NeurIPS 2026 论文列表

As Embodied Agents System (EAS) move into physical domains such as autonomous navigation and household assistance, reliable execution becomes critical for physical task completion and collaboration trust. Recent EAS reliability evaluation works typically focus on outcome-centric metrics as success rate or safety-only scores to assess an agent's performance, which collapse diverse execution trajectories into coarse outcomes. Therefore they ignore a critical property of EAS -- which we define as the **Resilience** -- that reflects how EASs recover, stabilize, and extend under perturbations and across iterative updates. The lack of resilience is particularly critical in open-world environments due to continuous unexpected disruptions, thus directly affecting the quality of EAS deployment. To address this problem, we gain insight from the resilience-engineering concepts to EAS groundings and propose a novel resilience evaluation framework that can be flexibly applied to any EAS. Specifically, we define the first comprehensive resilience metrics suite for EASs system that exposes *Rebound*, *Stability*, and *Graceful Extensibility* across embodied tasks execution, providing a practical grounding for EAS resilience analysis. We further implement the resilience evaluation layer that transforms execution evidence into assessments for comparison, diagnosis and optimization. Across 400 household tasks with 10 representative EAS baselines, our evaluation reveals process-level distinction hidden by outcome metrics, including recovery cost differences among successful episodes ($\Delta C_{\mathrm{rec}}=25.2$), increased instability under semantic perturbations, and task-family-specific degradation under stress. Metrics-guided optimizations reduce recovery cost by 42.94%, increase stability by 19.87%, and improve graceful extensibility completion by 10.08%, showing the diagnostic effect of resilience evaluation. Beyond these targeted gains, our results reveal trade-offs among resilience characteristics, suggesting that a resilient EAS construction should be evaluated and configured according to deployment-specific requirements. Our code and data are available at .

We show that Fréchet Distance (FD), long considered impractical as a training objective, can in fact be effectively optimized in the representation space. Our idea is simple: decouple the population size for FD estimation (e.g., 50k) from the batch size for gradient computation (e.g., 1024). We term this approach FD-Loss. Optimizing FD-Loss reveals several surprising findings. First, post-training a base generator with FD-Loss in different representation spaces consistently improves visual quality. Under the Inception feature space, a one-step generator achieves 0.72 FID on ImageNet $256\times256$. Second, the same FD-Loss repurposes multi-step generators into strong one-step generators without teacher distillation, adversarial training or per-sample targets. Third, FID can misrank visual quality: modern representations can yield better samples despite worse Inception FID. This motivates FDr$^{k}$, a multi-representation metric. We hope this work will encourage further exploration of distributional distances in diverse representation spaces as both training objectives and evaluation metrics for generative models. Code and checkpoints will be open-sourced.

Anchor graphs are a standard route to scalable multi-view clustering, but most existing pipelines still depend on either a shared anchor set sampled from concatenated features or a separate anchor-alignment stage before fusion. Both choices are restrictive: the former hard-codes equal anchor budgets and importance at anchor-construction time, while the latter introduces a cumbersome correspondence problem and still struggles with unequal anchor numbers. We develop an alignment-free probabilistic formulation in which view-specific anchor graphs are noisy manifestations of a shared latent cluster identity rather than objects that require cross-view correspondence. Each view has its own anchor space, number of anchors and cluster prototypes; the only shared latent variable is the sample label. We instantiate this idea with a Gaussian latent-label model and a deterministic prototype M-step. The resulting variational EM algorithm admits closed-form updates with convergence guarantees, while experiments demonstrate competitive clustering performance and practical runtime on most datasets.

Empirical Risk Minimization treats training samples uniformly, which can degrade performance in noisy or heterogeneous settings. We introduce a reference-guided objective that uses per-sample error comparisons with a fixed reference model to reweight gradient contributions without relying on prediction imitation, while preserving gradient direction and ensuring bounded scaling. Theoretical analysis shows that the formulation induces adaptive weighting with controlled amplification. Experiments on image classification with synthetic label noise and on time-series forecasting demonstrate broad improvements across architectures, particularly in moderate-to-high noise and heterogeneous regimes. Results further indicate that the method is most effective when the error-ranking alignment between the baseline model and the reference model is low, suggesting that gains arise primarily from the diversity of the reference error ranking relative to the learner, rather than the reference's absolute performance.

