NeurIPS 2025 论文列表

*Precision* and *Recall* are fundamental metrics in machine learning tasks where both accurate predictions and comprehensive coverage are essential, such as in multi-label learning, language generation, medical studies, and recommender systems. A key challenge in these settings is the prevalence of one-sided feedback, where only positive examples are observed during training—e.g., in multi-label tasks like tagging people in Facebook photos, we may observe only a few tagged individuals, without knowing who else appears in the image. To address learning under such partial feedback, we introduce a Probably Approximately Correct (PAC) framework in which hypotheses are set functions that map each input to a set of labels, extending beyond single-label predictions and generalizing classical binary, multi-class, and multi-label models. Our results reveal sharp statistical and algorithmic separations from standard settings: classical methods such as Empirical Risk Minimization provably fail, even for simple hypothesis classes. We develop new algorithms that learn from positive data alone, achieving optimal sample complexity in the realizable case, and establishing multiplicative—rather than additive—approximation guarantees in the agnostic case, where achieving additive regret is impossible.

Spurious correlations occur when models rely on non-essential features that coincidentally co-vary with target labels, leading to incorrect reasoning under distribution shift. We consider spurious correlations in multi-modal Large Vision Language Models (LVLMs) pretrained on extensive and diverse datasets without explicit task supervision. We develop a benchmark by sourcing GPT-4o errors on real-world visual-question-answering (VQA) benchmarks, then curating a subset through LVLM-human annotation and synthetic counterfactual evaluation to identify errors caused by spurious correlations. This process yields SpuriVerse, a novel benchmark comprised of 124 distinct types of spurious correlations extracted from real-world datasets, each containing 1 realistic and 10 synthetic VQA samples for a total of 1364 multiple choice questions. We evaluate 15 open and closed-source LVLMs on SpuriVerse, finding that even state-of-the-art closed-source models struggle significantly, achieving at best only 35.0\% accuracy. Fine-tuning on synthetic examples that emphasize the spurious correlation improves performance to 78.4\%, suggesting that training on diverse spurious patterns generalizes to unseen situations: models appear to learn to avoid "shortcuts" and attend to the overall image context.

Bayesian Network models are a powerful tool to collaboratively optimize production processes in various manufacturing industries. When interacting, collaborating parties must preserve their business secrets by maintaining the confidentiality of their model structures and parameters. While most realistic industry scenarios involve hybrid settings, handling both discrete and continuous data, current state-of-the-art methods for collaborative and confidential inference only support discrete data and have high communication costs. In a centralized setting, Junction Trees enable efficient inference even in hybrid scenarios without discretizing continuous variables, but no extension for collaborative and confidential scenarios exists. To address this research gap, we introduce Hybrid CCJT, the first framework for confidential multiparty inference in hybrid domains with semi-honest, non-colluding adversaries, comprising: (i) a method to construct a strongly-rooted Junction Tree across collaborating parties through a novel construct of interface cliques; and, (ii) a protocol for confidential inference built upon multiparty computation primitives comprising a one-time alignment phase and a belief propagation system for combining the inference results across the Junction Tree cliques. Extensive evaluation on nine datasets shows that Hybrid CCJT improves the predictive accuracy of continuous target variables by 32% on average compared to the state-of-the-art, while reducing communication costs by a median 10.4x under purely discrete scenarios.

Most ML datasets today contain biases. When we train models on these datasets, they often not only learn these biases but can worsen them --- a phenomenon known as bias amplification. Several co-occurrence-based metrics have been proposed to measure bias amplification in classification datasets. They measure bias amplification between a protected attribute (e.g., gender) and a task (e.g., cooking). These metrics also support fine-grained bias analysis by identifying the direction in which a model amplifies biases. However, co-occurrence-based metrics have limitations --- some fail to measure bias amplification in balanced datasets, while others fail to measure negative bias amplification. To solve these issues, recent work proposed a predictability-based metric called leakage amplification (LA). However, LA cannot identify the direction in which a model amplifies biases. We propose Directional Predictability Amplification (DPA), a predictability-based metric that is (1) directional, (2) works with balanced and unbalanced datasets, and (3) correctly identifies positive and negative bias amplification. DPA eliminates the need to evaluate models on multiple metrics to verify these three aspects. DPA also improves over prior predictability-based metrics like LA: it is less sensitive to the choice of attacker function (a hyperparameter in predictability-based metrics), reports scores within a bounded range, and accounts for dataset bias by measuring relative changes in predictability. Our experiments on well-known datasets like COMPAS (a tabular dataset), COCO, and ImSitu (image datasets) show that DPA is the most reliable metric to measure bias amplification in classification problems.

