NeurIPS 2026 Papers

Out-of-Distribution (OOD) detection requires sensitivity to subtle shifts without overreacting to natural In-Distribution (ID) diversity. However, from the viewpoint of detection granularity, global representation inevitably suppresses local OOD cues, while patch-based methods are unstable due to entangled spurious-correlation and noise. And neither of them is effective in detecting compositional OODs composed of valid ID components. Inspired by recognition-by-components theory, we present a post-hoc Component-Based OOD Detection (CoOD) framework that addresses the existing limitations by decomposing inputs into functional components. To instantiate CoOD, we derive Component Shift Score (CSS) to detect local appearance shifts, and Compositional Consistency Score (CCS) to identify cross-component compositional inconsistencies. Empirically, CoOD achieves consistent improvements on both coarse- and fine-grained OOD detection.

Recent studies on generalizable human Gaussian splatting have achieved the notable progress in synthesizing novel views of unseen human subjects from multi-view images. Despite this progress, existing methods still struggle to represent fine-grained details of human subjects, which inherently involve high geometric and textural complexity. This is because previous methods do not impose a constraint on how densely Gaussians are placed, which often leads to blurry rendering results in complex regions. To address this problem, we propose a complexity-guided regularization scheme. The key idea is to leverage a complexity prior computed via the local entropy in geometric and textural characteristics of a clothed human. This effectively prevents Gaussians from being coarsely placed in complex regions, which facilitates the faithful reconstruction of intricate structures. Furthermore, we sample local patches predominantly from complex regions according to this complexity prior, which allows the model to be sufficiently supervised by local details. Experimental results on benchmark datasets demonstrate that our method delivers state-of-the-art performance while maintaining the real-time inference speed in generalizable human Gaussian splatting.

We study the degree-weighted work required to compute $\ell_1$-regularized PageRank using the standard one-gradient-per-iteration accelerated proximal-gradient method (FISTA). For non-accelerated local methods (ISTA), the best known worst-case work scales as $\widetilde{O} ((\alpha\rho)^{-1})$, where $\alpha$ is the teleportation parameter and $\rho$ is the $\ell_1$-regularization parameter. A natural question is whether FISTA can improve the dependence on $\alpha$ from $1/\alpha$ to $1/\sqrt{\alpha}$ while preserving the $1/\rho$ locality scaling. The challenge is that acceleration can break locality by transiently activating nodes that are zero at optimality, thereby increasing the cost of gradient evaluations. We analyze FISTA with respect to a less regularized objective and show that, under a checkable confinement condition, all spurious activations remain inside a boundary set $\mathcal{B}$. This yields a bound consisting of an accelerated $(\rho\sqrt{\alpha})^{-1}\log(\alpha/\varepsilon)$ term plus a boundary overhead $\sqrt{vol(\mathcal{B})}/(\rho\alpha^{3/2})$. We provide graph-structural conditions that imply such confinement. Experiments on synthetic and real graphs show the resulting speedup and slowdown regimes under the degree-weighted work model.

Diffusion bridges have emerged as versatile diffusion-based frameworks for facilitating transformations between arbitrary data distributions. However, these approaches are hindered by the immensity of the optimization space without consideration of underlying high-order structures. This paper explores a complex-valued variant of diffusion bridges for solving physical problems using conformal field theory and mean field games. To this end, we propose a new class of dynamical diffusion bridges, called complex Schr\"odinger Bridges (CSB), whose derived algorithms are able to handle diffusion-based tasks using Hamiltonian-based geometric prior. Additionally, we propose image-to-image CSB (I$^2$CSB), tractable diffusion bridge techniques with a spiral analytic posterior. We verify our theoretical claims and practicality of our Hamiltonian based approach with a wide range of experiments.

Chemical reaction datasets such as USPTO suffer from substantial incompleteness, frequently missing byproducts, co-reactants, and stoichiometric coefficients. This limits their applicability and reliability in downstream applications. Here, we introduce CompleteRXN, a large-scale supervised benchmark for reaction completion under realistic missing-data conditions. We construct a dataset of aligned incomplete and atom-balanced reactions by mapping USPTO records to curated mechanistic reactions. We evaluate representative baselines, including a novel encoder-decoder reaction completion model with constrained decoding, the Constrained Reaction Balancer (CRB), and a recent algorithmic method, SynRBL. On our CompleteRXN benchmark, the CRB achieves high performance across splits of increasing difficulty, reaching 99.20% equivalence accuracy on the random split and 91.12% on the extreme out-of-distribution split. SynRBL produces many balanced and chemically plausible completions, but with lower accuracy on the benchmark test splits. Across all methods, performance degrades with increasing incompleteness. We observe a substantial drop when evaluating on reactions outside the benchmark (full uncurated USPTO), highlighting the gap between benchmark performance and practical robustness and motivating future work.