Diffusion models generate samples by iteratively querying learned score estimates. A rapidly growing literature focuses on accelerating sampling by minimizing the number of score evaluations, yet the information-theoretic limits of such acceleration remain unclear. In this work, we establish the first score query lower bounds for diffusion sampling. We prove that for $d$-dimensional distributions, given access to score estimates with polynomial accuracy $\varepsilon=d^{-O(1)}$ (in any $L^p$ sense), any sampling algorithm requires $\widetilde{\Omega}(\sqrt{d})$ adaptive score queries. In particular, our proof shows that any sampler must search over $\widetilde{\Omega}(\sqrt{d})$ distinct noise levels, providing a formal explanation for why multiscale noise schedules are necessary in practice.

Post-training quantization (PTQ) is widely used to deploy large language models efficiently, but its effect on reasoning models is not well understood. Across math, coding, and science QA, we find that aggressive PTQ reduces accuracy while increasing chain-of-thought (CoT) length. Surprisingly, we show that in up to 52% of the quantized models' failures, models reach the right answer in intermediate reasoning steps but do not output it as a final answer. To understand why quantization leads to this increase in overthinking errors, we measure the token-level KL divergence between quantized and full-precision output distributions. Positions with high KL divergence correlate strongly with high next-token entropy, and at these positions quantized models disproportionately sample overthinking markers such as “wait", “but", and “alternatively". We show that simply introducing a training-free logit penalty on a curated set of overthinking markers can reduce CoT length by 12--23% while preserving or improving accuracy across 5 models (1.5B--32B parameters), 3 quantization methods, and 5 benchmarks, yielding the best Pareto frontier of accuracy against reasoning cost. Overthinking errors produced by quantized models are particularly reduced by up to 58%.

Minimum Description Length (MDL) formalizes the principle of Occam's razor by optimizing the total description length: $L(\mathrm{model})+L(\mathrm{data} \ | \ \mathrm{model})$. For sequential prediction, the MDL method repeatedly selects a model with a minimum objective score of the observed prefix for the next step prediction. Classical MDL prediction theory shows that exact optimization of the MDL objective indeed provides a strong compression guarantee that supports reliable prediction. However, practical machine learning usually can only find models by approximately optimizing the objective function. To bridge this gap, this paper addresses the following fundamental question: \emph{Under what forms of approximation and regularization does approximate MDL still guarantee reliable sequential prediction?} This work offers a principled characterization. We prove that for any approximation with \emph{additive} slack \(C\) of the more general form of the \emph{balanced} MDL objective: $\lambda\cdot L(\mathrm{model})+L(\mathrm{data} \ | \ \mathrm{model})$, the cumulative expected squared prediction error is finite for all $\lambda\ge1$. The case $\lambda>1$ is proved by an affinity-telescoping argument, while the boundary case $\lambda=1$ is proved by a likelihood-ratio stopping argument based on exact static MDL bounds. Our results establish that classical MDL regularization remains robust to any fixed additive optimization error. Furthermore, we establish that our characterization of the approximate MDL framework is sharp: When $0<\lambda<1$, overfits can happen to incur infinite cumulative expected error in the universal class of estimable measures, and hence a strong form of model-complexity regularization is necessary. In addition, model selection may fail in every regularized regime $\lambda >0$, under multiplicative approximation, and thus, additive approximation is both sufficient and essential.

This position paper argues that {\sl fair representations cannot hold what they promise}. Fair representation learning has been a significant trend in research on fairness for machine learning models over the past decade. The main idea of fair representation learning is to provide a data preprocessing mechanism which can facilitate fairness for downstream tasks, and research papers in this area often insinuate a fairness guarantee for all downstream tasks without further qualification. However, provably this cannot be satisfied by any non-degenerate representation. We argue that such over-promising can be harmful in downstream applications and that the responsibility for fairness cannot safely be outsourced to a representation provider in the way current research seems to suggest. As a minimal requirement for a way forward, we suggest that newly proposed fairness representations should be accompanied by compatibility tests that would allow a user to verify whether the representation will actually guarantee fairness for the task at hand.

