NeurIPS 2026 论文列表

The Normalized Transformer, or nGPT (Loshchilov et al., 2025) achieves impressive training speedups and does not require weight decay or learning rate warmup. However, despite having hyperparameters that explicitly scale with model size, we observe that nGPT does not exhibit learning rate transfer across model dimension and token horizon. To rectify this, we combine numerical experiments with a principled use of alignment exponents (Everett et al., 2024) to revisit and modify the $\mu$P approach to yperparameter transfer (Yang and Hu, 2021). The result is a novel nGPT parameterization we call $\nu$GPT. Through extensive empirical validation, we find $\nu$GPT exhibits learning rate transfer across width, depth, and token horizon.

Deliberating takes time. In real-time settings, that time is not free. Standard reinforcement learning (RL) sidesteps this as the environment waits indefinitely for the agent's decision. Instead, we study real-time RL environments where the environment progresses while waiting for the agent's action. Building on prior real-time formalizations, we introduce variable-delay real-time RL, where the agent chooses how long to deliberate at each decision point since the environment progresses. For the planning agents we use, the right delay is state-dependent, and naively planning how long to plan can paralyze the agent. We instead approach this setting by training a lightweight gating policy on top of a planner to select state-dependent planning budgets. Across real-time Pac-Man, Tetris, Snake, Speed Hex, and Speed Go, our gating policy outperforms fixed-budget and heuristic baselines, and transfers to a real-time setup where the environment and agent run on two different GPUs.

Forward-Forward (FF) training allows each layer to learn from a local goodness criterion. In cumulative-goodness variants, however, later layers can inherit a task that earlier layers have already partially separated. We formalize this phenomenon as layer free-riding: under the softplus FF criterion, the class-discrimination gradient reaching block $d$ decays exponentially with the positive margin accumulated by preceding blocks. We then study three local remedies---per-block, hardness-gated, and depth-scaled---that recover current-layer separation measures without relying on backpropagated gradients. On CIFAR-10 and CIFAR-100, these remedies dramatically improve layer-separation statistics, with $4\times$--$45\times$ gains in deeper layers, while changing accuracy by less than one percentage point for non-degenerate training procedures. Tiny ImageNet provides a tougher cross-dataset check for our selected block-wise configuration and reveals the same qualitative gap between layer-health diagnostics and final accuracy. Calibration experiments further show that architecture and augmentation choices have a larger effect on final accuracy than the training-rule modifications studied here. Cumulative free-riding is therefore a real and repairable optimization pathology. Nonetheless, for the FF training rules, architectures, and datasets we study, it is not the dominant factor limiting achievable accuracy.

Personal intelligence agents aim to support users across daily-life tasks by learning their preferences, routines, needs, and emotional states from long-term interaction. They are expected to anticipate user needs, provide proactive assistance, and infer preferences that users have never explicitly articulated. However, existing benchmarks for LLM personalization lack real user data spanning extended periods and diverse daily-life domains, and typically reduce personalization to simplified settings such as recommendation or fact retrieval. We introduce JARVIS-Bench, a new benchmark for evaluating personal intelligence agents, curated from real users’ daily traces and augmented with synthetic trajectory expansions grounded in implicit-preference insights from surveys and structured personas. JARVIS-Bench is built from participants who contributed 28 to 44 days of multimodal self-tracking logs, structured personas, and a 100-question implicit-preference survey spanning eight domains. It supports four downstream task surfaces: implicit preference reasoning, proactive-help prediction, emotion-aware modeling, and cross-domain transfer, all evaluated through a unified event iterator and long-horizon user-memory pipeline. We benchmark 28 LLMs from 10 model families, including Gemini, GPT, Qwen, Gemma, and Claude, across a five-condition input ladder ranging from no memory to lifelong memory. Results show that memory and model scaling improve personalization, yet current frontier models remain far from achieving robust real-world personal intelligence.

