptive, code-driven framework that significantly enhances complex structured data reasoning by dynamically generating custom code functions beyond predefined operations.

The paper introduces OCC-RAG, a family of compact, task-specialized Small Language Models (SLMs) designed to achieve highly faithful, multi-hop question answering grounded strictly in provided context…

The paper proposes a question-aware evidence ledger pipeline that significantly improves video relational reasoning by explicitly guiding the model to extract necessary evidence for complex spatial, t…

The paper introduces a Variational Encrypted Model Predictive Control (VEMPC) protocol that enables online MPC execution using only encrypted polynomial operations, eliminating the need for intermedia…

The paper proposes CoMet, a method for uncertainty estimation in multimodal large language models, which decomposes uncertainty into context-specific and multiplicity-specific terms.

This paper proposes a new method for AC/DC Power Factor Correction in single-phase On-Board Chargers for Electric Vehicles using a duty cycle predictive Model Predictive Current Control with real-time…

The paper introduces Brain-IT-VQA, a novel framework that significantly improves visual question answering from fMRI signals, and presents NSD-VQA, a new, highly controlled dataset for this task.