Many projection-based imaging modalities reconstruct unknown objects from collections of noisy projections related by unknown in-plane rotations, making effective estimation dependent on rotationally consistent alignment and aggregation. In cryogenic electron microscopy (cryo-EM), the extremely low signal-to-noise ratio (SNR) makes such multi-image integration essential. We introduce the *polar transformer*, a permutation-invariant architecture for *sets* of images built around an $\mathrm{SO}(2)^K$-equivariant *angular attention* mechanism that jointly aligns and aggregates information across images. This architecture leverages a stable polar representation in which we define polar CNN feature extractors and evaluate attention weights over all relative angular shifts efficiently via FFT-based correlations, guaranteeing equivariance to independent in-plane rotations of each image in the set. We evaluate the polar transformer on simulated cryo-EM images using denoising as a quantitative proxy. Across different regimes, polar transformers outperform strong single-image and image-set baselines, achieving a reduction of up to 40% in relative MSE at an SNR of 0.02 and improving downstream ab initio reconstruction resolution by 20%.

AI tools are increasingly integrated into real-world workflows. However, existing measures of reliance on these tools focus on AI output adoption or on self-reported indicators, rather than how task effort is distributed between users and tools. Here, we introduce offloading score, a measure of reliance that quantifies the fraction of cognitive effort offloaded to an AI tool. Offloading score is simulation-based---we construct a counterfactual workflow by estimating how the user would have completed the task without the tool, and then computing the fraction of steps saved by using the tool. We validate offloading score through intrinsic evaluations of metric validity, and a controlled user study ($n=40$) with developers performing programming tasks using AI tools. We vary time pressure to test whether reliance measures capture the known increase in reliance under time pressure. We show that offloading score detects significantly higher reliance in time-constrained settings ($+43\%$, $p=0.018$), while usage-based and self-reported baseline measures do not distinguish the conditions. We complement this with descriptive insights showing that higher reliance manifests as greater delegation and more direct reuse of AI outputs. Finally, we demonstrate an approach of using offloading score in combination with target outcomes of reliance (e.g., task understanding) to identify when reliance may be (in)appropriate. Our framework offers two contributions: an instrument users can apply to measure and reflect on their own reliance, and a quantitative signal that agent designers can utilize to mitigate overreliance.

Digital entities such as AI agents and humanoid robots increasingly operate alongside real humans, yet their identity infrastructure is based on credentials rather than embodied biometric identity. We introduce Biometric Identity Provisioning (BIP), a new problem and solution framework that addresses: given an enrollment gallery of real human identities, provision virtual identities that are non-colliding with every enrolled identity, maintain sufficient inter-class separability, and are realizable as high-fidelity face images. The key geometric insight is that real face identities occupy a low-dimensional subspace of the embedding hypersphere, leaving no residual subspace for virtual identities. Hence, virtual identities must instead be allocated as unclaimed gaps within the real face manifold itself. BIP is therefore a constrained packing problem: available gaps vastly exceed any foreseeable enrollment scale, and provisioned identities remain non-colliding even as new real identities are subsequently enrolled. Grounded in this geometry, our repulsion-based allocation is not bounded by any fixed provisioning count; we demonstrate 10M non-colliding virtual identity embeddings against a gallery of 360K real identities. Realizing these embeddings as face images requires a generator that operates outside the training distribution of real face images; we introduce GapGen, a gap-aware generator trained with a curriculum that progressively extends synthesis into non-colliding regions, validated at 1M photorealistic virtual face images. We further construct v-LFW, a virtual counterpart to LFW face dataset, with protocols for virtual face verification, cross-reality matching, real-vs-virtual detection, and unified recognition and detection.

Neural populations exhibit heterogeneous tuning: Neurons differ in their selectivity, gain, and in how their preferred inputs are distributed across stimulus or latent-variable space. While this heterogeneity has been studied extensively in the context of encoding precision, its implications for learning and generalization are less well-understood. Here, we develop a probabilistic theory that links a neural population's tuning statistics to its inductive bias: in large populations, the tuning statistics induce a kernel and, equivalently, a prior of a generative model over functions. This prior in turn predicts the population's ability to generalize across a distribution of related tasks. Our theory determines the population tuning statistics that minimize the generalization error over a distribution of functions. We further present a normative account of tuning adaptation inspired by our probabilistic approach, showing that tuning changes that maximize the marginal likelihood of observed data systematically reduce generalization error relative to non-adapting populations. Applied to the adaptation of hippocampal spatial representations in a reward learning task, we found that our theory could explain the over-representation of rewarding locations through experience in an environment with a localized reward. We further demonstrate how different components of the population's generative model differentially impact the speed and magnitude of tuning adaptation. Overall, our work proposes a novel connection between tuning variability and a population's ability to learn and to generalize across tasks and develops a Bayesian theory of tuning adaptation in neural populations during learning.