Air pollution was responsible for 2.6 million deaths across South Asia in 2021 alone, with brick manufacturing contributing significantly to this burden. In particular, the Indo-Gangetic Plain; a densely populated and highly polluted region spanning northern India, Pakistan, Bangladesh, and parts of Afghanistan sees brick kilns contributing 8–14% of ambient air pollution. Traditional monitoring approaches, such as field surveys and manual annotation using tools like Google Earth Pro, are time and labor-intensive. Prior ML-based efforts for automated detection have relied on costly high-resolution commercial imagery and non-public datasets, limiting reproducibility and scalability. In this work, we introduce SENTINELKILNDB, a publicly available, hand-validated benchmark of 62,671 brick kilns spanning three kiln types Fixed Chimney Bull’s Trench Kiln (FCBK), Circular FCBK (CFCBK), and Zigzag kilns - annotated with oriented bounding boxes (OBBs) across 2.8 million km2 using free and globally accessible Sentinel-2 imagery. We benchmark state-of-the-art oriented object detection models and evaluate generalization across in-region, out-of-region, and super-resolution settings. SENTINELKILNDB enables rigorous evaluation of geospatial generalization and robustness for low-resolution object detection, and provides a new testbed for ML models addressing real-world environmental and remote sensing challenges at a continental scale. Datasets and code are available in SentinelKilnDB Dataset and SentinelKilnDB Bench- mark, under the Creative Commons Attribution–NonCommercial 4.0 International License.

Antimicrobial peptides have emerged as promising molecules to combat antimicrobial resistance. However, fragmented datasets, inconsistent annotations, and the lack of standardized benchmarks hinder computational approaches and slow down the discovery of new candidates. To address these challenges, we present the Expanded Standardized Collection for Antimicrobial Peptide Evaluation (ESCAPE), an experimental framework integrating over 80.000 peptides from 27 validated repositories. Our dataset separates antimicrobial peptides from negative sequences and incorporates their functional annotations into a biologically coherent multilabel hierarchy, capturing activities across antibacterial, antifungal, antiviral, and antiparasitic classes. Building on ESCAPE, we propose a transformer-based model that leverages sequence and structural information to predict multiple functional activities of peptides. Our method achieves up to a 2.56% relative average improvement in mean Average Precision over the second-best method adapted for this task, establishing a new state-of-the-art multilabel peptide classification. ESCAPE provides a comprehensive and reproducible evaluation framework to advance AI-driven antimicrobial peptide research.

We introduce *BecomingLit*, a novel method for reconstructing relightable, high-resolution head avatars that can be rendered from novel viewpoints at interactive rates. Therefore, we propose a new low-cost light stage capture setup, tailored specifically towards capturing faces. Using this setup, we collect a novel dataset consisting of diverse multi-view sequences of numerous subjects under varying illumination conditions and facial expressions. By leveraging our new dataset, we introduce a new relightable avatar representation based on 3D Gaussian primitives that we animate with a parametric head model and an expression-dependent dynamics module. We propose a new hybrid neural shading approach, combining a neural diffuse BRDF with an analytical specular term. Our method reconstructs disentangled materials from our dynamic light stage recordings and enables all-frequency relighting of our avatars with both point lights and environment maps. In addition, our avatars can easily be animated and controlled from monocular videos. We validate our approach in extensive experiments on our dataset, where we consistently outperform existing state-of-the-art methods in relighting and reenactment by a significant margin.

We present UniFoil, the largest publicly available universal airfoil database based on Reynolds-Averaged Navier–Stokes (RANS) simulations. It contains over 500,000 samples spanning a wide range of Reynolds and Mach numbers, capturing both transitional and fully turbulent flows across incompressible to compressible regimes. UniFoil is designed to support machine learning research in fluid dynamics, particularly for modeling complex aerodynamic phenomena. Most existing datasets are limited to incompressible, fully turbulent flows with smooth field characteristics, thus overlooking the critical physics of laminar–turbulent transition and shock-wave interactions—features that exhibit strong nonlinearity and sharp gradients. UniFoil fills this gap by offering a broad spectrum of realistic flow conditions. In the database, turbulent simulations utilize the Spalart–Allmaras (SA) model, while transitional flows are modeled using an $e^N$-based transition prediction method coupled with the SA model. The database includes a comprehensive geometry set comprising over 4,800 natural laminar flow (NLF) airfoils and 30,000 fully turbulent (FT) airfoils, effectively covering the diversity of airfoil designs relevant to aerospace, wind energy, and marine applications. This database is also highly valuable for scientific machine learning (SciML), enabling the development of data-driven models that more accurately capture the transport processes associated with laminar–turbulent transition. UniFoil is freely available under a permissive CC-BY-SA license.

