paperlist.ai

AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

NeurIPS 2026

When and How to Canonize: a Generalization Perspective

Yonatan Sverdlov, Benjy Friedmann, Snir Hordan, Nadav Dym

While equivariant architectures are standard for processing symmetric data, there is growing interest in achieving equivariance by applying group averaging or canonization to non-equivariant backbones. However, the theoretical generalization properties of these alternative strategies remain poorly understood. We introduce a theoretical framework to analyze the generalization error of these methods by bounding their covering numbers. We establish a rigorous generalization hierarchy: the error bounds of canonized models are at best equal to the error bounds of structurally equivariant and group-averaged models, and at worst equal to the bounds of non-equivariant baselines. Furthermore, we show that there exist "optimal" canonizations which attain the optimal error bounds, and "poor" canonizations which attain the non-equivariant error bounds, and that this depends on the regularity of the canonization. Finally, applying this framework to permutation groups in point cloud processing, we rigorously prove that the covering number of lexicographical sorting grows exponentially with point cloud dimension, whereas Hilbert curve canonization guarantees polynomial growth. This provides the first formal theoretical justification for the empirical success of Hilbert curve serialization in state-of-the-art point cloud architectures. We conclude with experiments which support our theoretical claims.

NeurIPS 2026

When a Zero-Shooter Cheats: Improving Age Estimation via Activation Steering

Erik Imgrund, Pia Hanfeld, Klim Kireev, Konrad Rieck

Different age-related regulations have been proposed to protect minors from harmful content and interactions online. Automated age estimation is central to enforcing such regulations, and vision-language models (VLMs) achieve state-of-the-art performance on this task. However, we find that the zero-shot nature of VLM-based age estimation produces an unexpected side effect we call the identity shortcut: Instead of estimating age from visual features, VLMs tend to identify the depicted person and infer their age from memorized knowledge. This phenomenon leads to substantially incorrect predictions when non-celebrities are misidentified as celebrities. It also produces deceptively high robustness to noise and adversarial perturbations on celebrity images, which dominate popular benchmarks. To mitigate this, we propose an activation steering method that suppresses the shortcut by intervening on the hidden states of the VLM. This method improves age estimation accuracy for both memorized and unseen identities, reducing mean absolute error by up to 25\% across popular benchmarks.

NeurIPS 2026

When a Window Is Not an Action: Selective Phase-Script Deliberation for Sliding-Window Human Activity Recognition

Qi Teng, Xueer Wang

Sliding-window human activity recognition (HAR) splits continuous sensor streams into fixed-length, overlapping windows and trains a classifier to assign one activity label to each window. Window length and stride are chosen from sampling rate, latency or computation constraints, and assumptions about typical motion duration, but they need not align with motion cycles or activity changes. Some windows therefore contain only part of a repeated motion, fragments shared by related activities, or mixed evidence near a transition. Yet each window still receives a single label, creating a granularity mismatch between activity-level supervision and local motion evidence. We propose PSDNet (Phase-Script Deliberation Network), which separates local phase interpretation from final activity classification. PSDNet encodes the current window into latent phase primitives, combines them with recent history, and produces an initial classification with an uncertainty score. When uncertainty remains high, a deliberation module compares the current phase evidence with learned class-specific phase scripts, i.e., compact templates of short-term phase patterns, and updates classification scores over a small candidate set. An auxiliary boundary objective encourages sensitivity to possible activity changes without serving as a hard routing rule. This design concentrates extra computation where direct classification is least reliable while keeping easy cases efficient. Experiments on eight public HAR benchmarks show that PSDNet consistently improves accuracy and weighted F1 over strong CNN- and sequence-based baselines. Additional analyses on ambiguous windows and similar-activity confusion pairs support phase-aware selective deliberation for windows whose local evidence is insufficient for reliable classification.

