NeurIPS 2025 论文列表

The imbalance (or long-tail) is the nature of many real-world data distributions, which often induces the undesirable bias of deep classification models toward frequent classes, resulting in poor performance for tail classes. In this paper, we propose a novel two-stage learning approach to mitigate such a majority-biased tendency while preserving valuable information within datasets. Specifically, the first stage proposes a new representation learning technique from the information theory perspective. This approach is theoretically equivalent to minimizing intra-class distance, yielding an effective and well-separated feature space. The second stage develops a novel sampling strategy that selects mathematically informative instances, able to rectify majority-biased decision boundaries without compromising a model’s overall performance. As a result, our approach achieves the state-of-the-art performance across various long-tailed benchmark datasets, validated via extensive experiments. Our code is available at https://github.com/fudong03/BNS_IPDPP.

Dynamic pricing with resource constraints is a critical challenge in online learning, requiring a delicate balance between exploring unknown demand patterns and exploiting known information to maximize revenue. We propose three tailored algorithms to address this problem across varying levels of prior knowledge: (1) a Boundary Attracted Re-solve Method for the full information setting, achieving logarithmic regret without the restrictive non-degeneracy condition; (2) an online learning algorithm for the no information setting, delivering an optimal $O(\sqrt{T})$ regret; and (3) an estimate-then-select re-solve algorithm for the informed price setting, leveraging machine-learned prices with known error bounds to bridge the gap between full and no information scenarios. Moreover, through numerical experiments, we demonstrate the robustness and practical applicability of our approaches. This work advances dynamic pricing by offering scalable solutions that adapt to diverse informational contexts while relaxing classical assumptions.

Large language models are trained with tokenizers that map text to a fixed vocabulary, yet the resulting token distribution is highly imbalanced: a few words dominate the stream while most occur rarely. Recent practice favours ever-larger vocabularies, but it is unclear whether the benefit comes from better word segmentation or from amplifying this frequency skew. To this end, we perform a controlled study that scales the vocabulary of a constant-size Transformer from 24K to 196K symbols while holding data, compute and optimisation unchanged. Above 24K every common word is already a single token, so further growth only increases imbalance. Word-level loss decomposition shows that larger vocabularies reduce cross-entropy almost exclusively by lowering uncertainty on the ~$2,500$ most frequent words, even though loss on the rare tail rises. Same frequent words cover roughly $80\%$ of tokens in downstream benchmarks, this training advantage transfers intact. We further show that enlarging model parameters with a fixed tokenizer yields the same frequent-word benefit, revealing a shared mechanism behind vocabulary and model scaling. Our results recast “bigger vocabularies help” as “sharper frequency imbalance helps,” offering a simple, principled knob for tokenizer–model co-design and clarifying the loss dynamics that govern language-model scaling in pre-training.

Recently, pre-trained state space models have shown great potential for video classification, which sequentially compresses visual tokens in videos with linear complexity, thereby improving the processing efficiency of video data while maintaining high performance. To apply powerful pre-trained models to downstream tasks, prompt learning is proposed to achieve efficient downstream task adaptation with only a small number of fine-tuned parameters. However, the sequentially compressed visual prompt tokens fail to capture the spatial and temporal contextual information in the video, thus limiting the effective propagation of spatial information within a video frame and temporal information between frames in the state compression model and the extraction of discriminative information. To tackle the above issue, we proposed a State Space Prompting (SSP) method for video understanding, which combines intra-frame and inter-frame prompts to aggregate and propagate key spatiotemporal information in the video. Specifically, an Intra-Frame Gathering (IFG) module is designed to aggregate spatial key information within each frame. Besides, an Inter-Frame Spreading (IFS) module is designed to spread discriminative spatio-temporal information across different frames. By adaptively balancing and compressing key spatio-temporal information within and between frames, our SSP effectively propagates discriminative information in videos in a complementary manner. Extensive experiments on four video benchmark datasets verify that our SSP significantly outperforms existing SOTA methods by 2.76\% on average while reducing the overhead of fine-tuning parameters.