In the machine learning system, the hybrid model parallelism combining tensor parallelism (TP) and pipeline parallelism (PP) has become the dominant solution for distributed training of Large Language Models~(LLMs) and Multimodal LLMs (MLLMs). However, TP introduces significant collective communication overheads, while PP suffers from synchronization inefficiencies such as pipeline bubbles. Existing works primarily address these challenges from isolated perspectives, focusing either on overlapping TP communication or on flexible PP scheduling to mitigate pipeline bubbles. In this paper, we propose a new synergistic tensor and pipeline parallelism schedule that simultaneously reduces both types of bubbles. Our proposed schedule decouples the forward and backward passes in PP into fine-grained computation units, which are then braided to form a composite computation sequence. This compositional structure enables near-complete elimination of TP-related bubbles. Building upon this structure, we further design the PP schedule to minimize PP bubbles. Experimental results demonstrate that our approach improves training throughput by up to 12\% for LLMs and 16\% for MLLMs compared to existing scheduling methods. Our source code is avaiable at https://github.com/MICLAB-BUPT/STP.

Model editing aims to efficiently revise incorrect or outdated knowledge within LLMs without incurring the high cost of full retraining and risking catastrophic forgetting. Currently, most LLM editing datasets are confined to narrow knowledge domains and cover a limited range of editing evaluation. They often overlook the broad scope of editing demands and the diversity of ripple effects resulting from edits. In this context, we introduce \uniedit, a unified benchmark for LLM editing grounded in open-domain knowledge. First, we construct editing samples by selecting entities from 25 common domains across five major categories, utilizing the extensive triple knowledge available in open-domain knowledge graphs to ensure comprehensive coverage of the knowledge domains. To address the issues of generality and locality in editing, we design an Neighborhood Multi-hop Chain Sampling (NMCS) algorithm to sample subgraphs based on a given knowledge piece to entail comprehensive ripple effects to evaluate. Finally, we employ proprietary LLMs to convert the sampled knowledge subgraphs into natural language text, guaranteeing grammatical accuracy and syntactical diversity. Extensive statistical analysis confirms the scale, comprehensiveness, and diversity of our \uniedit benchmark. We conduct comprehensive experiments across multiple LLMs and editors, analyzing their performance to highlight strengths and weaknesses in editing across open knowledge domains and various evaluation criteria, thereby offering valuable insights for future research endeavors.

Data attribution methods quantify the influence of training data on model outputs and are becoming increasingly relevant for a wide range of LLM research and applications, including dataset curation, model interpretability, data valuation. However, there remain critical gaps in systematic LLM-centric evaluation of data attribution methods. To this end, we introduce DATE-LM (Data Attribution Evaluation in Language Models), a unified benchmark for evaluating data attribution methods through real-world LLM applications. DATE-LM measures attribution quality through three key tasks — training data selection, toxicity/bias filtering, and factual attribution. Our benchmark is designed for ease of use, enabling researchers to configure and run large-scale evaluations across diverse tasks and LLM architectures. Furthermore, we use DATE-LM to conduct a large-scale evaluation of existing data attribution methods. Our findings show that no single method dominates across all tasks, data attribution methods have trade-offs with simpler baselines, and method performance is sensitive to task-specific evaluation design. Finally, we release a public leaderboard for quick comparison of methods and to facilitate community engagement. We hope DATE-LM serves as a foundation for future data attribution research in LLMs.

