Imagen de Portada

Universal Smoothness via Bernstein Polynomials: A Constructive Approximation Approach for Activation Functions

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Wentao, Zhang, Yutong, Zhu, Yifan, Mo, Wentao
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Bridging the Gap between 2D and 3D Visual Question Answering: A Fusion Approach for 3D VQA
por: Mo, Wentao, et al.
Publicado: (2024)

Distilling Neuro-Symbolic Programs into 3D Multi-modal LLMs
por: Mo, Wentao, et al.
Publicado: (2026)

VecCity: A Taxonomy-guided Library for Map Entity Representation Learning
por: Zhang, Wentao, et al.
Publicado: (2024)

Language Models Represent Beliefs of Self and Others
por: Zhu, Wentao, et al.
Publicado: (2024)

Vote-Tree-Planner: Optimizing Execution Order in LLM-based Task Planning Pipeline via Voting
por: Zhang, Chaoyuan, et al.
Publicado: (2025)

Can LLMs be Good Graph Judge for Knowledge Graph Construction?
por: Huang, Haoyu, et al.
Publicado: (2024)

Deconfounded Time Series Forecasting: A Causal Inference Approach
por: Gao, Wentao, et al.
Publicado: (2024)

TPC-ViT: Token Propagation Controller for Efficient Vision Transformer
por: Zhu, Wentao
Publicado: (2024)

STRAP: Spatio-Temporal Pattern Retrieval for Out-of-Distribution Generalization
por: Zhang, Haoyu, et al.
Publicado: (2025)

Efficient Multiscale Multimodal Bottleneck Transformer for Audio-Video Classification
por: Zhu, Wentao
Publicado: (2024)

Efficient Selective Audio Masked Multimodal Bottleneck Transformer for Audio-Video Classification
por: Zhu, Wentao
Publicado: (2024)

DataCross: A Unified Benchmark and Agent Framework for Cross-Modal Heterogeneous Data Analysis
por: Qi, Ruyi, et al.
Publicado: (2026)

Bias in Decision-Making for AI's Ethical Dilemmas: A Comparative Study of ChatGPT and Claude
por: Xu, Wentao, et al.
Publicado: (2025)

ORACLE: Optimizing Reasoning Abilities of Large Language Models via Constraint-Led Synthetic Data Elicitation
por: Yang, Zhuojie, et al.
Publicado: (2026)

Exponential Approximation Rates and Parameter Efficiency of Learnable Bernstein Activations
por: Albool, Ibrahim, et al.
Publicado: (2026)

Rethinking and Accelerating Graph Condensation: A Training-Free Approach with Class Partition
por: Gao, Xinyi, et al.
Publicado: (2024)

TRACER: Turn-level Regret Matching with Inner Reinforcement Credit for Cooperative Multi-LLM Reasoning
por: Li, Chusen, et al.
Publicado: (2026)

Seeing the Unseen: Learning Basis Confounder Representations for Robust Traffic Prediction
por: Ji, Jiahao, et al.
Publicado: (2023)

TransDex: Pre-training Visuo-Tactile Policy with Point Cloud Reconstruction for Dexterous Manipulation of Transparent Objects
por: Li, Fengguan, et al.
Publicado: (2026)

The Curse of Helpfulness: Inverse Scaling Law in Robustness to Distractor Instructions via DistractionIF
por: Su, Zeli, et al.
Publicado: (2026)

Embodied Representation Alignment with Mirror Neurons
por: Zhu, Wentao, et al.
Publicado: (2025)

VerifyBench: A Systematic Benchmark for Evaluating Reasoning Verifiers Across Domains
por: Li, Xuzhao, et al.
Publicado: (2025)

Certainty-Guided Reasoning in Large Language Models: A Dynamic Thinking Budget Approach
por: Nogueira, João Paulo, et al.
Publicado: (2025)

From Chat Logs to Collective Insights: Aggregative Question Answering
por: Zhang, Wentao, et al.
Publicado: (2025)

Paper2SysArch: Structure-Constrained System Architecture Generation from Scientific Papers
por: Guo, Ziyi, et al.
Publicado: (2025)

Arbitrary Time Information Modeling via Polynomial Approximation for Temporal Knowledge Graph Embedding
por: Fang, Zhiyu, et al.
Publicado: (2024)

Characterization of Political Polarized Users Attacked by Language Toxicity on Twitter
por: Xu, Wentao
Publicado: (2024)

Budget-aware Query Tuning: An AutoML Perspective
por: Wu, Wentao, et al.
Publicado: (2024)

Bridging Dual Knowledge Graphs for Multi-Hop Question Answering in Construction Safety
por: Zhang, Yuxin, et al.
Publicado: (2025)

A Unified and General Humanoid Whole-Body Controller for Versatile Locomotion
por: Xue, Yufei, et al.
Publicado: (2025)

Beyond Explicit Refusals: Soft-Failure Attacks on Retrieval-Augmented Generation
por: Zhang, Wentao, et al.
Publicado: (2026)

Leash: Adaptive Length Penalty and Reward Shaping for Efficient Large Reasoning Model
por: Li, Yanhao, et al.
Publicado: (2025)

The Impact of Big Five Personality Traits on AI Agent Decision-Making in Public Spaces: A Social Simulation Study
por: Ren, Mingjun, et al.
Publicado: (2025)

Interactive Training: Feedback-Driven Neural Network Optimization
por: Zhang, Wentao, et al.
Publicado: (2025)

VisualTrap: A Stealthy Backdoor Attack on GUI Agents via Visual Grounding Manipulation
por: Ye, Ziang, et al.
Publicado: (2025)

Chebyshev Polynomial-Based Kolmogorov-Arnold Networks: An Efficient Architecture for Nonlinear Function Approximation
por: SS, Sidharth, et al.
Publicado: (2024)

AppAgent-Pro: A Proactive GUI Agent System for Multidomain Information Integration and User Assistance
por: Zhao, Yuyang, et al.
Publicado: (2025)

A Dataset of Open-Domain Question Answering with Multiple-Span Answers
por: Luo, Zhiyi, et al.
Publicado: (2024)

Rotated Runtime Smooth: Training-Free Activation Smoother for accurate INT4 inference
por: Yi, Ke, et al.
Publicado: (2024)

FinWorld: An All-in-One Open-Source Platform for End-to-End Financial AI Research and Deployment
por: Zhang, Wentao, et al.
Publicado: (2025)