Self-supervised Vision Transformers (ViTs) like DINO encode rich semantics, enabling training-free segmentation of objects from the background and discovery of their parts via feature clustering. This paper focuses on part discovery: partitioning a foreground object into semantic parts. Existing approaches produce imprecise part boundaries. We trace this to the rigid ViT patch grid used in training DINO, where patches straddling boundaries contain pixels from multiple parts. While DINO's invariance-based training could absorb this pixel-level mixing into clean features, experiments with over 26K foreground patches show it does not: boundary-overlapping patches produce features with higher entropy and lower assignment confidence, blurring predicted part boundaries. Rather than make the massive effort of retraining DINO over geometrically coherent regions, an easier approach is to take boundaries directly from a boundary detector, which supplies the geometric information DINO's features lack. Motivated by this, we introduce Part-DINO, a training-free framework that combines boundaries from low-level image segmentation with DINO's semantic features. We use the boundaries to partition the image into regions, pool DINO features within each region, and group them to discover parts. Without any training, Part-DINO produces structurally coherent part assignments, outperforming training-free baselines across four standard benchmarks (CUB, CelebA, PartImageNet-OOD, PartImageNet-Seg) and remaining competitive with weakly-supervised and unsupervised methods.

Continuous test-time adaptation (CTTA) is crucial for deploying vision-language models (VLMs) in real-world environments where data distributions shift over time. Existing approaches typically utilize confidence-driven pseudo-labeling to enhance the performance on the target domain while retraining VLMs using historical information. Despite the progress, their performance is far from satisfactory due to error accumulation from noisy pseudo-labels and optimization interference between newly acquired and historical knowledge. Towards this end, we propose a novel approach named Complementary Cache Guidance with Gradient Disentanglement (CURE) for CTTA of VLMs. The core of our CURE is to balance instant knowledge acquisition and historical knowledge consolidation using both complementary cache systems and parameter space disentanglement. In particular, our CURE first constructs affinity structures among diverse text prompts, which guide majority voting to improve the quality of pseudo-labeling. More importantly, our CURE introduces a complementary cache system consisting of a short-term cache and a long-term cache with sample quality monitoring. The short-term cache stores recent reliable samples with high entropy, while the long-term cache preserves representative samples with high gradient consistency across iterations. Then, we extract prototypes from both caches for cross-modal alignment, enabling the model to acquire new knowledge while mitigating old knowledge forgetting. To further reduce the interference when learning from two caches, we perform low-rank decomposition of the gradient space, which facilitates historical knowledge consolidation in the null space of short-term signals. Extensive experiments on several benchmarks demonstrate the superiority of CURE over state-of-the-art baselines. Our source codes are available at https://anonymous.4open.science/r/CURE-B486.

Prefill-only KV compression freezes a token subset at the end of prefill and decodes from it without further eviction. The retention decision is therefore irreversible, yet existing methods estimate the corrective signals it relies on, per-head reliability and prompt-level compression sensitivity, online from a single noisy prompt. We argue this is the wrong statistical unit: these signals exhibit far higher cross-prompt regularity than within-prompt signal-to-noise. We introduce CompilerKV, a KV-retention policy whose corrective tables are compiled offline from a calibration corpus, reducing online correction after the standard observation-window scan to $O(1)$ lookups plus a budget clamp. We find that compiled retention tables behave as portable architectural priors: rankings transfer across disjoint corpora on four backbones, with mean Spearman $\bar{\rho}=0.90$, and direct model-to-model table transfer costs only $0.4$-$0.8$ LongBench points on average. At a 512-token budget, CompilerKV attains compressed-SOTA on all four backbones, improving over the strongest prefill-only baseline by $+1.67$ points on average, with task-bootstrap 95% CI $[+1.08,+2.37]$. Pressure regimes amplify the gap: under a fixed $512/32\mathrm{k}$ cache ratio, CompilerKV remains the strongest compressed method through 128k RULER, with approximately 73 versus FullKV 79 and SnapKV 38; on 32k NIAH it reaches $0.89$ versus SnapKV $0.42$; and at 32k input, retaining only $1.56\%$ of the prefill KV, batch-16 serving remains feasible where FullKV is OOM.