We ask whether agentic AI systems built for software engineering transfer to realistic hardware engineering. Existing hardware LLM benchmarks isolate sub-tasks but none jointly requires repository navigation, hierarchy-aware localization, Electronic Design Automation (EDA) executable verification, and maintenance-style patching. We introduce **Phoenix-bench**, a synchronized corpus of 511 verified Verilator instances from 114 GitHub repositories, each shipped with the developer patch, design-flow labels, fail-to-pass and pass-to-pass testbenches, and a Docker-pinned EDA environment so resolved-rate differences reflect agent behavior rather than toolchain availability. Using Phoenix-bench we run a uniform evaluation of four commerical agents and eight open-source agentic structures across four LLM backbones, plus two diagnostic interventions (file-level oracle localization and one round of testbench-log feedback). Three findings emerge. **Software and hardware are fundamentally different engineering tasks:** the same agent loses 37\% to 58\% from SWE-bench Verified to Phoenix-bench because hardware bugs propagate across parallel instantiated modules through signal flow rather than along a software-style call graph, and software-tuned agents stop at the symptom file instead of tracing back through the instantiation chain. **Failures concentrate on design control-flow / Finite State Machine bugs, verification testbench bugs, and hard cases** that demand cross-hierarchy signal-flow tracking and coordinated multi-file edits. **Localization granularity matters far more than localization itself:** a perfect file-level oracle yields only $+1.4$\% because the agent then breaks files that did not need editing, while a single round of test case feedback lifts resolved rate by $42$\% to $45$\% because the test case tells *where* the bug is and *what* the fix has to look like.

LLMs are increasingly used with external knowledge sources like the Internet. Do they weigh information appropriately---updating more for reliable sources (source discernment) and more when claims bring priors closer to the truth (truth discernment)? We formalize this as information discernment and introduce Learn2Discern (L2D), an experimental framework and benchmark grounded in three normative axioms with interpretable metrics. To establish external validity, a pre-registered, quota-matched user study (n=299) confirms that real LLM users endorse all three axioms and report that violations reduce their trust and usage intent. Across 13 models and nearly 670K trials, we find consistent failures across both dimensions: models perform near chance on source and truth discernment, rely on source popularity twice as much as source reliability, and update roughly equally whether a claim improves or worsens their position relative to the ground truth. Models integrate external knowledge most effectively on datasets where their priors are already the most accurate. Newer and larger models improve truth discernment but not source discernment, a blind spot that model complexity does not address. We identify simple inference-time interventions that meaningfully improve both forms of discernment. We release our dataset, metrics, and survey as a testbed for a core alignment property that scales in importance as LLMs replace traditional search.

Diffusion-based generators set the current state of the art for synthetic tabular data, deployed downstream wherever direct access to real records is restricted. These methods approach but rarely exceed real-data utility on downstream tasks, and closing this synthetic--real performance gap has so far been pursued exclusively at training time, via architectural advances, scaling, and retraining of monolithic generators. The inference-time alternative, i.e., refining the outputs of a pre-trained backbone with parameters left untouched, has remained largely unexplored for tabular synthesis. We introduce $\textbf{TARDIS}$ (Tabular generation through Refinement, Distillation, and Inference-time Sampling), an inference-time refinement framework that operates on a frozen pre-trained backbone, configured per dataset by a Tree-structured Parzen Estimator search over score-level guidance during reverse diffusion, with each trial's objective set by an inner grid search over post-hoc sample selectors and an optional soft-label distillation step. The search space encodes a single mathematical pattern we name $\textit{Bidirectional Chamfer Refinement}$ (BCR): the symmetric Chamfer functional between synthetic and real samples is minimized both continuously, via a score-level gradient during reverse diffusion, and discretely, via batch-ranking post-generation. On the majority of datasets the search selects BCR-aligned configurations over alternatives encoded in the search space, evidence both for BCR as the dominant refinement pattern and for TARDIS's per-dataset search as a procedure that recovers this pattern. Across 15 binary, multiclass, and regression benchmarks TARDIS achieves a median $+8.6\%$ downstream-task improvement over models trained on real data (95\% CI $[+3.3, +16.4]$, Wilcoxon $p=0.016$, 11/15 strict wins) and improves over the underlying TabDiff backbone on all 15 datasets (mean $+12.9\%$, $p<10^{-4}$), matching the backbone on manifold fidelity, diversity, and sample-level privacy. The synthetic--real gap is therefore not primarily a training-time problem: on the studied corpus, inference-time refinement of a pre-trained tabular diffusion backbone reaches and exceeds real-data utility in 1 to 80 minutes on a single consumer-grade GPU.