This position paper argues that there is an urgent need to restructure markets for the information that goes into AI systems. Specifically, small-to-medium sized producers of information (such as journalists, news organizations, researchers, and creative professionals) need to be able to appoint representatives who can carry out "collective bargaining" with AI product builders in order to receive a reasonable terms and a fair return on the informational value they contribute. Obstacles to this market structure can be removed through technical work that facilitates collective bargaining in the information economy (e.g., explainable data value estimation and federated data management tools) and regulatory/policy interventions (e.g., support for trusted data intermediary organizations that represent guilds or syndicates of information producers). We argue that without collective bargaining in the information economy, AI will exacerbate a large-scale "information market failure" that will lead not only to undesirable concentration of capital, but also to a potential "ecological collapse" in the informational commons. On the other hand, collective bargaining in the information economy can create market conditions necessary for a pro-social AI future. We provide concrete actions that can be taken to support a coalition-based approach to achieve this.

Diffusion-based generative methods have shown promising potential for modeling trajectories from offline reinforcement learning (RL) datasets, and hierarchical diffusion has been introduced to mitigate variance accumulation and computational challenges in long-horizon planning tasks. However, existing approaches typically assume a fixed two-layer diffusion hierarchy with a single predefined temporal scale, which limits adaptability to diverse downstream tasks and reduces flexibility in decision making. In this work, we propose SIHD, a novel Structural Information-based Hierarchical Diffusion framework for effective and stable offline policy learning in long-horizon environments with sparse rewards. Specifically, we analyze structural information embedded in offline trajectories to construct the diffusion hierarchy adaptively, enabling flexible trajectory modeling across multiple temporal scales. Rather than relying on reward predictions from localized sub-trajectories, we quantify the structural information gain of each state community and use it as a conditioning signal within the corresponding diffusion layer. To reduce overreliance on offline datasets, we introduce a structural entropy regularizer that encourages exploration of underrepresented states while avoiding extrapolation errors from distributional shifts. Extensive evaluations show that SIHD significantly outperforms state-of-the-art baselines in decision-making performance and demonstrates superior generalization across diverse scenarios.

Imaging systems have traditionally been designed to mimic the human eye and produce visually interpretable measurements. Modern imaging systems, however, process raw measurements computationally before or instead of human viewing. As a result, the information content of raw measurements matters more than their visual interpretability. Despite the importance of measurement information content, current approaches for evaluating imaging system performance do not quantify it: they instead either use alternative metrics that assess specific aspects of measurement quality or assess measurements indirectly with performance on secondary tasks. We developed the theoretical foundations and a practical method to directly quantify mutual information between noisy measurements and unknown objects. By fitting probabilistic models to measurements and their noise characteristics, our method estimates information by upper bounding its true value. By applying gradient-based optimization to these estimates, we also developed a technique for designing imaging systems called Information-Driven Encoder Analysis Learning (IDEAL). Our information estimates accurately captured system performance differences across four imaging domains (color photography, radio astronomy, lensless imaging, and microscopy). Systems designed with IDEAL matched the performance of those designed with end-to-end optimization, the prevailing approach that jointly optimizes hardware and image processing algorithms. These results establish mutual information as a universal performance metric for imaging systems that enables both computationally efficient design optimization and evaluation in real-world conditions. A video summary of this work can be found at: https://waller-lab.github.io/EncodingInformationWebsite/