Modeling interventions that include timing is an important task in many domains, such as treatments in healthcare, transactions in finance, and others. However, estimating these interventional distributions is challenging because standard next-token predictors, typically implemented using transformers, do not naturally support altering the timing of specific future events. We develop \emph{Competing Event Models} (CEMs), an autoregressive generative approach that simplifies the estimation of interventions on both what interventions are applied and \emph{when}. Drawing from the competing risks literature, CEMs model independent probability distributions for latent times of each event type, where the earliest realized time determines the next event. We show that this framework enables straightforward interventions on event timing and efficient sampling, and, through careful design choices, can also model concurrent events. We evaluate CEMs on a cancer tumor volume simulator and on prediction tasks using the MIMIC-IV dataset. Our results show that CEMs accurately recover causal effects of sequential treatments in simulations while surpassing standard transformer baselines in predictive performance on 3 out of 4 real-world medical data tasks.

Hybrid language models that mix attention and recurrent layers have shown promise: theoretically, recurrent layers ameliorate the limitations of pure transformers on state tracking, and empirically, hybrids can outperform pure transformers in loss and downstream evaluations \citep{waleffe2024empirical,merrill2026olmohybrid}. Yet it remains unclear which data or capabilities drive these gains, and to what degree they reflect the theoretical advantages motivating hybrid models. We address this by analyzing the benefits of hybrid models at the token level---which kinds of tokens are better predicted by hybrids than by pure transformers---using the open weights from Olmo 3 \citep{olmo2025olmo3} and Olmo Hybrid \citep{merrill2026olmohybrid}. Hybrids predict tokens better across the board, but we show these gains localize to open-class content words rather than closed-class function words. Across natural language and code, the loss gap shrinks on closing brackets (but not opening brackets), consistent with the hypothesis that attention, not hybrid layers, is largely responsible for processing hierarchical structure. The hybrid advantage also vanishes on repeated $n$-grams. Overall, while attention suffices for tokens involving copying and purely syntactic information, hybrids show an advantage on more semantically conditioned predictions, likely because these are aided by a strong representation of the discourse state. We conclude with discussion and proof-of-concept experiments showing how these findings could refine design principles and pretraining evaluations for hybrid architectures.

On two-sided platforms such as e-commerce marketplaces, recommender systems deliver personalized item rankings to consumers and serve as a primary channel through which transactions occur between item providers and consumers. At the same time, promoting the activities of item providers requires the platform to balance consumer satisfaction with fair exposure across items. Recent work formulates this objective as impact-based fair ranking, which maximizes a Nash social welfare criterion over stochastic ranking policies. However, the resulting policies must be served as user-specific mixtures of deterministic rankings, whose support size can grow combinatorially. This imposes substantial storage and serving overhead, driving up operational cost in production deployment. Moreover, unseen users must fall back to a generic ranking rule. We therefore develop compact representations for serving impact-based fair-ranking policies. We first prove a tight bound that every optimum admits an impact-preserving mixture with support size at most the number of items. Using a dual reformulation, we then replace stored user-specific ranking mixtures with item-indexed dual vectors and compress the resulting sequence of dual vectors by weighted random subsampling. The resulting deployment representation is independent of the training-user population and can be used for unseen users. Experiments on real-world recommendation datasets show that the sampled dual mixture preserves the fair-ranking objective while reducing the storage required at deployment by up to 2,596$\times$ relative to a user-coupled mixture baseline.

Subject-driven generation (SDG) evaluation using multi-modal LLMs (MLLMs) provides better interpretability and stronger alignment with human judgment than traditional embedding-based methods. However, MLLM-as-a-Judge scores are limited in differentiating between error and error-free SDG images. In this paper, we propose CompJudge, which overcomes these limitations by introducing comparative capabilities to MLLM-as-a-Judge and recalibrating scores based on comparison results. To rigorously evaluate the correctness of SDG evaluators, we introduce CompILIAS, a diagnostic benchmark of triplets (reference, identity-preserving image, identity-degraded image) with verified binary ground-truth labels indicating whether the SDG image preserves the reference identity. We demonstrate improvements of SDG evaluation over existing approaches: 8.9pp on CompILIAS and 10.62--15.98pp on the DreamBench++ dataset. These improvements consistently generalize across diverse MLLM backbones and across subject categories.