Activation monitoring, which probes a model's internal states using lightweight classifiers, is an emerging tool for AI safety. However, its worst-case robustness under a misalignment threat model, where a model might learn to actively conceal its internal states, remains untested. We ask: could a model learn to evade previously unseen activation monitors? We demonstrate that fine-tuning can create **Neural Chameleons**: models capable of zero-shot evading activation monitors. Specifically, we fine-tune an LLM to evade monitors for benign concepts (e.g., HTML) when conditioned on a trigger phrase "You are being probed for {concept}". This learned mechanism generalizes zero-shot: substituting the concept with a safety-relevant term like 'deception' causes the model to successfully evade previously unseen safety monitors, even those trained post hoc on no-trigger activations from the frozen fine-tuned checkpoint. We validate this across diverse model families (Llama, Gemma, Qwen), finding that evasion is highly selective to the triggered concept and incurs minimal capability degradation. Mechanistic analyses suggest that the trigger induces an activation shift that moves representations away from probe-aligned directions. Our work provides a proof-of-concept for this failure mode of activation monitoring under misalignment threat models.

Building general-purpose reasoning models with reinforcement learning (RL) entails substantial cross-domain heterogeneity, including large variation in inference-time response lengths and verification latency. Such variability complicates the RL infrastructure, slows training, and makes training curriculum (e.g., response length extension) and hyperparameter selection challenging. In this work, we propose cascaded domain-wise reinforcement learning (Cascade RL) to develop Nemotron-Cascade, capable of operating in both \emph{instruct} and deep \emph{thinking} modes, without any performance gap relative to a thinking-only counterpart. Departing from conventional approaches that blend heterogeneous prompts from different domains, Cascade RL orchestrates sequential, domain-wise RL, reducing engineering complexity and delivering state-of-the-art performance across a wide range of benchmarks. Notably, RLHF for alignment, when used as a pre-step, boosts the model's reasoning ability far beyond mere preference optimization, and subsequent domain-wise RLVR stages rarely degrade the benchmark performance attained in earlier domains and may even improve it. Our 14B model, after RL, outperforms its SFT teacher, DeepSeek-R1-0528, on LiveCodeBench v5/v6/Pro and achieves silver-medal performance in the 2025 International Olympiad in Informatics (IOI). We transparently share our training and data recipes.

Open-world semi-supervised learning aims to use limited labeled data from known classes to classify unlabeled samples that contain both known and novel classes. Most existing methods over-rely on known classes and tend to generalize incorrectly in complex open-world settings. This leads to degraded pseudo-label quality and the model is often overconfident in wrong predictions. To address this, this paper proposes a **M**itigating **C**onfidence **M**iscalibration Method in **Open**-World Semi-Supervised Learning (**OpenMCM**). By leveraging discriminative knowledge from known classes to guide learning in the novel class space, our method effectively mitigates overconfident misclassifications and improves discrimination accuracy. Furthermore, we propose an adaptive threshold calibration strategy to independently determine optimal decision boundary for each class. By integrating a high-reliable pseudo-label fusion mechanism, we enhance recognition stability for novel classes. Experiments on three benchmark datasets ($i.e.$, CIFAR-10, CIFAR-100, and ImageNet-100) show that our framework achieves performance improvements over existing state-of-the-art methods.

