20 results for “Flow Matching models”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
An Zhao, Shengyuan Zhang, Zhongjian Sun, Yixiang Zhou +4 more
This paper proposes a novel distillation framework for flow matching models that enables high-fidelity single-step generation.
The paper introduces GEM, an effective concept erasure framework for Rectified Flow Transformers, by unifying trajectory-based unlearning with classic teacher-guided flow matching.
This paper proposes a skip-free encoder-decoder backbone for flow-matching speech enhancement using Latent Representation Alignment.
This paper proposes a background-set-free and reference-free music quality estimation method using unconditional Flow Matching inversion.
Bin Xiao, Jingfu Dong, Changran Wang, Yitian Chen +4 more
Omni-Flow is a distributed scheduling framework for multimodal inference that provides a unified abstraction for control flow, data flow, and compute flow.
The paper proposes a context-weighted sampler and scaled cross-entropy loss function for discrete generative modeling to improve generation quality and reduce generative perplexity.
Low-Pass Flow Matching introduces a spectral bias into the flow matching process, allowing it to better model natural data by transitioning from a standard source spectrum to a frequency-decaying bias…
Ruizhi Yuan, Zeqiu Yu, Wei Gao, Wei Chen +2 more
This paper proposes a flow-guided target-space alignment method called FlowAlign that improves instance-level correspondence while preserving target-space structure in multimodal alignment problems.
This paper proves that no single-pass semi-streaming algorithm can achieve a better-than-half approximation to the maximum matching problem, implying the optimality of the naive greedy algorithm.
The paper develops a new framework for proving lower bounds for the maximum matching problem in the semi-streaming model, improving upon the previous best known bounds.
This paper investigates the use of spectral filtering for continuous subgraph matching over dynamic graphs and presents three key findings.
This paper studies online stochastic matching in an edge arrival model, showing that competitive ratios better than 1-1/e are possible.
Introduces Expanding Generative Flows (EFlows) and Expanding Flow Maps (EFMs) for generating outputs of varying sizes in continuous and discrete state spaces.
FlowGuard introduces an identity-independent defense using flow matching to detect data-free model stealing attacks by identifying synthetic queries as out-of-distribution based on their lower-dimensi…
This paper investigates the performance of BEACON, a state-of-the-art method for low-resource, domain-aware Entity Matching, under varying algorithmic choices and data availability conditions.
This paper defines a graph-based operational semantics and type system for Vega, a declarative language for creating interactive data visualizations.