Foundation models (FMs) trained with different objectives and data learn diverse representations, making some more effective than others for specific downstream tasks. Existing adaptation strategies, such as parameter-efficient fine-tuning, focus on individual models and do not exploit the complementary strengths across models. Probing methods offer a promising alternative by extracting information from frozen models, but current techniques do not scale well with large feature sets and often rely on dataset-specific hyperparameter tuning. We propose Combined backBones (ComBo), a simple and scalable probing-based adapter that effectively integrates features from multiple models and layers. ComBo compresses activations from layers of one or more FMs into compact token-wise representations and processes them with a lightweight transformer for task-specific prediction. Crucially, ComBo does not require dataset-specific tuning or backpropagation through the backbone models. However, not all models are equally relevant for all tasks. To address this, we introduce a mechanism that leverages ComBo’s joint multi-backbone probing to efficiently evaluate each backbone’s task-relevance, enabling both practical model comparison and improved performance through selective adaptation. On the 19 tasks of the VTAB-1k benchmark, ComBo outperforms previous probing methods, matches or surpasses more expensive alternatives, such as distillation-based model merging, and enables efficient probing of tuned models. Our results demonstrate that ComBo offers a practical and general-purpose framework for combining diverse representations from multiple FMs.

Latent variables (LVs) play a crucial role in encoder-decoder models by enabling effective data compression, prediction, and generation. Although their theoretical properties, such as generalization, have been extensively studied in supervised learning, similar analyses for unsupervised models such as variational autoencoders (VAEs) remain insufficiently underexplored. In this work, we extend information-theoretic generalization analysis to vector-quantized (VQ) VAEs with discrete latent spaces, introducing a novel data-dependent prior to rigorously analyze the relationship among LVs, generalization, and data generation. We derive a novel generalization error bound of the reconstruction loss of VQ-VAEs, which depends solely on the complexity of LVs and the encoder, independent of the decoder. Additionally, we provide the upper bound of the 2-Wasserstein distance between the distributions of the true data and the generated data, explaining how the regularization of the LVs contributes to the data generation performance.

To understand feature learning dynamics in neural networks, recent theoretical works have focused on gradient-based learning of Gaussian single-index models, where the label is a nonlinear function of a latent one-dimensional projection of the input. While the sample complexity of online SGD is determined by the *information exponent* of the link function, recent works improved this by performing multiple gradient steps on the same sample with different learning rates — yielding a *non-correlational* update rule — and instead are limited by the (potentially much smaller) *generative exponent*. However, this picture is only valid when these learning rates are sufficiently large. In this paper, we characterize the relationship between learning rate(s) and sample complexity for a broad class of gradient-based algorithms that encapsulates both correlational and non-correlational updates. We demonstrate that, in certain cases, there is a phase transition from an "information exponent regime" with small learning rate to a "generative exponent regime" with large learning rate. Our framework covers prior analyses of one-pass SGD and SGD with batch reuse, while also introducing a new layer-wise training algorithm that leverages a two-timescales approach (via different learning rates for each layer) to go beyond correlational queries without reusing samples or modifying the loss from squared error. Our theoretical study demonstrates that the choice of learning rate is as important as the design of the algorithm in achieving statistical and computational efficiency.

Despite recent advances in machine learning, many scientific discoveries in chemistry still rely on manually curated datasets extracted from the scientific literature. Automation of information extraction in specialized chemistry domains has the potential to scale up machine learning applications and improve the quality of predictions, enabling data-driven scientific discoveries at a faster pace. In this paper, we present ChemX, a collection of 10 benchmarking datasets across several domains of chemistry providing a reliable basis for evaluating and fine-tuning automated information extraction methods. The datasets encompassing various properties of small molecules and nanomaterials have been manually extracted from peer-reviewed publications and systematically validated by domain experts through a cross-verification procedure allowing for identification and correction of errors at sources. In order to demonstrate the utility of the resulting datasets, we evaluate the extraction performance of the state-of-the-art large language models (LLMs). Moreover, we design our own agentic approach to take full control of the document preprocessing before LLM-based information extraction. Finally, we apply the recently emerged multi-agent systems specialized in chemistry to compare performance against the strong baselines. Our empirical results highlight persistent challenges in chemical information extraction, particularly in handling domain-specific terminology, complex tabular and schematic formats, and context-dependent ambiguities. We discuss the importance of expert data validation, the nuances of the evaluation pipeline, and the prospects of automated information extraction in chemistry. Finally, we provide open documentation including standardized schemas and provenance metadata, as well as the code and other materials to ensure reproducibility. ChemX is poised to advance automatic information extraction in chemistry by challenging the quality and generalization capabilities of existing methods, as well as providing insights into evaluation strategies.