NeurIPS 2026

When Uncertainty Is the Target: Adversarial Attacks on Uncertainty-Aware Predictors

A Q M Sazzad Sayyed, Michele Caprio, Nathaniel D. Bastian, Francesco Restuccia

As machine learning becomes increasingly deployed in high-stakes scenarios, studying adversarial vulnerability of uncertainty-aware models has become a compelling necessity. In this paper, we focus on adversarial attacks that manipulate predictive uncertainty rather than model predictions. We focus on predictors that decompose uncertainty into aleatoric uncertainty (AU) and epistemic uncertainty (EU) and formalize uncertainty vulnerability as the maximum increase in AU achievable under a stealth constraint where the EU is kept below a threshold. This framing yields three complementary findings. First, we theoretically show that knowledge of the baseline EU can enlarge the attacker's feasible stealth region and increase the maximal achievable increase in AU. Second, a first-order analysis reveals that vulnerability is governed by the component of the AU gradient orthogonal to EU, enabling stealthy manipulation. Third, contrary to standard margin-based intuition, vulnerability peaks at moderate margins. Experiments across MNIST, CIFAR-10, and CIFAR-100 with standard architectures show that the proposed attack achieves non-trivial aleatoric damage while maintaining zero epistemic-stealth violation (e.g., mean AU increase of 0.0286, 0.0853, and 0.1568, respectively), whereas unconstrained uncertainty attacks violate the stealth constraint on over 90% of samples. Experiments indicate that the largest damage typically occurs in an intermediate uncertainty regime rather than at the extremes. Furthermore, consistent with our theoretical analysis, feasible attackability collapses under increasing epistemic uncertainty (e.g., mean attackability decreases from 0.0363 to 0). Overall, these results intimately connect uncertainty decomposition to adversarial geometry.

NeurIPS 2026

When Transcriptomic Foundation Models Scale: Domain-Focused Pretraining for Drug Development in Immunology and Inflammation

Karim El Kanbi, Yannis Cattan, Aziz Fouché, Charlotte Claye, Pierre Marschall, Julien Duquesne

Recent work has reported two failure modes of transcriptomic foundation models: validation loss plateaus beyond 100M parameters, and consistent underperformance against simple linear baselines on clinically relevant tasks. We show that both findings invert under a specific pretraining recipe. We introduce EVA-RNA, a transformer pretrained on 545k human and mouse samples spanning bulk RNA-seq, microarray, and pseudobulked single-cell data, scoped to immunology and inflammation, one of the largest therapeutic areas in clinical development. EVA-RNA exhibits clean power-law scaling from 7M to 300M parameters, with no plateau emerging within our scale range. On a benchmark co-designed with immunologists and drug development experts, EVA-RNA outperforms existing foundation models on every task category, spanning drug discovery, preclinical-to-clinical translation and patient stratification. Mechanistically, EVA-RNA learns species-invariant representations in which orthologous genes progressively align across layers without supervision. We interpret these results as evidence that scope and data composition are sufficient, with conventional architecture and knowledge-informed gene embeddings, to achieve clinical utility and scaling in I&I. We also release EVA-RNA 60M model weights to support continued investigation.

NeurIPS 2026

When Think-with-Image Meets Safety: What Determines Multimodal Jailbreak Robustness?

Yuan Tian, Bing Hu, Fang Wu, Xiaomin Li, Binghang Lu, Neil Gong

Think-with-image reasoning is emerging as a new inference paradigm for large vision-language models, but its safety implications remain poorly understood. Existing systems already span multiple process designs, including direct response generation, text-only prior turn, visual-state manipulation, and explicit external image-tool invocation. In this paper, we ask which of these evaluated paradigms improves multimodal jailbreak robustness, and why. Across multiple vision-language models, explicit image-tool interaction yields the lowest attack success rates in our experiments, reducing jailbreak success by around 30\% relative on average across the evaluated models. This finding is initially surprising: ASR remains low even when the returned image-tool output is manually overridden or itself unsafe-looking, but returns near direct-answering levels under text-only prior turn controls. These results indicate that the lower ASR is not explained by benign returned-image semantics or by the textual image-tool trace alone. To explain the pattern, we introduce an image-tool safety vector framework that models image-tool invocation as a residual shift in hidden representations toward a safety-relevant direction. Representation-level analyses and activation interventions support this account. Overall, our results suggest that explicit image-tool interaction is a promising design pattern for improving jailbreak robustness, while also motivating pipeline-specific safety evaluation.

