Despite the progress in the development of generative models, their usefulness in creating synthetic data that improve prediction performance of classifiers has been put into question. Besides heuristic principles such as ''synthetic data should be close to the real data distribution'', it is actually not clear which specific properties affect the generalization error. Our paper addresses this question through the lens of high-dimensional regression. Theoretically, we show that, for linear models, the *covariance shift* between the target distribution and the distribution of the synthetic data affects the generalization error but, surprisingly, the mean shift does not. Furthermore, in some regimes, we prove that matching the covariance of the target distribution is optimal. Remarkably, the theoretical insights for linear models carry over to deep neural networks and generative models. We empirically demonstrate that the *covariance matching* procedure (matching the covariance of the synthetic data with that of the data coming from the target distribution) performs well against several recent approaches for synthetic data selection, across various training paradigms, datasets and generative models used for augmentation.
论文检索
输入标题、作者或关键词，从 12,113 篇学术成果中精准定位
Deep Learning · Everything Else
Recent progress in text-to-music generation has enabled models to synthesize high-quality musical segments, full compositions, and even respond to fine-grained control signals, e.g. chord progressions. State-of-the-art (SOTA) systems differ significantly in many dimensions, such as training datasets, modeling paradigms, and architectural choices. This diversity complicates efforts to evaluate models fairly and identify which design choices influence performance the most. While factors like data and architecture are important, in this study we focus exclusively on the modeling paradigm. We conduct a systematic empirical analysis to isolate its effects, offering insights into associated trade-offs and emergent behaviors that can guide future text-to-music generation systems. Specifically, we compare the two arguably most common modeling paradigms: auto-regressive decoding and conditional flow-matching. We conduct a controlled comparison by training all models from scratch using identical datasets, training configurations, and similar backbone architectures. Performance is evaluated across multiple axes, including generation quality, robustness to inference configurations, scalability, adherence to both textual and temporally aligned conditioning, and editing capabilities in the form of audio inpainting. This comparative study sheds light on distinct strengths and limitations of each paradigm, providing actionable insights that can inform future architectural and training decisions in the evolving landscape of text-to-music generation. Audio sampled examples are available at: https://huggingface.co/spaces/ortal1602/ARvsFM
Computer Vision · 3D Rendering & Reconstruction
Persistent dynamic scene modeling for tracking and novel-view synthesis remains challenging, particularly due to the complexity of capturing accurate deformations while maintaining computational efficiency. In this paper, we present SCas4D, a novel cascaded optimization framework that leverages inherent structural patterns in 3D Gaussian Splatting (3DGS) for dynamic scenes. Our key insight is that real-world deformations often exhibit hierarchical patterns, where groups of Gaussians undergo similar transformations. By employing a structural cascaded optimization approach that progressively refines deformations from coarse part-level to fine point-level adjustments, SCas4D achieves convergence within 100 iterations per time frame while maintaining competitive quality to the state-of-the-art method with only 1/20th of the training iterations. We further demonstrate our method's effectiveness in self-supervised articulated object segmentation, establishing a natural capability from our representation. Extensive experiments demonstrate our method's effectiveness in novel view synthesis and dense point tracking tasks. Please find our project page at https://github-tree-0.github.io/SCas4D-project-page/.
Applications · Time Series
Cross-domain generalization is very important in Time Series Forecasting because similar historical information may lead to distinct future trends due to the domain-specific characteristics. Recent works focus on building unimodal time series foundation models and end-to-end multimodal supervised models. Since domain-specific knowledge is often contained in modalities like texts, the former lacks the explicit utilization of them, thus hindering the performance. The latter is tailored for end-to-end scenarios and does not support zero-shot inference for cross-domain scenarios. In this work, we introduce Aurora, the first Multimodal Time Series Foundation Model, which supports multimodal inputs and zero-shot inference. Pretrained on Cross-domain Multimodal Time Series Corpus, Aurora can adaptively extract and focus on key domain knowledge contained in corresponding text or image modalities, thus possessing strong cross-domain generalization capability. Through tokenization, encoding, and distillation, Aurora can extract multimodal domain knowledge as guidance and then utilizes a Modality-Guided Multi-head Self-Attention to inject them into the modeling of temporal representations. In the decoding phase, the multimodal representations are used to generate the conditions and prototypes of future tokens, contributing to a novel Prototype-Guided Flow Matching for generative probabilistic forecasting. Comprehensive experiments on 5 well-recognized benchmarks, including TimeMMD, TSFM-Bench, ProbTS, TFB, and EPF, demonstrate the consistent state-of-the-art performance of Aurora on both unimodal and multimodal scenarios.