Alzheimer's Disease (AD) poses a significant health threat to the aging population, underscoring the critical need for early diagnosis to delay disease progression and improve patient quality of life. Recent advances in heterogeneous multimodal artificial intelligence (AI) have facilitated comprehensive joint diagnosis, yet practical clinical scenarios frequently encounter incomplete modalities due to factors like high acquisition costs or radiation risks. Moreover, traditional convolution-based architecture face inherent limitations in capturing long-range dependencies and handling heterogeneous medical data efficiently. To address these challenges, in our proposed heterogeneous multimodal diagnostic framework (HAD), we develop a multi-view Hilbert curve-based Mamba block and a hierarchical spatial feature extraction module to simultaneously capture local spatial features and global dependencies, effectively alleviating spatial discontinuities introduced by voxel serialization. Furthermore, to balance semantic consistency and modal specificity, we build a unified mutual information learning objective in the heterogeneous multimodal embedding space, which maintains effective learning of modality-specific information to avoid modality collapse caused by model preference. Extensive experiments demonstrate that our HAD significantly outperforms state-of-the-art methods in various modality-missing scenarios, providing an efficient and reliable solution for early-stage AD diagnosis.

Learning complex functions that involve multi-step reasoning poses a significant challenge for standard supervised learning from input-output examples. Chain-of-thought (CoT) supervision, which augments training data with intermediate reasoning steps to provide a richer learning signal, has driven recent advances in large language model reasoning. This paper develops a statistical theory of learning under CoT supervision. Central to the theory is the *CoT information*, which measures the additional discriminative power offered by the chain-of-thought for distinguishing hypotheses with different end-to-end behaviors. The main theoretical results demonstrate how CoT supervision can yield significantly faster learning rates compared to standard end-to-end supervision, with both upper bounds and information-theoretic lower bounds characterized by the CoT information.

Obtaining a generalizable reward model is crucial in Reinforcement Learning from Human Feedback (RLHF) as it enables correctly evaluating unseen prompt-response pairs. However, existing reward models lack this ability, as they are typically trained by increasing the reward gap between chosen and rejected responses, while overlooking the prompts that the responses are conditioned on. Consequently, when the trained reward model is evaluated on prompt-response pairs that lie outside the data distribution, neglecting the effect of prompts may result in poor generalization of the reward model. To address this issue, we decompose the reward value into two independent components: prompt-free reward and prompt-related reward. Prompt-free reward represents the evaluation that is determined only by responses, while the prompt-related reward reflects the reward that derives from both the prompt and the response. We extract these two components from an information theoretical perspective, which requires no extra models.. Subsequently, we propose a new reward learning algorithm by prioritizing data samples based on their prompt-free reward values. Through toy examples, we demonstrate that the extracted prompt-free and prompt-related rewards effectively characterize two parts of the reward model. Further, standard evaluations show that our method improves both the alignment performance and the generalization capability of the reward model.

Brain-inspired spiking neural networks (SNNs) provide energy-efficient computation through event-driven processing. However, the shared weights across multiple timesteps lead to serious temporal feature redundancy, limiting both efficiency and performance. This issue is further aggravated when processing static images due to the duplicated input. To mitigate this problem, we propose a parameter-free and plug-and-play module named Mutual Information-based Temporal Redundancy Quantification and Reduction (MI-TRQR), constructing energy-efficient SNNs. Specifically, Mutual Information (MI) is properly introduced to quantify redundancy between discrete spike features at different timesteps on two spatial scales: pixel (local) and the entire spatial features (global). Based on the multi-scale redundancy quantification, we apply a probabilistic masking strategy to remove redundant spikes. The final representation is subsequently recalibrated to account for the spike removal. Extensive experimental results demonstrate that our MI-TRQR achieves sparser spiking firing, higher energy efficiency, and better performance concurrently with different SNN architectures in tasks of neuromorphic data classification, static data classification, and time-series forecasting. Notably, MI-TRQR increases accuracy by \textbf{1.7\%} on CIFAR10-DVS with 4 timesteps while reducing energy cost by \textbf{37.5\%}. Our codes are available at https://github.com/dfxue/MI-TRQR.