NeurIPS 2026

When Symbol Names Should Not Matter: A Logistic Theory of Fresh-Symbol Classification

Wenjie Guan, Jelena Bradic

Template tasks have emerged as a clean testbed for asking whether transformers reason with abstract symbols rather than concrete token names. We study the fixed-label classification version of this problem, where train and test examples share latent templates but may use disjoint vocabularies. Unlike next-token prediction, the model need not emit unseen symbols; it must learn a decision rule invariant to symbol renaming. We analyze regularized kernel logistic classification in the transformer-kernel regime. Our main result decomposes the learned predictor into an ideal template-level classifier and a finite-sample perturbation caused by accidental token overlaps in the training data. We encode these overlaps by a colored collision graph and prove high-probability margin-transfer guarantees for fresh-symbol classification. This perspective extends template-based analyses to logistic classification and refines scalar diversity conditions: vocabulary size controls the average rate of collisions, but collision geometry controls whether the ideal classification margin is preserved. More broadly, the same perturbation framework applies to abstraction-augmented inputs, yielding a general margin-versus-collision criterion for identifying when prompting strategies improve fresh-symbol generalization. Synthetic template experiments illustrate the predicted roles of regularization, sample size, and transformer-kernel structure.

NeurIPS 2026

When Stored Evidence Stops Being Usable: Scale-Conditioned Evaluation of Agent Memory

Jiaqi Shao, Yiyi Lu, Yunzhen Zhang, Bing Luo

Memory-agent evaluations report fixed-snapshot accuracy or retrieval quality, but these scores do not show whether evidence remains usable as irrelevant sessions (sessions not annotated as task-relevant evidence for the query) accumulate. We present a scale-conditioned evaluation protocol for agent memory under evidence-preserving growth: for each query, task evidence is held fixed while irrelevant sessions are added. The protocol logs agent--memory trajectories and reports four diagnostics: budget-compliant reliability, tail memory-call burden, failure-regime decomposition, and the usable-scale boundary where reliability falls below the target. Applied to LongMemEval and LoCoMo across flat, planar, and hierarchical memory interfaces, the protocol shows reliability loss is not a single phenomenon. On LongMemEval, HippoRAG stays within the two-call budget but loses 16--20 percentage points in budget-compliant reliability as irrelevant sessions are added; LiCoMemory's observed failures depend strongly on the agent, with Qwen3-8B exceeding the budget while Qwen3-32B and Qwen3-235B remain reliable in the tested range. The result supports a framework for making scalable-memory claims conditional on agent, interface, scale range, and interaction budget. Code and evaluation artifacts: https://github.com/AndyLu666/memory-at-scale.

NeurIPS 2026

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation

Shani Goren, Ido Galil, Ran El-Yaniv

LLMs are widely used, yet they remain prone to factual errors that erode trust and limit adoption in high-risk settings. One approach to mitigate this risk is to equip models with uncertainty estimation mechanisms that abstain when confidence is low. However, this binary "all-or-nothing" approach is excessively restrictive in long-form settings, often discarding valuable information. We introduce ***Selective Abstraction (SA)***, a framework that enables LLMs to trade specificity for reliability by selectively reducing the detail of uncertain content. We formalize SA through selective risk and coverage, and propose ***Atom-wise Selective Abstraction***, a claim-level instantiation that decomposes responses into atomic claims and replaces uncertain atoms with higher-confidence, less specific abstractions. We develop a novel end-to-end pipeline for evaluating long-form generation that instantiates risk as factual correctness and measures coverage as retained information. Our comprehensive empirical evaluation across five LLMs and two long-form factual benchmarks shows that atom-wise SA consistently improves the risk-coverage trade-off, outperforming seven baselines, including claim removal, self-revision, sampling-based aggregation, and chain-of-verification. It improves AURC by up to 35.61\% over claim removal, demonstrating that reducing specificity boosts reliability while preserving substantial information. We further provide a risk-guided procedure for selecting a confidence threshold that satisfies a target risk.