Field trials use plot-level crop-state measurements to interpret how crops grow under real field conditions, but repeated measurements of canopy greenness, canopy amount, canopy closure, and growth stage require field visits, sensing campaigns, and post-processing. Modern wheat trials also collect weather records, trial metadata, field-camera images, UAV and satellite observations, proximal sensors, canopy products, and phenological surveys. Turning these records into a machine-learning benchmark is nontrivial because observations are sparse, asynchronous, unevenly collected, missing for structured reasons, and tied to measurement pipelines. We introduce INVITA-WheatFieldState, a benchmark derived from the INVITA wheat field-trial archive for estimating the crop state of a plot on a target date from observations available for that plot and date. Each plot-date example specifies a plot, date, and crop-state target, and is paired with available observations after temporal and source-provenance filtering. The derived dataset contains over 220k examples across NDVI, LAI, FCover, and Zadoks growth stage, covering canopy greenness, canopy amount, canopy closure, and phenological timing. LAI and FCover are released with provenance labels that distinguish product and proxy targets rather than pooled manual ground truth. The benchmark suite provides a plot-disjoint split matched to the plot-level experimental unit, validators, prediction schemas, regression representations, and prediction-level diagnostics. Results show that source, timing, metadata, and observation-availability structure are strong signals. Observation-set representations improve some all-example targets, while sensor-sequence, field-camera, and fusion representations remain target-dependent and coverage-bound. INVITA-WheatFieldState offers a concrete test case for ML methods that must learn from incomplete, asynchronous, and provenance-sensitive measurements used to study crop development in real fields.

Manifold learning is a fundamental task at the core of data analysis and visualisation. It aims to capture the simple underlying structure of complex high-dimensional data by preserving pairwise dissimilarities in low-dimensional embeddings. Traditional methods rely on symmetric Riemannian geometry, thus forcing symmetric dissimilarities and embedding spaces, e.g. Euclidean. However, this discards in practice valuable asymmetric information inherent to the non-uniformity of data samples. We suggest to harness this asymmetry by switching to Finsler geometry, an asymmetric generalisation of Riemannian geometry, and propose a Finsler manifold learning pipeline that constructs asymmetric dissimilarities and embeds in a Finsler space. This greatly broadens the applicability of existing asymmetric embedders beyond traditionally directed data to any data. We also modernise asymmetric embedders by generalising current reference methods to asymmetry, like Finsler t-SNE and Finsler UMAP. On controlled synthetic and large real datasets, we show that our asymmetric pipeline reveals valuable information lost in the traditional pipeline, e.g. density hierarchies, and consistently provides superior quality embeddings than their Euclidean counterparts.

AI agents are increasingly embedded in continuous integration and continuous delivery (CI/CD) workflows to autonomously review pull requests, triage issues, and maintain codebases. We study fully automated configurations in which external contributions invoke agents without prior human approval. Because these agents ingest untrusted content while operating with repository credentials and tools, prompt injection can have software supply chain consequences. We present GitInject, an open-source framework for evaluating prompt injection in live GitHub Actions workflows. Unlike benchmarks that simulate tool calls, GitInject provisions ephemeral repositories and executes actual workflows, exposing platform semantics such as sandbox constraints, credential handling, and permission boundaries. We use GitInject to evaluate eleven named attack scenarios across five workflows from four AI providers, covering configuration-file injection, credential exfiltration, judgment manipulation, and availability. Every provider is susceptible to at least one high-severity attack in the tested configurations. The most consequential vulnerabilities are structural: attacker-controlled configuration files from an unmerged contribution are loaded as operator-level instructions, allowing the agent--infrastructure interaction to expose credentials or corrupt review judgments. Two configuration-file attacks replicate on GitLab and Hugging Face as well as GitHub. We evaluate workflow-level countermeasures and show their coverage and utility tradeoffs. We release GitInject and all attack scenarios.