Large vision-language models (LVLMs) excel at multimodal understanding but suffer from high computational costs due to redundant vision tokens. Existing pruning methods typically rely on single-layer attention scores to rank and prune redundant visual tokens to solve this inefficiency. However, as the interaction between tokens and layers is complicated, this raises a basic question: Is such a simple single-layer criterion sufficient to identify redundancy? To answer this question, we rethink the emergence of redundant visual tokens from a fundamental perspective: information flow, which models the interaction between tokens and layers by capturing how information moves between tokens across layers. We find (1) the CLS token acts as an information relay, which can simplify the complicated flow analysis; (2) the redundancy emerges progressively and dynamically via layer-wise attention concentration; and (3) relying solely on attention scores from single layers can lead to contradictory redundancy identification. Based on this, we propose FlowCut, an information-flow-aware pruning framework, mitigating the insufficiency of the current criterion for identifying redundant tokens and better aligning with the model's inherent behaviors. Extensive experiments show FlowCut achieves superior results, outperforming SoTA by 1.6% on LLaVA-1.5-7B with 88.9% token reduction, and by 4.3% on LLaVA-NeXT-7B with 94.4% reduction, delivering 3.2$\times$ speed-up in the prefilling stage. Our code is available at https://github.com/TungChintao/FlowCut.

Multi-table data integrate various entities and attributes, with potential interconnections between them. However, existing tabular learning methods often struggle to describe and leverage the underlying complementarity across distinct tables. To address this limitation, we propose the first unified paradigm for multi-table learning that systematically quantifies and integrates complementary information across tables. Specifically, we introduce a metric called complementarity strength (CS), which captures inter-table complementarity by incorporating relevance, similarity, and informativeness. For the first time, we systematically formulate the paradigm towards multi-table learning by establishing formal definitions of tasks and loss functions. Correspondingly, we present a network for multi-table learning that combines Adaptive Table encoder and Cross table Attention mechanism (ATCA-Net), achieving the simultaneous integration of complementary information from distinct tables. Extensive experiments show that ATCA-Net effectively leverages complementary information and that the CS metric accurately quantifies the richness of complementarity across multiple tables. To the best of our knowledge, this is the first work to establish theoretical and practical foundations for multi-table learning.

Capturing effective long-range information propagation remains a fundamental yet challenging problem in graph representation learning. Motivated by this, we introduce SONAR, a novel GNN architecture inspired by the dynamics of wave propagation in continuous media. SONAR models information flow on graphs as oscillations governed by the wave equation, allowing it to maintain effective propagation dynamics over long distances. By integrating adaptive edge resistances and state-dependent external forces, our method balances conservative and non-conservative behaviors, improving the ability to learn more complex dynamics. We provide a rigorous theoretical analysis of SONAR's energy conservation and information propagation properties, demonstrating its capacity to address the long-range propagation problem. Extensive experiments on synthetic and real-world benchmarks confirm that SONAR achieves state-of-the-art performance, particularly on tasks requiring long-range information exchange.

Estimating mutual information (MI) is a fundamental task in data science and machine learning. Existing estimators mainly rely on either highly flexible models (e.g., neural networks), which require large amounts of data, or overly simplified models (e.g., Gaussian copula), which fail to capture complex distributions. Drawing upon recent vector copula theory, we propose a principled interpolation between these two extremes to achieve a better trade-off between complexity and capacity. Experiments on state-of-the-art synthetic benchmarks and real-world data with diverse modalities demonstrate the advantages of the proposed method.