Visual decoding from brain signals is a key challenge at the intersection of computer vision and neuroscience, requiring methods that bridge neural representations and computational models of vision. A field-wide goal is to achieve accurate, generalizable decoding from non-invasive, temporally resolved signals, including electroencephalography (EEG). A major obstacle towards this goal is the low signal-to-noise ratio of EEG and the substantial inter-subject variability, which render direct end-to-end EEG–image supervision weak and unstable. To address this, we introduce a tri-modal contrastive framework for EEG-based visual decoding that aligns EEG, visual, and textual representations within a unified latent space. Our approach follows a two-stage design. First, we pre-train an EEG encoder via masked reconstruction on unlabeled trials, learning spatio-temporal regularities that transfer robustly downstream. Second, we jointly align EEG, image, and LLM-generated textual descriptions through contrastive learning, where text supervision acts as a semantic regularizer that injects linguistic structure into the shared space without overwhelming the primary EEG–image signal. The encoder integrates subject-specific adaptation, graph-attention over channels, and temporal-spatial convolutional embeddings. On the Things-EEG2 200-way zero-shot benchmark, our framework achieves 54.1\% Top-1 and 83.4\% Top-5 accuracy, substantially exceeding the strongest prior baseline (32.4\% / 64.0\%), with paired Wilcoxon tests confirming significance (p < 0.01) over all in-subject baselines. We validate generalization on Things-MEG. Analysis reveals that compact embedding geometries (CN-CLIP) outperform much larger backbones, and that decoding aligns with established neurophysiology of visual processing. This work is a critical step towards robust, semantically-grounded visual decoding from non-invasive temporal neural signals.

Estimating the number of distinct elements in a data stream is well understood when repeated elements are identical. In modern settings, however, observations are high-dimensional and noisy, so repeated instances of the same object are only approximately similar -- for example, different images of the same individual may vary significantly at the pixel level. Classical sketches such as HyperLogLog rely on consistent hash values for identical elements and break down in this regime. Recent work on robust distinct counting in general metric spaces achieves $\tilde\Theta(\sqrt{n})$ memory, which is tight in the worst case. We show that substantially improved memory guarantees are possible under geometric structure common in learned representations. We introduce MaxSketch, a simple max-linear sketch built from random Gaussian projections, and prove that it succeeds in estimating the number of distinct latent objects. Concretely, we show that under this assumption $m = \tilde{O}(\log n / \varepsilon^4)$ random projections (and hence $\tilde{O}(\log n/\varepsilon^4)$ memory) suffice to recover the true distinct count within a $(1+\varepsilon)$ factor. Experiments on image streams confirm that MaxSketch accurately estimates distinct counts and generalizes beyond the training regime. Our results bridge classical streaming algorithms and modern representation learning, showing how geometric structure can fundamentally reduce the complexity of distinct counting.

Understanding and predicting wildlife movement is critical for ecology and conservation. While trajectory forecasting has advanced for human and vehicle movement, wildlife trajectories present distinct challenges: they are unconstrained in space, highly stochastic, and influenced by environmental conditions. We introduce MOVEBENCH, the first large-scale benchmark for probabilistic wildlife movement forecasting, containing 2.6M GPS locations from 800+ individuals across 110 species in 127 countries, paired with 1.6B environmental raster tiles capturing 160 covariates known or hypothesized to influence movement. We propose a probabilistic evaluation protocol for movement trajectory forecasts, addressing limitations of point-prediction metrics for inherently stochastic phenomena. Through comprehensive empirical evaluation of four method families across multiple temporal and spatial scales, we reveal that: (1) existing predictive methods generalize better to future timepoints than to unseen individuals, (2) deep learning approaches do not consistently outperform simpler baselines, and (3) environmental covariate selection significantly impacts performance. MOVEBENCH enables standardized evaluation of movement forecasting methods and provides a foundation for methodological advances on this ecologically important task.

Modern AI progress has been driven by ML methods that are generalizable across settings and scalable to larger regimes. As large language models demonstrate advanced capabilities in reasoning, coding, and engineering tasks, it is increasingly important to understand whether they can discover such methods rather than only apply existing ones. We introduce MLS-Bench, a benchmark for evaluating whether AI systems can invent generalizable and scalable ML methods. MLS-Bench contains 140 tasks across 12 domains, each requiring an agent to improve one targeted component of an ML system or algorithm and demonstrate that the improvement generalizes across controlled settings and scales. We find that current agents remain far from reliably surpassing human-designed methods, and that engineering-style tuning is easier for them than genuine method invention. We further study the effects of test-time scaling, adaptive compute allocation, and context provision on agents' discovery performance, together with case studies of their behavior. Our analyses suggest that the bottleneck is not only in proposing new methods, but also in the scientific insight needed to plan, validate, and scale claims about them. More search, compute, or context alone does not remove this bottleneck. We build and maintain a community platform for cumulative and comparable iteration, and release the data and code at https://mls-bench.com.