Copertina

Quantifying Multimodal Capabilities: Formal Generalization Guarantees in Pairwise Metric Learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhou, Richeng, Zhang, Xuelin, Liu, Liyuan
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

On the Stability and Generalization of First-order Bilevel Minimax Optimization
di: Zhang, Xuelin, et al.
Pubblicazione: (2026)

Learning to Generate Formally Verifiable Step-by-Step Logic Reasoning via Structured Formal Intermediaries
di: Chen, Luoxin, et al.
Pubblicazione: (2026)

Gradient Compression May Hurt Generalization: A Remedy by Synthetic Data Guided Sharpness Aware Minimization
di: Gu, Yujie, et al.
Pubblicazione: (2026)

Less is More: Multimodal Region Representation via Pairwise Inter-view Learning
di: Namgung, Min, et al.
Pubblicazione: (2025)

Theoretical Analysis of Meta Reinforcement Learning: Generalization Bounds and Convergence Guarantees
di: Wang, Cangqing, et al.
Pubblicazione: (2024)

Decipher the Modality Gap in Multimodal Contrastive Learning: From Convergent Representations to Pairwise Alignment
di: Yi, Lingjie, et al.
Pubblicazione: (2025)

Pairwise Difference Learning for Classification
di: Belaid, Mohamed Karim, et al.
Pubblicazione: (2024)

Meta Additive Model: Interpretable Sparse Learning With Auto Weighting
di: Zhang, Xuelin, et al.
Pubblicazione: (2026)

Deep Metric Loss for Multimodal Learning
di: Moon, Sehwan, et al.
Pubblicazione: (2023)

Quantifying the Capability Boundary of DeepSeek Models: An Application-Driven Performance Analysis
di: Zhao, Kaikai, et al.
Pubblicazione: (2025)

Annealed Co-Generation: Disentangling Variables via Progressive Pairwise Modeling
di: Zhang, Hantao, et al.
Pubblicazione: (2026)

A3S: A General Active Clustering Method with Pairwise Constraints
di: Deng, Xun, et al.
Pubblicazione: (2024)

Reinforcement Learning for Control with Probabilistic Stability Guarantee: A Finite-Sample Approach
di: Han, Minghao, et al.
Pubblicazione: (2026)

GAR: Generative Adversarial Reinforcement Learning for Formal Theorem Proving
di: Wang, Ruida, et al.
Pubblicazione: (2025)

On the Learn-to-Optimize Capabilities of Transformers in In-Context Sparse Recovery
di: Liu, Renpu, et al.
Pubblicazione: (2024)

Fine-grained Analysis of Stability and Generalization for Stochastic Bilevel Optimization
di: Zhang, Xuelin, et al.
Pubblicazione: (2026)

Reinforcement Learning with Pairwise Preferences in Long-Term Decision Problems
di: Carr, Jonathan Colaço, et al.
Pubblicazione: (2026)

Fast and Featureless Node Representation Learning with Partial Pairwise Supervision
di: Chakraborty, Sujan, et al.
Pubblicazione: (2026)

Local Pairwise Distance Matching for Backpropagation-Free Reinforcement Learning
di: Tanneberg, Daniel
Pubblicazione: (2025)

Quantifying the Capabilities of LLMs across Scale and Precision
di: Badshah, Sher, et al.
Pubblicazione: (2024)

Generalization Capability for Imitation Learning
di: Wang, Yixiao
Pubblicazione: (2025)

Efficient Quantization of Mixture-of-Experts with Theoretical Generalization Guarantees
di: Chowdhury, Mohammed Nowaz Rabbani, et al.
Pubblicazione: (2026)

Optimal Embedding Learning Rate in LLMs: The Effect of Vocabulary Size
di: Hayou, Soufiane, et al.
Pubblicazione: (2025)

Bounded-Abstention Pairwise Learning to Rank
di: Ferrara, Antonio, et al.
Pubblicazione: (2025)

Debiasing Reward Models by Representation Learning with Guarantees
di: Ng, Ignavier, et al.
Pubblicazione: (2025)

PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees
di: Xie, Chulin, et al.
Pubblicazione: (2023)

Deciphering Raw Data in Neuro-Symbolic Learning with Provable Guarantees
di: Tao, Lue, et al.
Pubblicazione: (2023)

Hierarchical Reinforcement Learning for Optimal Agent Grouping in Cooperative Systems
di: Hu, Liyuan
Pubblicazione: (2025)

Pairwise Calibrated Rewards for Pluralistic Alignment
di: Halpern, Daniel, et al.
Pubblicazione: (2025)

Shift of Pairwise Similarities for Data Clustering
di: Chehreghani, Morteza Haghir
Pubblicazione: (2021)

Trust the uncertain teacher: distilling dark knowledge via calibrated uncertainty
di: Kim, Jeonghyun, et al.
Pubblicazione: (2026)

Preference-based Reinforcement Learning beyond Pairwise Comparisons: Benefits of Multiple Options
di: Lee, Joongkyu, et al.
Pubblicazione: (2025)

On the Representation of Pairwise Causal Background Knowledge and Its Applications in Causal Inference
di: Fang, Zhuangyan, et al.
Pubblicazione: (2022)

Gradient Aligned Regression via Pairwise Losses
di: Zhu, Dixian, et al.
Pubblicazione: (2024)

FormalMATH: Benchmarking Formal Mathematical Reasoning of Large Language Models
di: Yu, Zhouliang, et al.
Pubblicazione: (2025)

Diffusion-DICE: In-Sample Diffusion Guidance for Offline Reinforcement Learning
di: Mao, Liyuan, et al.
Pubblicazione: (2024)

Cooperative Backdoor Attack in Decentralized Reinforcement Learning with Theoretical Guarantee
di: Gao, Mengtong, et al.
Pubblicazione: (2024)

Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning
di: Gao, Hang, et al.
Pubblicazione: (2025)

Revisiting Meta-Learning with Noisy Labels: Reweighting Dynamics and Theoretical Guarantees
di: Zhang, Yiming, et al.
Pubblicazione: (2025)

Quantifying Generalisation in Imitation Learning
di: Gavenski, Nathan, et al.
Pubblicazione: (2025)