Vision–language models (VLMs) exhibit strong multimodal reasoning, yet their growing parameter counts incur prohibitive memory footprints and inference latency, hindering real-time deployment. Post-training quantization alleviates these costs, but aggressive low-bit quantization often degrades accuracy by disrupting visual–linguistic alignment. Meanwhile, lossless compression preserves accuracy but suffers from metadata overhead and sequential decoding, limiting GPU parallelism. We propose Comp²VLM, a hybrid framework that jointly designs quantization and lossless compression for efficient VLM serving. We introduce Duplication-Enhanced Quantization (DEQ), which adaptively selects group-wise scales to reduce the entropy of quantized representations while preserving reconstruction fidelity, thereby improving compressibility. To realize runtime gains, we present Quantized Data-aware Lossless Compression (QPress), a hardware-friendly scheme based on a universal Huffman table that enables block-wise metadata sharing and GPU-parallel decoding. Across diverse VLMs and benchmarks, Comp²VLM maintains competitive accuracy while reducing the effective precision to W3.5A3.2~4.9. On LLaVA-onevision-7B, it achieves +4.7% TextVQA and +7.7% OCRBench accuracy over W4A8-based SOTA at an average bit-width of W3.5A4.6. DEQ yields up to 33% entropy reduction, and QPress improves compression efficiency by up to 13.3% with only ~4% end-to-end latency overhead. To our knowledge, Comp²VLM is the first unified framework to co-design quantization and lossless compression for VLMs, demonstrating their complementary benefits beyond standalone methods.

Swapping two LLM post-training stages can change the final model, but an aggregate loss or benchmark delta only says that something moved, not where the order-dependent residue landed. We ask whether this residue leaves a memory trace: a structured signal that is localized in output space, changes held-out order-gap NLL under targeted interventions, and is assignable from paired endpoint weights. For a specified two-stage path $(A,B)$, we define commutator memory by projecting the Lie bracket $b_{AB} := H_B g_A - H_A g_B$ at the base model through the logits into token scores $\tau_k=\mathbb{E}[e_k\,\delta z_k]$, whose sum is the leading bracket-predicted order effect. The token readout is localized: endpoint and batch-resampled checks preserve bracket top-token supports far more than norm-matched random directions (82--99% vs. 35--49% top-20 overlap), and a separate endpoint-support prediction check recovers 53--57% of Qwen top-1% active-token supports. It has intervention leverage in the tested protocols: top-positive-$\tau_k$ token interventions close 32% (median) of the held-out Qwen-3-4B SFT ordering gap with tau-neutral controls near zero, with the same bracket-vs-control separation on a pre-specified above-floor Qwen-2.5-1.5B fp32 subset. It is assignable from paired endpoints: given a base model, candidate stages, and paired alternate-order endpoints, the statistic $\langle\theta_{AB}-\theta_{BA},\,b_{AB}\rangle$ distinguishes $k=1$ SGD training order in 66/72 pair-seed units across four LLMs. Matched-batch DPO and frozen-rollout reward-surrogate experiments are matched-path stress tests; AdamW is reported as an analogous lifted-state pilot. Commutator memory turns training order from a scalar nuisance into a localized, intervention-tested, and paired-endpoint-readable residue.

Scaling Transformers to long contexts is constrained by the quadratic cost of self-attention and the linear growth of key-value cache memory transfer. Sparse attention mitigates this by retrieving only relevant tokens, but current approaches either require large-scale training or, within the training-free regime, rely on semantically coarse heuristics or expensive clustering that is difficult to update efficiently during decoding. We introduce CommunityKV, a framework that formulates sparse attention as a community detection problem. CommunityKV constructs a token graph from the $QK^T$ scores already computed during standard prefill, and partitions the graph into communities to enable retrieval of semantically coherent token groups. A local update rule assigns newly generated tokens to communities in constant time, enabling sparse retrieval throughout streaming decoding without global re-partitioning. We evaluate CommunityKV on open weight models and long context benchmarks, demonstrating that our approach achieves up to $1.86\times$ higher decoding throughput than exact FlashAttention-2 with negligible accuracy degradation.