NeurIPS 2026

When Sanitization Becomes the Trigger: Defense-Triggered Backdoor Attacks

Zhiguo Yang, Ruotian Liu, Peipei Xu, Wenjie Ruan

Backdoor defenses are widely regarded as key to secure third-party model deployment. However, we are the *first* to show that, in standard backdoor sanitization pipelines, the defense process itself can be exploited and turned into a conditional trigger. We propose ***D**efense-**T**riggered **B**ackdoor* (DTB): an attacker implants both a normally active *decoy backdoor* and a dormant *hidden backdoor*, so that model sanitization suppresses the decoy backdoor while activating the hidden backdoor, thereby making the defense process the trigger condition for the hidden backdoor. DTB uses bi-level optimization to approximate the shared sanitization effect of mainstream backdoor defenses, while constraining the hidden backdoor to activate only after the decoy backdoor is sufficiently suppressed. Experiments on multiple datasets, different networks, and 14 representative defenses show that DTB can *stably trigger* the hidden backdoor, and this phenomenon remains significant after multi-round compositional sanitization. Our findings reveal a potential threat in existing backdoor defense pipelines and suggest that post-sanitization safety cannot be judged solely by whether the original backdoor has been eliminated.

NeurIPS 2026

When Safety Becomes An Outlier: Understanding the Retention of LLM Safety Behaviors

Binchi Zhang, Hadi Abdullah, Yiwei Cai, Jundong Li

Safety-aligned large language models often lose their safety behaviors after fine-tuning, even when safety data are included. While this fragility is well documented, its underlying cause remains unclear. We propose that formulaic refusal strings function as *outlier modes* in the model's output distribution, i.e., low-support behaviors that are easy to fit but structurally unstable under subsequent fine-tuning, and that this is an important source of safety fragility. Controlled experiments verify this: fixed refusals are acquired and forgotten much like arbitrary constant strings, in contrast to prompt-grounded natural responses. Motivated by this insight, we improve safety retention by constructing natural, context-aware safety supervision that keeps safety responses within the model's existing output distribution and grounded in semantics. We instantiate this principle in both supervised and preference-based alignment settings, using perplexity under the original model as a practical proxy for distributional naturalness. Across multiple models and fine-tuning regimes, our approach improves both immediate safety and its retention under continued fine-tuning without sacrificing helpfulness, suggesting that naturalness is a useful principle for durable safety alignment.

NeurIPS 2026

When Riemann flows with Wasserstein: Generative Modeling of Probability Distributions on Manifolds

Doron Haviv, Edward De Brouwer, Rishabh Anand, Rex Ying, Gabriele Scalia, Hector Corrada Bravo

Many scientific datasets, such as molecular conformational ensembles or single-cell tissue measurements, are naturally modeled as meta-distributions: distributions over probability measures on non-Euclidean domains. Existing generative methods largely assume Euclidean geometry and fail to capture this structure. We introduce Riemannian Wasserstein Entropic Flow Matching (RWEFM), a generative framework on the Wasserstein space $\mathcal{P}_2(\mathcal{M})$ of a Riemannian manifold $(\mathcal{M},g)$. RWEFM is trained by regressing a neural vector field onto Riemannian optimal transport velocities, using McCann displacement interpolations as conditional paths. We confirm theoretically that this construction leads to a valid flow matching approach on $\mathcal{P}_2(\mathcal{M})$ and introduce the Riemannian Entropic Map, a GPU-efficient approximation of the optimal transport map on manifolds. Our experiments show that by respecting the intrinsic geometry of the data, RWEFM can generate whole single-cell samples in hyperspherical latent spaces and protein conformational ensembles on the torus. Code and tutorials are available at \href{https://github.com/AnonRWEFM/RWEFM}{RWEFM}.