Orientation-rich images, such as fingerprints and textures, often exhibit coherent angular directional patterns that are challenging to model using standard generative approaches based on isotropic Euclidean diffusion. Motivated by the role of phase synchronization in biological systems, we propose a score-based generative model built on periodic domains by leveraging stochastic Kuramoto dynamics in the diffusion process. In neural and physical systems, Kuramoto models capture synchronization phenomena across coupled oscillators -- a behavior that we re-purpose here as an inductive bias for structured image generation. In our framework, the forward process performs \textit{synchronization} among phase variables through globally or locally coupled oscillator interactions and attraction to a global reference phase, gradually collapsing the data into a low-entropy von Mises distribution. The reverse process then performs \textit{desynchronization}, generating diverse patterns by reversing the dynamics with a learned score function. This approach enables structured destruction during forward diffusion and a hierarchical generation process that progressively refines global coherence into fine-scale details. We implement wrapped Gaussian transition kernels and periodicity-aware networks to account for the circular geometry. Our method achieves competitive results on general image benchmarks and significantly improves generation quality on orientation-dense datasets like fingerprints and textures. Ultimately, this work demonstrates the promise of biologically inspired synchronization dynamics as structured priors in generative modeling.

While large language models (LLMs) can solve PhD-level reasoning problems over long context inputs, they still struggle with a seemingly simpler task: *following explicit length instructions*—e.g., *write a 10,000-word novel*. Additionally, models often generate far too short outputs, terminate prematurely, or even refuse the request. Existing benchmarks focus primarily on evaluating generations quality, but often overlook whether the generations meet length constraints. To this end, we introduce **Length Instruction Following Evaluation Benchmark** (LIFEBench) to comprehensively evaluate LLMs' ability to follow length instructions across diverse tasks and a wide range of specified lengths. LIFEBench consists of 10,800 instances across 4 task categories in both English and Chinese, covering length constraints ranging from 16 to 8192 words. We evaluate 26 widely-used LLMs and find that most models reasonably follow short-length instructions but deteriorate sharply beyond a certain threshold. Surprisingly, almost all models fail to reach the vendor-claimed maximum output lengths in practice, as further confirmed by our evaluations extending up to 32K words. Even long-context LLMs, despite their extended input-output windows, counterintuitively fail to improve length-instructions following. Notably, Reasoning LLMs outperform even specialized long-text generation models, achieving state-of-the-art length following. Overall, LIFEBench uncovers fundamental limitations in current LLMs' length instructions following ability, offering critical insights for future progress.

There has been increasing research interest in AI/ML for social impact, and correspondingly more publication venues refining review criteria for practice-driven AI/ML research. However, these review guidelines tend to most concretely recognize projects that simultaneously achieve deployment and novel ML methodological innovation. We argue that this introduces incentives for researchers that undermine the sustainability of a broader research ecosystem of social impact, which benefits from projects that make contributions on one front (applied _or_ methodological) that may better meet project partner needs. Our position is that researchers and reviewers in machine learning for social impact must simultaneously adopt: 1) a more expansive conception of social impacts beyond deployment and 2) more rigorous evaluations of the impact of deployed systems.

We introduce HeisenVec, a large-scale dataset designed to advance research in vector graphics generation from natural language descriptions. Unlike conventional image generation datasets that focus on raster images, HeisenVec targets the structured and symbolic domain of Scalable Vector Graphics (SVG), where images are represented as sequences of drawing commands and style attributes. The dataset comprises 2.2 million SVGs collected from different online sources, each paired with four complementary textual descriptions generated by multi-modal models. To ensure structural consistency and efficiency for autoregressive modeling, all SVGs are standardized through a pre-processing pipeline that unifies geometric primitives as paths, applies affine transformations, and compresses syntax via custom tokens set. HeisenVec exhibits broad coverage among visual styles and sequence lengths, with a substantial portion of samples exceeding 8,000 tokens, making it particularly well-suited for benchmarking long-context language models. Our benchmark enables rigorous evaluation of text-conditioned SVG generation, encourages progress on sequence modeling with symbolic outputs, and bridges the gap between vision, graphics, and language. We release the dataset, tokenization tools, and evaluation pipeline to foster further research in this emerging domain.

CAPTCHAs have been a critical bottleneck for deploying web agents in real-world applications, often blocking them from completing end-to-end automation tasks. While modern multimodal LLM agents have demonstrated impressive performance in static perception tasks, their ability to handle interactive, multi-step reasoning challenges like CAPTCHAs is largely untested. To address this gap, we introduce **Open CaptchaWorld**, the first web-based benchmark and platform specifically designed to evaluate the visual reasoning and interaction capabilities of MLLM-powered agents through diverse and dynamic CAPTCHA puzzles. Our benchmark spans 20 modern CAPTCHA types, totaling 225 CAPTCHAs, annotated with a new metric we propose: CAPTCHA Reasoning Depth, which quantifies the number of cognitive and motor steps required to solve each puzzle. Experimental results show that humans consistently achieve near-perfect scores, state-of-the-art MLLM agents struggle significantly, with success rates at most **40.0\%** by Browser-Use Openai-o3, far below human-level performance,**93.3\%**. This highlights Open CaptchaWorld as a vital benchmark for diagnosing the limits of current multimodal agents and guiding the development of more robust multimodal reasoning systems.