We present GenZ, a hybrid model that turns a foundational model (FM) into a {\bf knowledge-discovery engine} explaining variation in real-valued multidimensional targets. The FM is treated as a noisy oracle that can answer yes/no questions about a semantic item $s$ (text, image, or both) and GenZ learns {\bf which questions to ask} so that the answers $\bz$ explain the statistical link to a possibly high-dimensional target $\by$. Discovery is driven by {\bf group reasoning}: at each step, the model partitions items by the posterior of the current latent features, and asks the FM to articulate the semantic commonality that explains the divide. The resulting feature descriptors $\theta_f$ are the primary product---human-readable hypotheses about why $s$ predicts $\by$---while predictive accuracy is a secondary, but consistently strong, by-product (e.g.~beating both the 0-shot FM baseline and TabPFN on LLM embeddings of the same items in hedonic price regression). Across four domains---hedonic house pricing, Netflix cold-start recommendations, Arizona species ecology, and human visual-cortex fMRI---GenZ recovers dataset-specific structure that the FM does not surface from priors alone. Holding the items $s$ fixed and varying only the target $\by$ (Arizona species under spatial/taxonomic/functional targets; the same natural images under FFA/EBA/PPA brain responses) yields {\bf qualitatively different} discovered feature sets, demonstrating that GenZ characterizes the $s\!\to\!\by$ link rather than the marginal distribution of $s$.

Learning neural stochastic differential equations (SDEs) from trajectory data is a central task in scientific machine learning, but standard neural SDEs trade flexibility for coefficient fidelity: flexible parameterizations recover coefficients poorly, while structured architectures impose strong coefficient priors. We introduce *Gaeta-Lie Neural SDEs*, a three-stage pipeline that improves coefficient recovery through discovered symmetries without priors on the drift or diffusion. Building on the Itô SDE symmetry framework of Gaeta and Quintero (1999), we first train a flexible neural SDE surrogate, then discover approximate projectable Lie symmetries of the learned surrogate in a finite basis of canonical symmetry generators, and finally regularize the surrogate by penalizing the residual of the Itô symmetry determining equations. The discovery stage is *lightweight*, scalable, and theory-guided: the SDE symmetry Lie algebra has known dimensional bounds that constrain the symmetry search space. The resulting regularization is *architecture-agnostic* and improves existing neural SDE methods when combined with them. Across non-trivial SDEs spanning low and high dimensions and a real-data setting, Gaeta-Lie regularization consistently improves fidelity over multiple baselines, with gains that persist in the data-scarce regime as guaranteed by the symmetry residual's freedom from data sparsity. To our knowledge, this is the first method to use SDE Lie symmetry to improve a learned stochastic surrogate.

Diffusion and flow matching have emerged as expressive generative planners for autonomous driving planning, owing to their ability to model high-fidelity and multi-modal trajectory distributions. Nevertheless, existing generative planners are predominantly optimized through imitation learning, which induces a fundamental mismatch between supervised trajectory fitting and closed-loop planning metrics, while their iterative sampling procedures often impose substantial computational overhead. In this paper, we propose FlashPlanner, a goal-conditioned flow-matching planner with online RL finetuning for closed-loop AD planning. FlashPlanner introduces a continuous future goal point as a compact navigation interface for the generative planning policy. This goal is produced by a continuous goal predictor, which is first pretrained and subsequently optimized with RL using closed-loop feedback from multiple candidate goals at each decision step. To support efficient online reinforcement fine-tuning and real-time deployment, FlashPlanner adopts a data-prediction flow-matching objective and removes redundant architectural components in existing diffusion-based planners. Experiments on the closed-loop nuPlan and interPlan benchmarks demonstrate that \textit{FlashPlanner} achieves state-of-the-art planning performance while delivering 6× faster inference (166 FPS) than the previous SOTA baseline (28 FPS). We will open-source our project.

