Imagen de Portada

OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ong, Keane, Boughorbel, Sabri, Xiao, Luwei, Ekbote, Chanakya, Dai, Wei, Qu, Ao, Wu, Jingyao, Mao, Rui, Hoque, Ehsan, Cambria, Erik, Mengaldo, Gianmarco, Liang, Paul Pu
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

ClimaEmpact: Domain-Aligned Small Language Models and Datasets for Extreme Weather Analytics
por: Varshney, Deeksha, et al.
Publicado: (2025)

Towards Robust ESG Analysis Against Greenwashing Risks: Aspect-Action Analysis with Cross-Category Generalization
por: Ong, Keane, et al.
Publicado: (2025)

Deriving Strategic Market Insights with Large Language Models: A Benchmark for Forward Counterfactual Generation
por: Ong, Keane, et al.
Publicado: (2025)

Enhancing Language Models for Robust Greenwashing Detection
por: Braun, Neil Heinrich, et al.
Publicado: (2026)

Human Behavior Atlas: Benchmarking Unified Psychological and Social Behavior Understanding
por: Ong, Keane, et al.
Publicado: (2025)

FinXABSA: Explainable Finance through Aspect-Based Sentiment Analysis
por: Ong, Keane, et al.
Publicado: (2023)

Leveraging LLMS for Top-Down Sector Allocation In Automated Trading
por: Heng, Ryan Quek Wei, et al.
Publicado: (2025)

Explainable Natural Language Processing for Corporate Sustainability Analysis
por: Ong, Keane, et al.
Publicado: (2024)

ESGSenticNet: A Neurosymbolic Knowledge Base for Corporate Sustainability Analysis
por: Ong, Keane, et al.
Publicado: (2025)

QoQ-Med: Building Multimodal Clinical Foundation Models with Domain-Aware GRPO Training
por: Dai, Wei, et al.
Publicado: (2025)

Explain the Black Box for the Sake of Science: the Scientific Method in the Era of Generative Artificial Intelligence
por: Mengaldo, Gianmarco
Publicado: (2024)

Understanding the Emergence of Multimodal Representation Alignment
por: Tjandrasuwita, Megan, et al.
Publicado: (2025)

Beyond Correlation: Refutation-Validated Aspect-Based Sentiment Analysis for Explainable Energy Market Returns
por: van der Heever, Wihan, et al.
Publicado: (2026)

Dynamical errors in machine learning forecasts
por: Fang, Zhou, et al.
Publicado: (2025)

SCATR: Simple Calibrated Test-Time Ranking
por: Shyamal, Divya, et al.
Publicado: (2026)

TAMP: Token-Adaptive Layerwise Pruning in Multimodal Large Language Models
por: Lee, Jaewoo, et al.
Publicado: (2025)

Improving Language Models Trained on Translated Data with Continual Pre-Training and Dictionary Learning Analysis
por: Boughorbel, Sabri, et al.
Publicado: (2024)

eXIAA: eXplainable Injections for Adversarial Attack
por: Pesce, Leonardo, et al.
Publicado: (2025)

Hierarchy of extreme-event predictability in turbulence revealed by machine learning
por: Yang, Yuxuan, et al.
Publicado: (2026)

Revisiting the robustness of post-hoc interpretability methods
por: Wei, Jiawen, et al.
Publicado: (2024)

Beyond the Leaderboard: Understanding Performance Disparities in Large Language Models via Model Diffing
por: Boughorbel, Sabri, et al.
Publicado: (2025)

Explainable AI: Learning from the Learners
por: Vinuesa, Ricardo, et al.
Publicado: (2026)

Explore the Use of Time Series Foundation Model for Car-Following Behavior Analysis
por: Zeng, Luwei, et al.
Publicado: (2025)

Continual Learning from Simulated Interactions via Multitask Prospective Rehearsal for Bionic Limb Behavior Modeling
por: Dey, Sharmita, et al.
Publicado: (2024)

Exploring Cognitive and Aesthetic Causality for Multimodal Aspect-Based Sentiment Analysis
por: Xiao, Luwei, et al.
Publicado: (2025)

What One Cannot, Two Can: Two-Layer Transformers Provably Represent Induction Heads on Any-Order Markov Chains
por: Ekbote, Chanakya, et al.
Publicado: (2025)

Evaluation of post-hoc interpretability methods in time-series classification
por: Turbé, Hugues, et al.
Publicado: (2022)

ProtoS-ViT: Visual foundation models for sparse self-explainable classifications
por: Turbé, Hugues, et al.
Publicado: (2024)

Tell me why: Visual foundation models as self-explainable classifiers
por: Turbé, Hugues, et al.
Publicado: (2025)

Explainability matters: The effect of liability rules on the healthcare sector
por: Wei, Jiawen, et al.
Publicado: (2025)

Harf-Speech: A Clinically Aligned Framework for Arabic Phoneme-Level Speech Assessment
por: Azad, Asif, et al.
Publicado: (2026)

From Query to Explanation: Uni-RAG for Multi-Modal Retrieval-Augmented Learning in STEM
por: Wu, Xinyi, et al.
Publicado: (2025)

A Systematic Analysis of Biases in Large Language Models
por: Zhang, Xulang, et al.
Publicado: (2025)

Affective Flow Language Model for Emotional Support Conversation
por: Zou, Chenghui, et al.
Publicado: (2026)

Design and Evaluation of a Culturally Adapted Multimodal Virtual Agent for PTSD Screening
por: Ozel, Cengiz, et al.
Publicado: (2026)

Local to Global: Learning Dynamics and Effect of Initialization for Transformers
por: Makkuva, Ashok Vardhan, et al.
Publicado: (2024)

MURPHY: Feedback-Aware GRPO with Retrospective Credit Assignment for Multi-Turn Code Generation
por: Ekbote, Chanakya, et al.
Publicado: (2025)

MiniMind-O Technical Report: An Open Small-Scale Speech-Native Omni Model
por: Gong, Jingyao
Publicado: (2026)

SapiensID: Foundation for Human Recognition
por: Kim, Minchul, et al.
Publicado: (2025)

Sapiens: Foundation for Human Vision Models
por: Khirodkar, Rawal, et al.
Publicado: (2024)