NeurIPS 2026

When Reasoning Meets Its Laws

Junyu Zhang, Yifan Sun, Tianang Leng, Jingyan Shen, Liu Ziyin, Paul Liang, Huan Zhang

Despite the superior performance of Large Reasoning Models (LRMs), their reasoning behaviors are often counterintuitive, *e.g.*, excessive reasoning on simple questions or insufficient reasoning on complex ones, leading to suboptimal reasoning capabilities. This paper presents the Laws of Reasoning (LoRe), a unified framework that formalizes intrinsic reasoning patterns in ideal LRMs. We first propose *compute law* with the hypothesis that the reasoning compute should scale linearly with question complexity. Beyond compute, we extend LoRe with a supplementary *accuracy law*, positing exponential decay of accuracy with increasing complexity. Since the complexity is difficult to quantify in practice, we approximate these hypotheses via two tractable properties, *monotonicity* and *compositionality*. We therefore introduce LoRe-Bench, a benchmark that systematically measures these properties for large reasoning models. Evaluation shows that most reasoning models exhibit reasonable monotonicity but lack compositionality. In response, we develop an effective finetuning approach that enforces compute-law compositionality. Extensive empirical studies demonstrate that better compliance with compute laws yields consistently improved reasoning performance on multiple benchmarks, and uncovers synergistic gains across properties and laws.

NeurIPS 2026

When Policy Entropy Constraint Fails: Preserving Diversity in Flow-based RLHF via Perceptual Entropy

Xiaofeng Tan, Jun Liu, Bin-Bin Gao, Yuanting Fan, Xi Jiang, Chengjie Wang, Hongsong Wang, Feng Zheng

RLHF is widely used to align flow-matching text-to-image models with human preferences, but often leads to severe diversity collapse after fine-tuning. In RL, diversity is often assumed to correlate with policy entropy, motivating entropy regularization. However, we show this intuition breaks in flow models: policy entropy remains constant, even while perceptual diversity collapses. We explain this mismatch both theoretically and empirically: the constant entropy arises from the fixed, pre-defined noise schedule, while the diversity collapse is driven by the mode-seeking nature of policy gradients. As a result, policy entropy fails to prevent the model from converging to a narrow high-reward region in the perceptual space. To this end, we introduce perceptual entropy that captures diversity in a perceptual space and maintains the property of standard entropy. Building upon this insight, we propose two entropy-regularized strategies, Perceptual Entropy Constraint and Perceptual Constraints on Generation Space, to preserve perceptual diversity and improve the quality. Experiments across two base models, neural and rule-based rewards, and three perceptual spaces demonstrate consistent gains in the quality-diversity trade-off; PEC achieves the best overall score of 0.734 (vs.\ baseline's 0.366); a complementary setting of PEC further reaches a diversity average of 0.989 (vs.\ baseline's 0.047). Code will be released.

NeurIPS 2026

When Policies Cannot Be Retrained: A Unified Closed-Form View of Post-Training Steering in Offline Reinforcement Learning

Elias Hossain, Mohammad J Basher, Ivan Garibay, Ozlem Garibay, Niloofar Yousefi

Offline RL can learn effective policies from fixed datasets, but deployment objectives often shift after training, while the trained actor may be frozen due to data, cost, or governance constraints. We study deployment-time adaptation of frozen offline actors using Product-of-Experts (PoE) composition with a goal-conditioned prior. Our main practical finding is graceful degradation rather than universal improvement: with degraded or random priors, precision-weighted PoE remains anchored to the frozen actor, whereas additive and prior-only adaptation often collapse, and a KL-budget selector typically reaches a near-oracle operating point. We also clarify that, for diagonal-Gaussian actors and priors, PoE with coefficient $\alpha$ induces the same deterministic policy as KL-regularized adaptation with $\beta=\alpha/(1-\alpha)$, with posterior covariance differences cancelling under deterministic action selection. Across D4RL MuJoCo and AntMaze diagnostics, results reveal an actor-competence ceiling: composition helps or preserves performance when the frozen actor is sufficiently competent, but cannot recover when the actor itself fails. Swept CQL/IQL-guided and SF/GPI baselines are competitive in some settings, but do not eliminate this regime boundary. Thus, PoE/KL-Reg is best viewed as an actor-anchored safety layer for deployment-time objective shift, not as a general return-maximization method, with effectiveness governed by actor competence rather than knob choice.