Human-centric video customization, particularly at the garment level, has shown significant commercial value. However, existing approaches cannot support low-latency and interactive garment control, which is crucial for applications such as e-commerce and content creation. This paper studies how to achieve interactive multi-garment video customization while preserving motion coherence using only single-garment video data. We present FashionChameleon, a real-time and interactive framework for human-garment customization in autoregressive video generation, where users can interactively switch garment during generation. FashionChameleon consists of three key techniques: (i) Instead of training on multi-garment video data, we train a Teacher Model with In-Context Learning on a single reference–garment pair. By retaining the image-to-video training paradigm while enforcing a mismatch between the reference and garment image, the model is encouraged to implicitly preserve coherence during single-garment switching. (ii) To achieve consistency and efficiency during generation, we introduce Streaming Distillation with In-Context Learning, which fine-tunes the model with in-context teacher forcing and improves extrapolation consistency via gradient-reweighted distribution matching distillation. (iii) To extend the model for interactive multi-garment video customization, we propose Training-Free KV Cache Rescheduling, which includes garment KV refresh, historical KV withdraw, and reference KV disentangle to achieve garment switching while preserving motion coherence. Our FashionChameleon uniquely supports interactive customization and long-video extrapolation, while achieving real-time generation at 23.8 FPS on a single GPU, 30-180$\times$ faster than existing baselines.

Real-time execution is crucial for deploying Vision-Language-Action (VLA) models in the physical world. Existing asynchronous inference methods primarily optimize trajectory smoothness, but neglect the critical latency in reacting to environmental changes. By rethinking the notion of reaction in action chunking policies, this paper presents a systematic analysis of the factors governing reaction time. We show that reaction time follows a uniform distribution determined jointly by the Time to First Action (TTFA) and the execution horizon. Moreover, we reveal that the standard practice of applying a constant schedule in flow-based VLAs can be inefficient and forces the system to complete all sampling steps before any movement can start, forming the bottleneck in reaction latency. To overcome this issue, we propose Fast Action Sampling for ImmediaTE Reaction (FASTER). By introducing a Horizon-Aware Schedule, FASTER adaptively prioritizes near-term actions during flow sampling, compressing the denoising of the immediate reaction by tenfold (e.g., in $\pi_{0.5}$ and X-VLA) into a single step, while preserving the quality of long-horizon trajectory. Coupled with a streaming client-server pipeline, FASTER substantially reduces the effective reaction latency on real robots, especially when deployed on consumer-grade GPUs. Real-world experiments, including a highly dynamic table tennis task, prove that FASTER unlocks substantially improved real-time responsiveness for generalist policies, enabling rapid generation of accurate and smooth trajectories.

Air quality prediction at unmonitored locations is challenging because historical AQI observations are unavailable, while conventional spatiotemporal models largely rely on target histories to learn spatial dependencies. Meanwhile, widely available weather covariates provide useful station-specific evidence for target-absent inference. In this paper, we propose \textbf{ExtrapAir}, a lightweight weather-bridged framework for air quality inference at unmonitored locations. ExtrapAir preserves variable-specific weather patterns through per-variable weather encoding and learns adaptive weather and AQI correlations for spatial transfer. To support robust inference, we introduce \textbf{Activation Attention with Prior Inductive Biases}, which enables non-competitive spatial aggregation, incorporates geographic and semantic priors for station-pair guidance, and avoids full station-to-station attention computation for scalability. Extensive experiments on five real-world air-quality datasets against \textbf{32} baselines show that ExtrapAir reduces MAE by up to \textbf{15.24\%} overall and \textbf{16.01\%} on unmonitored stations, while cutting training time by \textbf{84.9\%} and memory usage by \textbf{76.23\%}, achieving a strong accuracy--efficiency trade-off.

