5arXiv cs.LG (Machine Learning)·
Expanding Flow Maps (EFMs): flow-based generative models with variable output dimensionality
A new arXiv preprint introduces Expanding Generative Flows (EFlows) and Expanding Flow Maps (EFMs), a framework that extends flow-based generative models to handle variable output dimensions and sequence lengths. The approach defines flows between distributions of increasing dimensionality via an expanding interpolant, factoring the generative map into an expand operator and a transport map. The framework covers both continuous and discrete modalities, enabling variable-size graph and variable-length sequence generation, and subsumes existing fixed-canvas flows as a special case.
Related guides (1)
Related events (8)
IMPFM: Multi-particle flow-map framework for online feedback-driven generative search
A new arXiv preprint introduces Sequentially-Controlled Interactive Multi-Particle Flow-Maps (IMPFM), a framework for sample-efficient online search under sequential human feedback. The method transports an ensemble of particles toward a target distribution using flow maps and a posterior sample-sharing mechanism, aiming to balance global exploration with reward over-optimization avoidance. The authors prove convergence to a KL-tilted target via a Feynman-Kac corrector and demonstrate improvements over baselines on alignment and search tasks. The work addresses a gap in training-free reward alignment methods that struggle with unknown or sequentially revealed preferences.
FlowPipe: LLM-conditioned Generative Flow Networks for automated data preparation pipeline construction
FlowPipe is a new framework that frames ML data preparation pipeline synthesis as conditional probabilistic flow generation over a directed acyclic graph, using Conditional Generative Flow Networks (C-GFlowNets) with a Trajectory Balance objective. LLM-derived semantic priors are injected into the policy via Feature-wise Linear Modulation (FiLM), and a failure-aware flow objective steers search away from invalid states. Evaluated on 74 real-world datasets across two benchmark suites, FlowPipe improves accuracy by 11.96% on average over SOTA baselines and achieves 12.5x faster training convergence. The work addresses long-standing limitations in automated data pipeline construction including weak credit assignment and inefficient exploration.
FMLM+ introduces Posterior Refinement for fast non-autoregressive language generation
Researchers introduce FMLM+, a framework combining Flow Map Language Models with masking-style noise schedules to enable joint sequence generation with per-token global consistency scoring. The key contribution is Posterior Refinement, an inference-time self-correction strategy that matches discrete baseline performance with 32x fewer neural function evaluations (NFEs). The approach improves the speed-quality tradeoff over both Masked Diffusion Models and standard FLMMs across multiple benchmarks, addressing longstanding factorization error problems in non-autoregressive generation.
EdgeFlow: Edge-Map Augmented VLM-Based Flowchart Processing for Industrial Requirements Engineering
EdgeFlow augments Vision Language Models with deterministically extracted Canny edge maps as structural priors to improve flowchart-to-Mermaid conversion in industrial requirements engineering, requiring no annotated training data or fine-tuning. Evaluated on IndusReqFlow, a real-world industrial dataset, it achieves +17.39 pp node-level F1 and +16.94 pp edge-level F1 over off-the-shelf VLMs. Cross-dataset evaluation on a synthetic benchmark shows no significant gains, highlighting the gap between synthetic and industrial benchmarks for VLM-based RE tools.
Unified framework for generalization and sketching across variable-size inputs via random sampling maps
A new arXiv preprint introduces a theoretical framework for understanding how ML models trained on small inputs generalize to larger, unseen input sizes — covering sequences, graphs, point clouds, and tensors. The approach uses random sampling maps (generalizing sampling with replacement, random binning, and species sampling) to compare inputs of different sizes and derive explicit generalization and sketching rates. The framework applies to transformers, graph neural networks, and moment polynomials, among other architectures. This is a foundational theoretical contribution addressing out-of-distribution generalization across input dimensionality.
Black Forest Labs releases FLUX 3 multimodal flow model, reportedly outperforming Seedance 2.0, Gemini Omni, and Grok Imagine
Black Forest Labs has released FLUX 3, a multimodal flow model that reportedly beats competing image/video generation systems including Seedance 2.0, Gemini Omni, and Grok Imagine on key benchmarks. The release also includes a FLUX-mimic video-action robotics model, extending the FLUX family into embodied AI applications. This represents a significant capability advance for BFL in the competitive generative media space.
DanceOPD: On-policy generative field distillation for composing image generation capabilities
DanceOPD is a new training framework for flow-matching image generation models that addresses the conflict between text-to-image generation, local editing, and global editing capabilities. The approach routes each sample to a capability-specific velocity field, queries student-induced rollout states on-policy, and trains with a velocity MSE objective to compose multiple expert capabilities without mutual degradation. Experiments show improvements in multi-capability composition while preserving baseline generation quality. The method also absorbs operator-defined fields such as classifier-free guidance.
Minimax framework establishes fundamental statistical limits for transport map estimation in generative models
A new arXiv preprint formalizes the task of estimating valid transport maps (used in diffusion models, normalizing flows, and flow matching) within a minimax statistical framework. The key result is that under standard stability assumptions from optimal transport theory, estimating any valid transport map is as statistically hard as estimating the optimal transport map itself. The authors also show that when those stability assumptions fail, alternative transport maps can be learned substantially more accurately than the OT map, clarifying when targeting sub-optimal maps yields real statistical advantages. The work provides theoretical sample complexity lower bounds applicable to a broad class of modern generative modeling methods.