Parameter-efficient fine-tuning methods, such as LoRA, offer a practical way to adapt large vision and language models to client tasks. However, this becomes particularly challenging under task-level heterogeneity in federated deployments. In this regime, personalization requires balancing general knowledge with personalized knowledge, yet existing approaches largely rely on heuristic mixing rules and lack theoretical justification. Moreover, prior model merging approaches are also computation and communication intensive, making the process inefficient in federated settings. In this work, we propose Potara, a principled framework for federated personalization that constructs a personalized model for each client by merging two complementary models: (i) a federated model capturing general knowledge, and (ii) a local model capturing personalized knowledge. Through the construct of linear mode connectivity, we show that the expected task loss admits a variance trace upper bound, whose minimization yields closed-form optimal mixing weights that guarantee a tighter bound for the merged model than for either the federated or local model alone. Experiments on vision and language benchmarks show that Potara consistently improves personalization while reducing communication, leading to a strong performance-communication trade-off.

Decentralized training enables large-model training over low-end GPUs and internet-grade connections, but communication along both data-parallel and pipeline-parallel axes becomes the primary bottleneck. We study post-pretraining adaptation in this setting. We propose an asynchronous two-circuit system: a fast compressed training circuit drives throughput using activation masking for pipeline-parallel (PP) transfer and compressed data-parallel (DP) synchronization, while a slow anchor circuit runs occasional unmasked forward--backward passes off the critical path. Then, we introduce a spectral correction optimizer that uses these delayed anchor priors to denoise masked gradients without blocking the fast stream. Although prior work has found aggressive activation compression unreliable, we show that masking supports post-pretraining adaptation at high compression rates when anchored this way. Pipeline-parallel compression alone yields up to a 9x throughput gain, and combining it with data-parallel compression increases beyond 40x over internet-grade 200Mbps connections, while matching dense uncompressed performance across domain adaptation and continual pretraining.

Test-time compute scaling, where language models "think longer" via extended chain-of-thought (CoT), is the dominant paradigm for improving reasoning. Prevailing intuition holds that extended reasoning *converges* toward an answer; we show the opposite. Across three reasoning-RL families (DeepSeek-R1, Qwen-QwQ, Llama-3.1-Nemotron) and three benchmarks (GSM8K, MATH, GPQA), step-to-step SAE feature turnover and entropy *rise* monotonically across the chain (Cohen's $d = 0.61$–$0.68$, $p < 10^{-3}$). Yet the final answer is already linearly decodable from the residual stream within the first $\sim 20\%$ of the chain. We call this pattern **commit then explore**: the answer becomes stably decodable early, and the bulk of test-time compute is then spent exploring *around* an already-decodable answer. Targeted ablation shows post-commit features have a $2$–$6\times$ smaller teacher-forced log-probability effect (matched-mass control: $1.5$–$4.6\times$) and a $2$–$3\times$ smaller free-regeneration answer-flip rate than pre-commit features. A terminal-reward RLVR credit-assignment account predicts this asymmetry, and the dynamic is absent in base models: Qwen-2.5 and Llama-3.1 bases fail our detector at every layer, and a held-out quantitative prediction derived from R1 generalises to Qwen-QwQ at Pearson $r = 0.96$. Leveraging the structure, we build a Reasoning Monitor that saves $26$–$34\%$ of inference compute at $\geq 92\%$ accuracy retention, dominating four adaptive-compute baselines. Extended chain-of-thought, under this view, is not the computation of an answer; it is the exploration of its neighborhood.

Adapting language models to new domains during post-training risks degrading previously acquired capabilities, a phenomenon commonly known as \emph{catastrophic forgetting}. Existing mitigation methods largely treat forgetting as a consequence of excessive model drift. They therefore constrain updates by preserving old outputs, replaying old data, or regularizing changes to parameters and representations so that the updated model remains close to its previous state. We take a \textit{different view}: {Rather than pulling the updated model back toward its old state, we translate the new domain into the model’s pre-existing knowledge space, making unfamiliar knowledge learnable through familiar procedures}. Therefore, we propose \textbf{Skill Schema Transport (SST)}, a post-training framework that transports new knowledge into the model's existing skill space. SST abstracts each example type into a skill schema, preserving its essential operations, dependencies, and verification steps while removing domain-specific surface forms. By recasting new examples as instances of reusable procedures, SST turns knowledge update from trajectory memorization into procedural reuse. In continual domain adaptation settings, SST consistently reduces forgetting while improving generalization to related tasks. Across two 3B instruction-tuned backbones, SST improves average final performance on streamed domains by 2.53-5.75 points over sequential post-training. It also lowers max-drop forgetting in all evaluated settings, with the largest reduction from 42.41 to 7.10 points on the Qwen-3B MATH stream, while substantially recovering the OOD degradation induced by sequential updates.