AI agents are rapidly gaining capabilities that could significantly reshape cybersecurity, making rigorous evaluation urgent. A critical capability is exploitation: turning a vulnerability, which is not yet an attack, into a concrete security impact, such as unauthorized file access or code execution. Exploitation is a particularly challenging task because it requires low-level program reasoning (e.g., about memory layout), runtime adaptation, and sustained progress over long horizons. Meanwhile, it is inherently dual-use, supporting defensive workflows while lowering the barrier for offense. Despite its importance and diagnostic value, exploitation remains under-evaluated. To address this gap, we introduce ExploitGym, a large-scale, diverse, realistic benchmark on the exploitation capabilities of AI agents. Given a program input that triggers a vulnerability, ExploitGym tasks agents with progressively extending it into a working exploit. The benchmark comprises 898 instances sourced from real-world vulnerabilities across three domains, including userspace programs, Google's V8 JavaScript engine, and the Linux kernel. We vary the security protections applied to each instance, isolating their impact on agent performance. All configurations are packaged in reproducible containerized environments. Our evaluation shows that while exploitation remains challenging, frontier models can successfully exploit a non-trivial fraction of vulnerabilities. For example, Claude Mythos Preview, Anthropic's latest model, produces working exploits for 208 instances. Notably, even with widely used defenses enabled, models retain non-trivial success rates. These results establish ExploitGym as an effective testbed for exploitation and highlight the growing cybersecurity risks posed by increasingly capable AI agents.

ECG, with mature physiological simulators and public benchmarks, is a useful testbed for evaluating what synthetic pretraining supports. We introduce a reusable framework for ECG representation learning that compares patient-free physiological simulators, patient-derived real ECGs, and learned synthetic ECGs from real-ECG-trained generators. Holding the encoder and MAE objective fixed, we study three matched settings. Transfer-protocol analysis compares abnormal-inclusive real ECGs, normal-only real ECGs, and simulator pretraining under frozen probing and full fine-tuning on 26 abnormal-ECG tasks from PTB-XL, G12EC, and CPSC2018 using a single-lead-II pipeline. Compute-normalized PTB-XL scaling tests whether simulator pretraining matches real-data pretraining under equal processed-sample budgets. A fixed 100k-sample generator-class comparison evaluates VAE, DCGAN, SSSD-ECG diffusion variants with and without labels, and two simulators, SimECG-M and SimECG-N. The transfer analysis shows that protocol determines the supported claim: abnormal-inclusive real ECG pretraining yields more linearly separable pathology features under frozen probing, whereas full fine-tuning narrows the gap and can reverse it when the simulator corpus is sufficiently scaled. Under the fixed-100k protocol, task-wise F1 averaged over five runs ranks SimECG-N first on 22/26 tasks; no evaluated learned generator ranks first under this fixed-100k protocol; and SimECG-N obtains higher mean F1 than both diffusion variants on all 26 tasks. These results delineate where abnormal-inclusive real exposure remains beneficial and where patient-free physiological simulation can serve as an effective, protocol-bound substitute under the evaluated single-lead-II MAE pretraining and full-fine-tuning setting. We release pretraining corpora, splits, and code to support reproducible evaluation of synthetic ECG pretraining sources.

Fine-tuning LLMs on narrow harmful datasets can induce Emergent Misalignment (EM), where models exhibit misaligned behavior far beyond the fine-tuning distribution. We argue that emergent misalignment can be better understood as a data-mediated transfer phenomenon: harmful fine-tuning examples do not induce uniform behavioral spillover, but interact with the structural properties of the dataset and the difficulty of the tasks relative to the model. Across our experiments, we find that misalignment appears more readily when fine-tuning and evaluation prompts share similar underlying functional structure, when prompts leave more room for coherent harmful completions, and when the target behavior has been more reliably learned by the model. The training pipeline itself also matters: pretraining composition shapes later misalignment. We further study Subliminal Learning (SL), where misalignment is transmitted by fine-tuning on seemingly benign data generated by a harmful teacher. Moving beyond the standard SFT setting, we for the first time compare this transfer under off-policy and on-policy distillation as well, allowing us to separate the roles of the teacher guidance and the training data distribution in transmitting misalignment. Together, these results argue for a data-centric view: Emergent/subliminal misalignment should not be treated as a simple consequence of isolated harmful fine-tuning examples, but as the result of interactions between fine-tuning data structure, pretraining distributions, and training channels.