Image de couverture de livre

Position: Weight Space Should Be a First-Class Generative AI Modality

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Zhangyang, Wang, Peihao, Wang, Kai
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights
par: Liang, Zhiyuan, et autres
Publié: (2025)

Recurrent Diffusion for Large-Scale Parameter Generation
par: Wang, Kai, et autres
Publié: (2025)

Junk DNA Hypothesis: Pruning Small Pre-Trained Weights Irreversibly and Monotonically Impairs "Difficult" Downstream Tasks in LLMs
par: Yin, Lu, et autres
Publié: (2023)

Position: AI Evaluations Should be Grounded on a Theory of Capability
par: Jo, Nathanael, et autres
Publié: (2025)

Why Neural Network Can Discover Symbolic Structures with Gradient-based Training: An Algebraic and Geometric Foundation for Neurosymbolic Reasoning
par: Wang, Peihao, et autres
Publié: (2025)

Neon: Negative Extrapolation From Self-Training Improves Image Generation
par: Alemohammad, Sina, et autres
Publié: (2025)

Data Distribution as a Lever for Guiding Optimizers Toward Superior Generalization in LLMs
par: Gangavarapu, Tushaar, et autres
Publié: (2026)

Position: AI Security Policy Should Target Systems, Not Models
par: Riegler, Michael A., et autres
Publié: (2026)

PIPA: Preference Alignment as Prior-Informed Statistical Estimation
par: Li, Junbo, et autres
Publié: (2025)

Generalization Error Analysis for Sparse Mixture-of-Experts: A Preliminary Study
par: Zhao, Jinze, et autres
Publié: (2024)

Generative Modeling of Class Probability for Multi-Modal Representation Learning
par: Shin, Jungkyoo, et autres
Publié: (2025)

Position: Capability Control Should be a Separate Goal From Alignment
par: Siddiqui, Shoaib Ahmed, et autres
Publié: (2026)

When Are Teacher Tokens Reliable? Position-Weighted On-Policy Self-Distillation for Reasoning
par: Liu, Xiaogeng, et autres
Publié: (2026)

Position: AI Scaling: From Up to Down and Out
par: Wang, Yunke, et autres
Publié: (2025)

When Is Rank-1 Steering Cheap? Geometry, Granularity, and Budgeted Search
par: Robertson, John T., et autres
Publié: (2026)

Reconciling In-Context and In-Weight Learning via Dual Representation Space Encoding
par: Chen, Guanyu, et autres
Publié: (2026)

On The Planning Abilities of OpenAI's o1 Models: Feasibility, Optimality, and Generalizability
par: Wang, Kevin, et autres
Publié: (2024)

Improved Generalization of Weight Space Networks via Augmentations
par: Shamsian, Aviv, et autres
Publié: (2024)

Position: Beyond Euclidean -- Foundation Models Should Embrace Non-Euclidean Geometries
par: He, Neil, et autres
Publié: (2025)

Neurosymbolic LoRA: Why and When to Tune Weights vs. Rewrite Prompts
par: Wang, Kevin, et autres
Publié: (2026)

Estimating Worst-Case Frontier Risks of Open-Weight LLMs
par: Wallace, Eric, et autres
Publié: (2025)

LLaGA: Large Language and Graph Assistant
par: Chen, Runjin, et autres
Publié: (2024)

Revolutionizing Biomarker Discovery: Leveraging Generative AI for Bio-Knowledge-Embedded Continuous Space Exploration
par: Ying, Wangyang, et autres
Publié: (2024)

Fair Class-Incremental Learning using Sample Weighting
par: Park, Jaeyoung, et autres
Publié: (2024)

Position: We Need An Algorithmic Understanding of Generative AI
par: Eberle, Oliver, et autres
Publié: (2025)

Cross-Modality Controlled Molecule Generation with Diffusion Language Model
par: Zhang, Yunzhe, et autres
Publié: (2025)

LLM4XCE: Large Language Models for Extremely Large-Scale Massive MIMO Channel Estimation
par: Li, Renbin, et autres
Publié: (2025)

NNiT: Width-Agnostic Neural Network Generation with Structurally Aligned Weight Spaces
par: Kim, Jiwoo, et autres
Publié: (2026)

We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systems
par: Fang, Junfeng, et autres
Publié: (2025)

Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs
par: Song, Xiangchen, et autres
Publié: (2025)

Learning and Generating Diverse Residential Load Patterns Using GAN with Weakly-Supervised Training and Weight Selection
par: Liang, Xinyu, et autres
Publié: (2025)

How Should We Meta-Learn Reinforcement Learning Algorithms?
par: Goldie, Alexander David, et autres
Publié: (2025)

Artificial Geographically Weighted Neural Network: A Novel Framework for Spatial Analysis with Geographically Weighted Layers
par: Cao, Jianfei, et autres
Publié: (2025)

Temporal Imbalance of Positive and Negative Supervision in Class-Incremental Learning
par: Ma, Jinge, et autres
Publié: (2026)

Representation Learning with Mutual Influence of Modalities for Node Classification in Multi-Modal Heterogeneous Networks
par: Li, Jiafan, et autres
Publié: (2025)

Not Every AI Problem is a Data Problem: We Should Be Intentional About Data Scaling
par: Rodchenko, Tanya, et autres
Publié: (2025)

AI Should Sense Better, Not Just Scale Bigger: Adaptive Sensing as a Paradigm Shift
par: Baek, Eunsu, et autres
Publié: (2025)

GAMMA: Global Bit Allocation for Mixed-Precision Models under Arbitrary Budgets
par: Yao, Zhangyang, et autres
Publié: (2026)

Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference
par: Dong, Harry, et autres
Publié: (2024)

When Should an AI Workflow Release? Always-Valid Inference for Black-Box Generate-Verify Systems
par: Cho, Young Hyun, et autres
Publié: (2026)