paper-with-me

Papers

Memory Bear AI Memory Science Engine for Multimodal Affective Intelligence: A Technical Report

2026-03-18 · Deliang Wen, Ke Sun, Yu Wang arxiv

Affective judgment in real interaction is rarely a purely local prediction problem. Emotional meaning often depends on prior trajectory, accumulated context, and multimodal evidence that may be weak, noisy, or incomplete at the current moment. Although multimodal emotion recognition (MER) has improved the integration of text, speech, and visual signals, many existing systems remain optimized for short-range inference and provide limited support for persistent affective memory, long-horizon dependency modeling, and robust interpretation under imperfect input. This technical report presents the Memory Bear AI Memory Science Engine, a memory-centered framework for multimodal affective intelligence. Instead of treating emotion as a transient output label, the framework models affective information as a structured and evolving variable within a memory system. It organizes processing through structured memory formation, working-memory aggregation, long-term consolidation, memory-driven retrieval, dynamic fusion calibration, and continuous memory updating. At its core, multimodal signals are transformed into structured Emotion Memory Units (EMUs), enabling affective information to be preserved, reactivated, and revised across interaction horizons. Experimental results show consistent gains over comparison systems across benchmark and business-grounded settings, with stronger accuracy and robustness, especially under noisy or missing-modality conditions. The framework offers a practical step from local emotion recognition toward more continuous, robust, and deployment-relevant affective intelligence.

📄 PDF Abstract BibTeX arXiv:2603.22306

Code (0)

등록된 구현이 없습니다.

Tasks

Multimodal Emotion Recognition

Similar Papers 제목 키워드 기반

Memory Bear AI A Breakthrough from Memory to Cognition Toward Artificial General Intelligence

2025-12-17 · Deliang Wen, Ke Sun arxiv

Large language models (LLMs) face inherent limitations in memory, including restricted context windows, long-term knowledge forgetting, redundant information accumulation, and hallucination generation. These issues sever…

Does Spatial Cognition Emerge in Frontier Models?

2024-10-09 · Santhosh Kumar Ramakrishnan, Erik Wijmans, Philipp Kraehenbuehl, Vladlen Koltun

Not yet. We present SPACE, a benchmark that systematically evaluates spatial cognition in frontier models. Our benchmark builds on decades of research in cognitive science. It evaluates large-scale mapping abilities that…

AUGUSTUS: An LLM-Driven Multimodal Agent System with Contextualized User Memory

2025-10-17 · Jitesh Jain, Shubham Maheshwari, Ning Yu, Wen-mei Hwu 외 arxiv

Riding on the success of LLMs with retrieval-augmented generation (RAG), there has been a growing interest in augmenting agent systems with external memory databases. However, the existing systems focus on storing text i…

AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agents

2025-12-29 · Jiafeng Liang, Hao Li, Chang Li, Jiaqi Zhou 외 arxiv

Memory serves as the pivotal nexus bridging past and future, providing both humans and AI systems with invaluable concepts and experience to navigate complex tasks. Recent research on autonomous agents has increasingly f…

BEAR: Sketching BFGS Algorithm for Ultra-High Dimensional Feature Selection in Sublinear Memory

2020-10-26 · Amirali Aghazadeh, Vipul Gupta, Alex DeWeese, O. Ozan Koyluoglu 외

We consider feature selection for applications in machine learning where the dimensionality of the data is so large that it exceeds the working memory of the (local) computing machine. Unfortunately, current large-scale …

feature selection