Image de couverture de livre

VisGym: Diverse, Customizable, Scalable Environments for Multimodal Agents

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Zirui, Zhang, Junyi, Ge, Jiaxin, Lian, Long, Fu, Letian, Dunlap, Lisa, Goldberg, Ken, Wang, XuDong, Stoica, Ion, Chan, David M., Min, Sewon, Gonzalez, Joseph E.
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents
par: Jain, Naman, et autres
Publié: (2025)

Constantly Improving Image Models Need Constantly Improving Benchmarks
par: Ge, Jiaxin, et autres
Publié: (2025)

Some Present-Day Problems of Romanian Library Science
par: Stoica, Ion
Publié: (1973)

The Central University Library, Bucharest. Over Seventy-five Years in the History of a Collection
par: Stoica, Ion
Publié: (1972)

Visually Prompted Benchmarks Are Surprisingly Fragile
par: Feng, Haiwen, et autres
Publié: (2025)

From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline
par: Li, Tianle, et autres
Publié: (2024)

VisionArena: 230K Real World User-VLM Conversations with Preference Labels
par: Chou, Christopher, et autres
Publié: (2024)

M$^2$RNN: Non-Linear RNNs with Matrix-Valued States for Scalable Language Modeling
par: Mishra, Mayank, et autres
Publié: (2026)

EconGym: A Scalable AI Testbed with Diverse Economic Tasks
par: Mi, Qirui, et autres
Publié: (2025)

CLI-Gym: Scalable CLI Task Generation via Agentic Environment Inversion
par: Lin, Yusong, et autres
Publié: (2026)

Reconstruction Alignment Improves Unified Multimodal Models
par: Xie, Ji, et autres
Publié: (2025)

AExGym: Benchmarks and Environments for Adaptive Experimentation
par: Wang, Jimmy, et autres
Publié: (2024)

AgentGym: Evolving Large Language Model-based Agents across Diverse Environments
par: Xi, Zhiheng, et autres
Publié: (2024)

EO-Gym: A Multimodal, Interactive Environment for Earth Observation Agents
par: Ma, Sai, et autres
Publié: (2026)

OmniThoughtVis: A Scalable Distillation Pipeline for Deployable Multimodal Reasoning Models
par: Yue, Yuanhao, et autres
Publié: (2026)

MedAgentGym: A Scalable Agentic Training Environment for Code-Centric Reasoning in Biomedical Data Science
par: Xu, Ran, et autres
Publié: (2025)

K-Search: LLM Kernel Generation via Co-Evolving Intrinsic World Model
par: Cao, Shiyi, et autres
Publié: (2026)

Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens
par: Qin, Yiming, et autres
Publié: (2025)

ClawEnvKit: Automatic Environment Generation for Claw-Like Agents
par: Li, Xirui, et autres
Publié: (2026)

Rethinking Patch Dependence for Masked Autoencoders
par: Fu, Letian, et autres
Publié: (2024)

A Touch, Vision, and Language Dataset for Multimodal Alignment
par: Fu, Letian, et autres
Publié: (2024)

Online Dynamic Goal Recognition in Gym Environments
par: Matan, Shamir, et autres
Publié: (2025)

pyRDDLGym: From RDDL to Gym Environments
par: Taitler, Ayal, et autres
Publié: (2022)

DS SERVE: A Framework for Efficient and Scalable Neural Retrieval
par: Liu, Jinjian, et autres
Publié: (2025)

HistoGym: A Reinforcement Learning Environment for Histopathological Image Analysis
par: Liu, Zhi-Bo, et autres
Publié: (2024)

OceanGym: A Benchmark Environment for Underwater Embodied Agents
par: Xue, Yida, et autres
Publié: (2025)

FogROS2-FT: Fault Tolerant Cloud Robotics
par: Chen, Kaiyuan, et autres
Publié: (2024)

OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning
par: Liu, Yanqing, et autres
Publié: (2025)

UserBench: An Interactive Gym Environment for User-Centric Agents
par: Qian, Cheng, et autres
Publié: (2025)

CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents
par: Wang, Bowen, et autres
Publié: (2026)

Post-Training Sparse Attention with Double Sparsity
par: Yang, Shuo, et autres
Publié: (2024)

UnSAMv2: Self-Supervised Learning Enables Segment Anything at Any Granularity
par: Yu, Junwei, et autres
Publié: (2025)

Segment Anything without Supervision
par: Wang, XuDong, et autres
Publié: (2024)

PC-Gym: Benchmark Environments For Process Control Problems
par: Bloor, Maximilian, et autres
Publié: (2024)

WorldGym: World Model as An Environment for Policy Evaluation
par: Quevedo, Julian, et autres
Publié: (2025)

Gym-Anything: Turn any Software into an Agent Environment
par: Aggarwal, Pranjal, et autres
Publié: (2026)

Deep Reinforcement Learning for Scalable Multiagent Spacecraft Inspection
par: Dunlap, Kyle, et autres
Publié: (2024)

LEANN: A Low-Storage Vector Index
par: Wang, Yichuan, et autres
Publié: (2025)

Break the Sequential Dependency of LLM Inference Using Lookahead Decoding
par: Fu, Yichao, et autres
Publié: (2024)

Revisiting Cache Freshness for Emerging Real-Time Applications
par: Mao, Ziming, et autres
Publié: (2024)