Deep Learning · Everything Else
Assessing the quality of generative model outputs from large language models (LLMs) or vision-language models (VLMs), poses significant challenges. Traditional evaluation methods either rely on human assessment which is resource-intensive and not scalable or on automatic metrics that often correlate poorly with human preferences. Another approach is to train dedicated neural evaluators, but this typically requires substantial training data and compute. In this study, we thus introduce ReFeR, a tuning-free framework for evaluating generative outputs including both text and images, using a two-level hierarchy of pre-trained LLM and VLM evaluators. This multi-agent hierarchical strategy leverages additional compute at inference time by orchestrating multiple models and utilizing the increased test-time reasoning to boost performance. By having models themselves provide feedback and final judgments, ReFeR reduces the dependence on human evaluation. We rigorously evaluate ReFeR on four diverse evaluation benchmarks, where it surpasses prior methods in accuracy while also generating constructive feedback useful for downstream distillation and self-improvement via finetuning. Interestingly, ReFeR is also applicable for reasoning tasks - experiments on four reasoning benchmarks show ReFeR’s superior collective reasoning abilities. We present two variants of the framework: ReFeR-Turbo, optimized for accelerated performance, and ReFeR-Lite, offering a more test-time compute efficient solution. ReFeR-Lite is $\sim12-14\times$ more compute efficient than previous works while being comparably accurate to ReFeR-Turbo.
Computer Vision · Image and Video Generation
We introduce TINKER, a novel framework for high-fidelity 3D editing without any per-scene finetuning, where only a single edited image (one-shot) or a few edited images (few-shot) are required as input. Unlike prior techniques that demand extensive per-scene optimization to ensure multi-view consistency or to produce dozens of consistent edited input views, TINKER delivers robust, multi-view consistent edits from as few as one or two images. This capability stems from repurposing pretrained diffusion models, which unlocks their latent 3D awareness. To drive research in this space, we curate the first large-scale multi-view editing dataset and data pipeline, spanning diverse scenes and styles. Building on this dataset, we develop our framework capable of generating multi-view consistent edited views without per-scene training, which consists of two novel components: (1) Multi-view consistent editor: Enables precise, reference-driven edits that remain coherent across all viewpoints. (2) Any-view-to-video scene completion model : Leverages spatial-temporal priors from video diffusion to perform high-quality scene completion and novel-view generation even from sparse inputs. Through extensive experiments, TINKER significantly reduces the barrier to generalizable 3D content creation, achieving state-of-the-art performance on editing, novel-view synthesis, and rendering enhancement tasks, while also demonstrating strong potential for 4D editing. We believe that TINKER represents a key step towards truly scalable, zero-shot 3D and 4D editing.
Deep Learning · Algorithms
Optimizing deep learning algorithms currently requires slow, manual derivation, potentially leaving much performance untapped. Methods like FlashAttention have achieved a x6 performance improvement over native PyTorch by avoiding unnecessary data transfers, but required three iterations over three years to be developed. Automated compiled methods have consistently lagged behind. This paper extends Neural Circuit Diagrams for deep learning models to consider resource usage and the distribution of tasks across a GPU hierarchy. We show how diagrams can use simple relabellings to derive high-level streaming and tiling optimization strategies along with performance models. We show how this high-level performance model allows the effects of quantization and multi-level GPU hierarchies to be readily considered. We develop a methodology for representing intermediate-level pseudocode with diagrams, allowing hardware-aware algorithms to be derived step-by-step. Finally, we show how our methodology can be used to better understand existing techniques like FlashAttention. This work uses a theoretical framework to link assumptions about GPU behaviour to claims about performance. We aim to lay the groundwork for a scientific approach to GPU optimization where experiments can address clear hypotheses rather than post-hoc rationalizations.