NeurIPS 2026

When Poison Meets Structure: Topology-based Defense against Poisoning Attack on Graph-based Retrieval-Augmented Generation

Qizhi Chen, Junhao Wen, Shuang Liang, Jiakai Li, Yizhuo Ma, Rongzheng Wang, Ke Qin

Poisoning attacks against GraphRAG focus on knowledge pollution at the node and community levels, but conventional poisoning defenses mainly rely on sentence-level semantic features, which makes them less effective against such attacks. To address this issue, we analyze the poisoning strategy from a game-theoretic perspective and find that attackers prioritize fabricating query-related facts while ignoring supporting background knowledge, which in turn induces a systematic topological discrepancy between poisoned and clean subgraphs. Based on this insight, we propose the lightweight **T**opology-based **D**efense against **P**oisoning Attack on GraphRAG (TDP). TDP constructs a pair of conflicting candidate subgraphs from the retrieved evidence and trains a pairwise topology-ranking discriminator to distinguish clean evidence with dense cross-validation from poisoned evidence with sparse structural support, thereby removing poisoned subgraphs. Notably, the topological patterns captured by TDP reflect structural preferences induced by the poisoning game rather than dataset-specific distributional biases, allowing it to be transferred as a plug-and-play module after pretraining without end-to-end retraining. To the best of our knowledge, this is the first systematic work on poisoning defense for GraphRAG, and experiments show that TDP achieves state-of-the-art defense performance across multiple benchmarks and poisoning attacks, demonstrating strong generalization.

NeurIPS 2026

When Parallelism Pays Off: Cohesion-Aware Task Partitioning for Multi-Agent Coding

Xu Yang, Lunyiu Nie, Ethan Chandra, Stanislav Gannutin, Fangru Lin, Swarat Chaudhuri

Multi-agent Large Language Model (LLM) systems offer a way to decompose complex tasks such as coding through parallelization and context isolation, but adding agents in practice introduces inter-agent communication overhead that can offset efficiency gains. We formalize multi-agent orchestration as a graph partitioning problem that captures the *communication-to-computation trade-off*: task decomposition can shorten critical-path computation, while cross-agent dependencies require costly context transfer. We instantiate this view in repository-level software engineering through **Co**hesion-aware **Coder** (CoCoder), which builds dependency graphs from static analysis, isolates structural hub files, partitions the graph via community detection, and executes the partition with a dependency-aware scheduler. Across \(28\) real-world tasks on DevEval and CodeProjectEval, CoCoder Pareto-dominates sequential and file-based parallel baselines as well as Claude Code with Agent Teams, improving pass rate by up to \(14.0\%\) on CodeProjectEval, achieving up to a \($2.10\times$\) wall-clock speedup, and reducing API cost by up to \(35\%\), with the largest gains on the most dependency-dense projects. CoCoder demonstrates how dependency-aware orchestration can make parallel coding agents both theoretically grounded and practically efficient, suggesting a broader design principle for multi-agent LLM systems.

NeurIPS 2026

When Noise Meets Long-Tail: Feature-Threshold Dual Calibration for Robust Pseudo-Labeling

