Image de couverture de livre

TorchUMM: A Unified Multimodal Model Codebase for Evaluation, Analysis, and Post-training

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Luo, Yinyi, Wang, Wenwen, Bai, Hayes, Zhu, Hongyu, Chen, Hao, He, Pan, Savvides, Marios, Li, Sharon, Wang, Jindong
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

LatentUMM: Dual Latent Alignment for Unified Multimodal Models
par: Luo, Yinyi, et autres
Publié: (2026)

UniPath: Adaptive Coordination of Understanding and Generation for Unified Multimodal Reasoning
par: Bai, Hayes, et autres
Publié: (2026)

Self-Corrected Image Generation with Explainable Latent Rewards
par: Luo, Yinyi, et autres
Publié: (2026)

KnowledgeSmith: Uncovering Knowledge Updating in LLMs with Model Editing and Unlearning
par: Luo, Yinyi, et autres
Publié: (2025)

FedUMM: A General Framework for Federated Learning with Unified Multimodal Models
par: Su, Zhaolong, et autres
Publié: (2026)

Image Tokenizer Needs Post-Training
par: Qiu, Kai, et autres
Publié: (2025)

MetaVLA: Unified Meta Co-training For Efficient Embodied Adaption
par: Li, Chen, et autres
Publié: (2025)

UniGame: Turning a Unified Multimodal Model Into Its Own Adversary
par: Su, Zhaolong, et autres
Publié: (2025)

A Unified Study of LoRA Variants: Taxonomy, Review, Codebase, and Empirical Evaluation
par: He, Haonan, et autres
Publié: (2026)

SOLAR: Scalable Optimization of Large-scale Architecture for Reasoning
par: Li, Chen, et autres
Publié: (2025)

An Embarrassingly Simple Baseline for Imbalanced Semi-Supervised Learning
par: Chen, Hao, et autres
Publié: (2022)

Robust Latent Matters: Boosting Image Generation with Sampling Error Synthesis
par: Qiu, Kai, et autres
Publié: (2025)

Conv-Adapter: Exploring Parameter Efficient Transfer Learning for ConvNets
par: Chen, Hao, et autres
Publié: (2022)

SciPost Physics Codebases
Publié: (2026)

ChatUMM: Robust Context Tracking for Conversational Interleaved Generation
par: Dai, Wenxun, et autres
Publié: (2026)

Rethinking UMM Visual Generation: Masked Modeling for Efficient Image-Only Pre-training
par: Sun, Peng, et autres
Publié: (2026)

PromptBench: A Unified Library for Evaluation of Large Language Models
par: Zhu, Kaijie, et autres
Publié: (2023)

Reward Evolution with Graph-of-Thoughts: A Bi-Level Language Model Framework for Reinforcement Learning
par: Yao, Changwei, et autres
Publié: (2025)

OpenWorldLib: A Unified Codebase and Definition of Advanced World Models
par: DataFlow Team, et autres
Publié: (2026)

RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation
par: Luo, Jane, et autres
Publié: (2025)

On Fairness of Unified Multimodal Large Language Model for Image Generation
par: Liu, Ming, et autres
Publié: (2025)

UniSD: Towards a Unified Self-Distillation Framework for Large Language Models
par: Jin, Yiqiao, et autres
Publié: (2026)

Self-Ensemble Post Learning for Noisy Domain Generalization
par: Lu, Wang, et autres
Publié: (2025)

RTGen: Generating Region-Text Pairs for Open-Vocabulary Object Detection
par: Chen, Fangyi, et autres
Publié: (2024)

Hierarchical Knowledge Graph Construction from Images for Scalable E-Commerce
par: Yang, Zhantao, et autres
Publié: (2024)

TorchTitan: One-stop PyTorch native solution for production ready LLM pre-training
par: Liang, Wanchao, et autres
Publié: (2024)

MASLab: A Unified and Comprehensive Codebase for LLM-based Multi-Agent Systems
par: Ye, Rui, et autres
Publié: (2025)

MotionVerse: A Unified Multimodal Framework for Motion Comprehension, Generation and Editing
par: Hou, Ruibing, et autres
Publié: (2025)

ExecuTorch -- A Unified PyTorch Solution to Run AI Models On-Device
par: Nachin, Mergen, et autres
Publié: (2026)

A CLIP-based Uncertainty Modal Modeling (UMM) Framework for Pedestrian Re-Identification in Autonomous Driving
par: Li, Jialin, et autres
Publié: (2025)

Efficient Autoregressive Audio Modeling via Next-Scale Prediction
par: Qiu, Kai, et autres
Publié: (2024)

FormulaCode: Evaluating Agentic Optimization on Large Codebases
par: Sehgal, Atharva, et autres
Publié: (2026)

Neural Radiance Fields with Torch Units
par: Ni, Bingnan, et autres
Publié: (2024)

STELAR-VISION: Self-Topology-Aware Efficient Learning for Aligned Reasoning in Vision
par: Li, Chen, et autres
Publié: (2025)

ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and Localization
par: Du, Bo, et autres
Publié: (2025)

torchtune: PyTorch native post-training library
par: Obozov, Mark, et autres
Publié: (2026)

SWE-Adept: An LLM-Based Agentic Framework for Deep Codebase Analysis and Structured Issue Resolution
par: He, Kang, et autres
Publié: (2026)

TinyLLaVA Factory: A Modularized Codebase for Small-scale Large Multimodal Models
par: Jia, Junlong, et autres
Publié: (2024)

When to Re-Commit: Temporal Abstraction Discovery for Long-Horizon Vision-Language Reasoning
par: Li, Chen, et autres
Publié: (2026)

Can Vision Replace Text in Working Memory? Evidence from Spatial n-Back in Vision-Language Models
par: Liang, Sichu, et autres
Publié: (2026)