Deep Learning · Attention Mechanisms
Transformer-based deep learning methods have emerged as the standard approach to model diverse data such as sequences, images, and graphs. These methods rely on self-attention, which treats data as an unordered set of elements. This ignores the neighborhood structure or graph topology of the data and requires the use of inductive biases, such as position embeddings in sequences and images, and random walks in graphs, to incorporate topology. However, developing bespoke inductive biases for each task requires significant effort and can also introduce side-effects hindering generalization. In this work, we introduce Chimera, a unified model that directly incorporates the data topology in a principled way, obviating the need for domain-specific biases. Central to Chimera is the observation that state-space models---which naturally do not require position embeddings---can be generalized to capture any general graph topology. Our experiments demonstrate the versatility of our approach---Chimera achieves strong performance across the domains of language, vision, and graphs, outperforming BERT on GLUE by 0.7 points, ViT on ImageNet-1k by 2.6%, and all the baselines on the Long Range Graph Benchmark. Our results validate Chimera's principled methodological contributions and affirm the long-held belief that data topology is a powerful inductive bias across modalities. We further propose algorithmic optimizations to improve Chimera's efficiency while maintaining performance: 1) For the subclass of Directed Acyclic Graphs we show that Chimera can be implemented as a linear time recurrence. 2) For general graphs, we relax the method with a simple mathematical approximation, achieving Transformer's quadratic complexity without relying on domain-specific biases.
General Machine Learning · Everything Else
Modern Gradient Boosted Decision Trees (GBDTs) accelerate split finding with histogram-based binning, which reduces complexity from $O(N\log N)$ to $O(N)$ by aggregating gradients into fixed-size bins. However, the predominant quantile binning strategy—designed to distribute data points evenly among bins—may overlook critical boundary values that could enhance predictive performance. In this work, we consider a novel approach that replaces quantile binning with a $k$-means discretizer initialized with quantile bins, and justify the swap with a proof showing how, for any $L$-Lipschitz function, k-means maximizes the worst-case explained variance of Y obtained when treating all values in a given bin as equivalent. We test this swap against quantile and uniform binning on 33 OpenML datasets plus synthetics that control for modality, skew, and bin budget. Across 18 regression datasets, k-means shows no statistically significant losses at the 5% level and wins in three cases—most strikingly a 55% MSE drop on one particularly skewed dataset—even though k-means' mean reciprocal rank (MRR) is slightly lower (0.65 vs 0.72). On the 15 classification datasets the two methods are statistically tied (MRR 0.70 vs 0.68) with gaps $\leq$0.2 pp. Synthetic experiments confirm consistently large MSE gains—typically $>$20% and rising to 90% as outlier magnitude increases or bin budget drops. We find that k-means keeps error on par with exhaustive (no-binning) splitting when extra cuts add little value, yet still recovers key split points that quantile overlooks. As such, we advocate for a built-in bin_method=$k$-means flag, especially in regression tasks and in tight-budget settings such as the 32–64-bin GPU regime—because it is a "safe default" with large upside, yet adds only a one-off, cacheable overhead ($\approx$ 3.5s per feature to bin 10M rows on one Apple M1 thread).
This tutorial serves as an intuitive introduction to adding inference-time controls to pretrained flow matching and rectified flow generative models, to make them perform tasks they weren't trained to do. We take an unconditional flow model trained on MNIST digits and apply two types of guidance: classifier guidance to generate specific digits, and inpainting to fill in missing pixels. Both approaches work by adding velocity corrections during the sampling process to steer the model toward desired outcomes. Since modern generative models operate in compressed latent spaces, we examine guidance methods that work directly in latent space as well as those that decode to pixel space. We also explore PnP-Flow, which satisfies constraints by iteratively projecting samples backward and forward in time rather than correcting flow velocities. The approaches demonstrated here work with other flow models and control tasks, so you can guide flows where you want them to go.
Deep Learning · Algorithms
Diffusion large language models (dLLMs) have emerged as a promising alternative to standard autoregressive (AR) Transformers, offering parallel token generation and flexible infilling instead of strict left-to-right decoding. This post walks through how masked discrete diffusion works at a high level: a forward process that randomly masks tokens, a reverse process that iteratively denoises them, and training setups that either start from scratch or adapt existing AR models. We then discuss how diffusion decoding differs from AR decoding, including its strengths for infilling, structured generation, and long-horizon planning, as well as practical challenges around length control, number of denoising steps, and blockwise generation. Finally, we examine both sides of the current evidence: where dLLMs shine in data-constrained regimes and where theoretical and empirical work suggests they can underperform or even collapse back toward autoregressive behavior, ending with some possible hybrid futures that combine diffusion for reasoning and autoregression for generation.