Ping Guo, Zhiqi Huang, Xinran Li

Pseudo-labeling has become a cornerstone of learning from unlabeled data in semantic segmentation. Yet its effectiveness drops sharply in real-world scenarios where strong imaging noise and long-tailed class distributions occur together. We trace this failure to a vicious cycle of pseudo-label degradation. Imaging noise entangles foreground and background features, lowering prediction confidence across all classes, while long-tailed distributions leave tail classes with far fewer training samples and inherently lower confidence. Under fixed high-threshold filtering, these tail-class predictions are systematically filtered out, so they receive no supervision from unlabeled data and thus features keep degrading in subsequent iterations. Critically, noise and long-tail are not independent obstacles but mutually amplifying ones, and addressing either alone is insufficient. To break this cycle, we propose FTC-Seg, a Feature-Threshold dual-Calibration framework built on a standard teacher-student framework. At the feature level, Orthogonal Prototype Reconstruction (OPR) uses a set of learnable orthogonal prototypes to residually purify pixel-wise features, widening the margin between weak foreground targets and noisy backgrounds. At the threshold level, Adaptive Threshold Calibration (ATC) dynamically adjusts class-specific thresholds based on learning difficulty and prediction-distribution bias, rescuing low-confidence pseudo-labels of tail classes from systematic exclusion. Extensive experiments on four public benchmarks spanning three distinct noise modalities show that FTC-Seg achieves strong performance against state-of-the-art methods, with particularly substantial gains on tail classes. Our results establish that jointly calibrating features and thresholds is essential for robust pseudo-labeling under compounded noise and class imbalance.

NeurIPS 2026

When Must AI Training Stage Checkpoints? A Distributional Model of Durability Boundaries at Scale

Farid Talibli, Awais Khan, Christopher Zimmer, Sungyong Park, Jihoon Yang, Youngjae Kim

Large-scale AI training runs span days within fixed HPC allocations, making checkpointing essential for bounded recovery after failure. Asynchronous checkpointing hides checkpoint latency from the training loop, but does not guarantee that the most recent state has reached a durable target: data may still be in flight to the shared parallel filesystem (PFS) when a failure occurs, forcing rollback to an older checkpoint. We formalize this durability gap through a distributional model that combines hardware crossover analysis with statistical models of PFS completion time under scale and contention. Rank-local completion times follow a lognormal body distribution, while wall-clock completion is governed by an extreme-value process determined by the slowest writer. The resulting analysis yields a contention-dependent threshold,~$C^\star_p(n)$, beyond which the PFS is no longer the fastest path to durable persistence. Guided by this analysis, we design CacheX, a transparent staging layer that composes with PyTorch Distributed Checkpoint~(DCP). CacheX stages bulk data to local DRAM and replicates it to a neighboring node's NVMe, providing allocation-local durability while preserving eventual persistence to the PFS. On Frontier, across IOR runs up to 256~nodes and end-to-end FSDP+DCP training up to 64~nodes, CacheX reduces write-time variability by up to~$43\times$, achieves a replica-durable effective throughput of~${\sim}\,2.5$ to $2.8$\,GiB/s per node decoupled from PFS contention, and reduces worst-case rollback exposure. Our results show that staging is not a universal accelerator; rather, it is a conditional policy for selecting the first durable checkpoint boundary under measured scale, load, and tail behavior.

NeurIPS 2026

When Metropolis and Hastings Meet Bradley and Terry: Exact MCMC From Preference Voting

Ariel Smogorghevski, Nir Rosenfeld, Yaniv Romano

conditioned on desired semantic properties is an emerging challenge in modern generative modeling. Metropolis-Hastings (MH) provides a principled route to conditional sampling, but requires access to exact pointwise target-density evaluations, which are not available in generative settings. Meanwhile, pairwise comparisons by humans or model ``judges'' are highly accessible and have proved valuable across diverse applications. We introduce Pref-MH, a general exact MH sampler for judge-induced conditional distributions using only stochastic binary pairwise comparisons. Our key observation is that the MH unnormalized density ratio matches the preference odds of BT choice models. The central challenge is that while MH requires precise ratio computation, BT judges provide only sampled binary feedback. To this end, we develop a valid accept/reject rule whose resulting Markov chain provably converges to the target distribution. We further show that, for a fixed proposal kernel and budget, Pref-MH is optimal in the Peskun-Tierney sense among this class of exact reversible acceptance rules. Experiments on text generation with LLM judges and image generation with VLM judges demonstrate that Pref-MH provides a practical and flexible approach to conditional sampling from comparative feedback.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.