Large language models (LLMs) frequently refuse to respond to pseudo-malicious instructions: semantically harmless input queries triggering unnecessary LLM refusals due to conservative safety alignment, significantly impairing user experience. Collecting such instructions is crucial for evaluating and mitigating over-refusals, but existing instruction curation methods, like manual creation or instruction rewriting, either lack scalability or fail to produce sufficiently diverse and effective refusal-inducing prompts. To address these limitations, we introduce EVOREFUSE, a prompt optimization approach that generates diverse pseudo-malicious instructions consistently eliciting confident refusals across LLMs. EVOREFUSE employs an evolutionary algorithm exploring the instruction space in more diverse directions than existing methods via mutation strategies and recombination, and iteratively evolves seed instructions to maximize evidence lower bound on LLM refusal probability. Using EVOREFUSE, we create two novel datasets: EVOREFUSE-TEST, a benchmark of 582 pseudo-malicious instructions that outperforms the next-best benchmark with 85.34% higher average refusal triggering rate across 9 LLMs, 34.86% greater lexical diversity, and 40.03% improved LLM response confidence scores; and EVOREFUSE-ALIGN, which provides 3,000 pseudo-malicious instructions with responses for supervised and preference-based alignment training. LLAMA3.1-8B-INSTRUCT supervisedly fine-tuned on EVOREFUSE-ALIGN achieves up to 29.85% fewer over-refusals than models trained on the second-best alignment dataset, without compromising safety. Our analysis with EVOREFUSE-TEST reveals models trigger over-refusals by overly focusing on sensitive keywords while ignoring broader context. Our code and datasets are available at https://github.com/FishT0ucher/EVOREFUSE.

Existing Embodied Question Answering (EQA) benchmarks primarily focus on household environments, often overlooking safety-critical aspects and reasoning processes pertinent to industrial settings. This drawback limits the evaluation of agent readiness for real-world industrial applications. To bridge this, we introduce IndustryEQA, the first benchmark dedicated to evaluating embodied agent capabilities within safety-critical industrial warehouse scenarios. Built upon the NVIDIA Isaac Sim platform, IndustryEQA provides high-fidelity episodic memory videos featuring diverse industrial assets, dynamic human agents, and carefully designed hazardous situations inspired by real-world safety guidelines. The benchmark includes rich annotations covering six categories: equipment safety, human safety, object recognition, attribute recognition, temporal understanding, and spatial understanding. Besides, it also provides extra reasoning evaluation based on these categories. Specifically, it comprises 971 question-answer pairs generated from small warehouse scenarios and 373 pairs from large ones, incorporating scenarios with and without human. We further propose a comprehensive evaluation framework, including various baseline models, to assess their general perception and reasoning abilities in industrial environments. IndustryEQA aims to steer EQA research towards developing more robust, safety-aware, and practically applicable embodied agents for complex industrial environments.

Super-resolution (SR) advances astronomical imaging by enabling cost-effective high-resolution capture, crucial for detecting faraway celestial objects and precise structural analysis. However, existing datasets for astronomical SR (ASR) exhibit three critical limitations: flux inconsistency, object-crop setting, and insufficient data diversity, significantly impeding ASR development. We propose STAR, a large-scale astronomical SR dataset containing 54,738 flux-consistent star field image pairs covering wide celestial regions. These pairs combine Hubble Space Telescope high-resolution observations with physically faithful low-resolution counterparts generated through a flux-preserving data generation pipeline, enabling systematic development of field-level ASR models. To further empower the ASR community, STAR provides a novel Flux Error (FE) to evaluate SR models in physical view. Leveraging this benchmark, we propose a Flux-Invariant Super Resolution (FISR) model that could accurately infer the flux-consistent high-resolution images from input photometry, suppressing several SR state-of-the-art methods by 24.84% on a novel designed flux consistency metric, showing the priority of our method for astrophysics. Extensive experiments demonstrate the effectiveness of our proposed method and the value of our dataset. Code and models are available at https://github.com/GuoCheng12/STAR.