General Machine Learning · Representation Learning
High-dimensional data can be compressed into lower-dimensional embeddings while retaining a relatively large amount of relevant information, a phenomenon which, despite its widespread use, we struggle to fully explain. In this post, we use a common property of datasets - a limit on the number of features per data point - to show how a slight uniform dependence between features can be exploited to reduce the required dimensions by at least a third, while sacrificing no information about the features. To do so, we introduce the concepts of dataset resolution and feature composition of a dataset, and analyse how a set of orderings of the dataset affects the types of partitions we can create of the dataset.
General Machine Learning · Everything Else
Positive-Unlabeled (PU) learning, a challenging paradigm for training binary classifiers from only positive and unlabeled samples, is fundamental to many applications. While numerous PU learning methods have been proposed, the research is systematically hindered by the lack of a standardized and comprehensive benchmark for rigorous evaluation. Inconsistent data generation, disparate experimental settings, and divergent metrics have led to irreproducible findings and unsubstantiated performance claims. To address this foundational challenge, we introduce **PU-Bench**, the first unified open-source benchmark for PU learning. PU-Bench provides: 1) a unified data generation pipeline to ensure consistent input across configurable sampling schemes, label ratios and labeling mechanisms; 2) an integrated framework of 18 state-of-the-art PU methods; and 3) standardized protocols for reproducible assessment. Through a large-scale empirical study on 8 diverse datasets (**2880** evaluations in total), PU-Bench reveals a complex yet intuitive performance landscape, uncovering critical trade-offs between effectiveness and efficiency, and systematically mapping method robustness against variations in label frequency and selection bias. It is anticipated to serve as a foundational resource to catalyze reproducible, rigorous, and impactful research in the PU learning community. The source code is publicly available at .
Achieving generalization in robotic manipulation remains a critical challenge, particularly for unseen scenarios and novel tasks. Current Vision-Language-Action (VLA) models, while building on top of general Vision-Language Models (VLMs), still fall short of achieving robust zero-shot performance due to the scarcity and heterogeneity prevalent in embodied datasets. To address these limitations, we propose FSD (From Seeing to Doing), a novel vision-language model that generates intermediate representations through spatial relationship reasoning, providing fine-grained guidance for robotic manipulation. Our approach combines a hierarchical data construction pipeline for training with a self-consistency mechanism that aligns spatial coordinates with visual signals. Through extensive experiments, we comprehensively validated FSD’s capabilities in both “seeing” and “doing”, achieving outstanding performance across 8 benchmarks for general spatial reasoning and embodied reference abilities, as well as on our proposed more challenging benchmark VABench. We also verified zero-shot capabilities in robot manipulation, demonstrating significant performance improvements over baseline methods in both SimplerEnv and real robot settings. Experimental results show that FSD achieves 40.6% success rate in SimplerEnv and 72% success rate across 8 real-world tasks, outperforming the strongest baseline by 30%.
Applications · Time Series
In dynamic financial market characterized by shifting regimes, how can we make effective investment decisions under the changing 1) market regimes and 2) their impact? Among many research fields in financial AI, portfolio allocation stands out as one of the most practically significant areas. Consequently, numerous researchers and financial institutions continually seek approaches that improve the risk–reward trade-off and strive to apply them in real-world investment scenarios. However, achieving robust risk-adjusted performance is extremely challenging, because each asset's return and volatility fluctuate according to the shifting market regime. In response, modern portfolio theory (MPT) addresses this issue by solving for asset weights that maximize a risk–reward objective, using estimates of the return mean and covariance from historical returns. Reinforcement learning (RL) frameworks have been introduced to directly decide portfolio allocations by optimizing risk‑adjusted objectives using asset prices and macroeconomic indices. In this work, we propose STABLE (Shift-Tolerant Allocation with Black-Litterman Using Conditional Diffusion Estimates), which combines a diffusion-based generative model that captures regime shifts with an estimation-based portfolio allocation module that maximizes expected risk-adjusted return. STABLE takes macroeconomic context and asset-specific signals as inputs and generates per-stock return trajectories that reflect the prevailing macro regime while preserving firm-specific dynamics. This yields regime-aware predictive return distributions at the single-stock level together with a coherent covariance structure, which are then incorporated as investor views within a Black-Litterman allocation module to obtain risk-diversified portfolio weights. Empirically, STABLE delivers superior portfolio outcomes, achieving up to 122.9% higher Sharpe ratios with reduced drawdowns across major equity markets. It also attains state‑of‑the‑art time‑series estimation, lowering MSE by up to 15.7% compared with generative baselines.
Social Aspects · Accountability, Transparency and Interpretability
Influence estimation methods promise to explain and debug machine learning by estimating the impact of individual samples on the final model. Yet, existing methods collapse under training randomness: the same example may appear critical in one run and irrelevant in the next. Such instability undermines their use in data curation or cleanup since it is unclear if we indeed deleted/kept the correct datapoints. To overcome this, we introduce *f-influence* -- a new influence estimation framework grounded in hypothesis testing that explicitly accounts for training randomness, and establish desirable properties that make it suitable for reliable influence estimation. We also design a highly efficient algorithm *f*-*IN*fluence *E*stimation (**f-INE**) that computes f-influence in a **in a single training run**. Finally, we scale up f-INE to estimate influence of instruction tuning data on Llama 3.1 8B and show it can reliably detect poisoned samples that steer model opinions, demonstrating its utility for data cleanup and attributing model behavior.
Deep Learning · Everything Else
Tabular foundation models struggle with large datasets due to the quadratic attention. While methods like FlashAttention promise scalability, practical challenges persist in their application to tabular foundation models. Our work resolves these hurdles, enabling efficient attention, and reveals that contrary to the eariler reports, TabPFN's performance improves with larger contexts, highlighting its inherent robustness and minimal fine-tuning needs when scaling to complex, long datasets from the TabArena benchmark.
Generalization in embodied AI is hindered by the "seeing-to-doing gap", stemming from data scarcity and embodiment heterogeneity. To address this, we pioneer "pointing" as a unified, embodiment-agnostic intermediate representation, defining four core embodied pointing abilities that bridge high-level vision-language comprehension with low-level action primitives. We introduce Embodied-R1, a 3B Vision-Language Model (VLM) specifically designed for embodied reasoning and pointing. We use a wide range of embodied and general visual reasoning datasets as sources to construct a large-scale dataset, Embodied-Points-200K, which supports key embodied pointing capabilities. Then we train Embodied-R1 using a two-stage Reinforced Fine-tuning (RFT) curriculum with specialized multi-task reward design. Embodied-R1 achieves state-of-the-art performance on 11 embodied spatial and pointing benchmarks. Critically, it demonstrates robust zero-shot generalization by achieving a 56.2% success rate in the SIMPLEREnv and 87.5% across 8 real-world XArm tasks without any task-specific fine-tuning, representing a 62% improvement over strong baselines. Furthermore, the model exhibits high robustness against diverse visual disturbances. Our work shows that a pointing-centric representation, combined with an RFT training paradigm, offers an effective and generalizable pathway to closing the perception-action gap in robotics.
Representational similarity metrics typically force all units to be matched, making them susceptible to noise and outliers common in neural representations. We extend the soft-matching distance to a partial optimal transport setting that allows some neurons to remain unmatched, yielding rotation-sensitive but robust correspondences. This partial soft-matching distance provides theoretical advantages---relaxing strict mass conservation while maintaining interpretable transport costs---and practical benefits through efficient neuron ranking in terms of cross-network alignment without costly iterative recomputation. In simulations, it preserves correct matches under outliers and reliably selects the correct model in noise-corrupted identification tasks. On fMRI data, it automatically excludes low-reliability voxels and produces voxel rankings by alignment quality that closely match computationally expensive brute-force approaches. It achieves higher alignment precision across homologous brain areas than standard soft-matching, which is forced to match all units regardless of quality. In deep networks, highly matched units exhibit similar maximally exciting images, while unmatched units show divergent patterns. This ability to partition by match quality enables focused analyses, \emph{e.g.,} testing whether networks have privileged axes even within their most aligned subpopulations. Overall, partial soft-matching provides a principled and practical method for representational comparison under partial correspondence.
Applications · Language, Speech and Dialog
This post is my attempt to write down the UnigramLM tokenization algorithm cleanly and explicitly because, well, I still haven't found such a derivation and I think understanding the theory behind the method could help us make it better. I'll formalize the generative model around which the algorithm is based, derive the EM updates, explain why pruning is needed (and how it's done), and point out the spots where the practical implementation defined by the SentencePiece library diverges from the pretty mathematical models.