NeurIPS 2026 论文列表

While diffusion has drawn considerable recent attention from the language modeling community, continuous diffusion has appeared less scalable than discrete approaches. To challenge this belief we revisit Plaid, a likelihood-based continuous diffusion language model (DLM), and construct RePlaid by aligning the architecture of Plaid with modern discrete DLMs. In this unified setting, we establish the first scaling law for continuous DLMs that rivals discrete DLMs: RePlaid exhibits a compute gap of only $22\times$ compared to autoregressive models, matches Duo while using fewer parameters, and outperforms MDLM in the over-trained regime. We benchmark RePlaid against recent continuous DLMs: on OpenWebText, RePlaid achieves a new state-of-the-art PPL bound of $22.6$ among continuous DLMs and superior generation quality. These results suggest that continuous diffusion, when trained via likelihood, is a highly competitive and scalable alternative to discrete DLMs. Moreover, we offer theoretical insights to understand the advantage of likelihood-based training. We show that optimizing the noise schedule to minimize the ELBO's variance naturally yields linear cross-entropy (information loss) over time. This evenly distributes denoising difficulty without any case-specific time reparameterization. In addition, we find that optimizing embeddings via likelihood creates structured geometries and drives the most significant likelihood gain.

Large audio language models (LALMs) have shown impressive capabilities on diverse audio understanding tasks, ranging from speech transcription to music analysis. However, because LALMs are typically trained to produce text-aligned responses, their hidden states are progressively shaped for text generation rather than for preserving acoustic information. As a result, the diverse acoustic content that audio carries, such as phonetic detail, prosody, sound events, affect, and pitch, is lost along the way and difficult to leverage in the response. We introduce Continuous Audio Thinking (CoAT), a framework that equips audio language models with a continuous latent workspace for organizing acoustic information prior to response generation, grounded by distillation from audio experts. Within the thinking space, the model can utilize the rich acoustic information provided by expert distillation when generating its response. Furthermore, the proposed continuous thinking block can be processed in a single prefill, so CoAT does not require additional autoregressive decoding cost over the baseline. Across three LALMs, Qwen2-Audio, Qwen2.5-Omni-7B, and Audio Flamingo~3, performance gains on a broad benchmark suite spanning audio reasoning, audio understanding, music classification, speech emotion, and speech transcription demonstrate the effectiveness of CoAT. Further analysis confirms that the auxiliary supervision propagates from the thinking positions to the model's textual responses.

Vision-language-action (VLA) models show promising knowledge accumulation ability from pretraining, yet continual learning in VLA remains challenging, especially for efficient adaptation. Existing continual imitation learning (CIL) methods often rely on additional parameters or external modules, limiting scalability for large VLA models. We propose Stellar VLA, a knowledge-driven CIL framework without increasing network parameters. Two progressively extended variants are designed: T-Stellar for flat task-centric modeling and TS-Stellar for hierarchical task–skill structure. Stellar VLA enables self-evolving knowledge learning by jointly optimizing task representations and a learned knowledge space. We propose a knowledge-guided expert routing mechanism conditioned on knowledge relation and Top-$K$ semantic embeddings, enabling task specialization without increasing model size. Experiments on the LIBERO benchmark show that Stellar VLAs achieve strong performance among both VLA and CIL baselines, using only 1\% data replay. Real-world evaluation on a dual-arm platform with distinct embodiment and scene configurations validates effective knowledge transfer. TS-Stellar excels in hierarchical manipulation, and visualizations reveal robust knowledge retention and task discovery. Project website is provided in the supplementary material.

Generative models, including diffusion models, are increasingly used as foundation models and adapted through sequential fine-tuning, making continual learning an essential problem setting. However, continual learning in such generative models remains poorly understood: after a task change, what aspects of the learned distribution are most easily lost, and what replay samples should be prioritized? We address these questions through the modern Hopfield energy. Recent links between modern Hopfield networks (MHNs) and diffusion models allow analyses in MHNs to be transferred to diffusion models. We introduce intrinsic forgetting as an increase in Hopfield energy after the task change. In tractable settings in an MHN, we prove that high-energy, outlier-like samples undergo a larger energy increase than cluster-like samples, implying that samples located in sharp, isolated basins are more forgettable. We further analyze memory replay and show that replay is particularly effective for high-energy samples, enabling an energy-based selection of replay samples. We validate these predictions in experiments on MHNs and two diffusion models under continual-learning settings: Stable Diffusion and a pixel-space DDPM. In these diffusion models, Hopfield energy tracks reconstruction-based forgetting, and replay experiments reveal energy-dependent mitigation of forgetting that is consistent with the MHN analysis.

Continual learning, the ability of AI systems to improve through sequential experience, has attracted substantial interest, but no high-quality benchmark exists to evaluate it. We introduce Continual Learning Bench (CL-Bench), the first difficult, expert-validated benchmark designed to measure whether LLM-based systems genuinely improve with experience. CL-Bench spans six diverse domains (software engineering, signal processing, disease outbreak forecasting, database querying, strategic game-playing, and demand forecasting), each validated by domain experts and designed so that tasks share a learnable latent structure (codebase layout, disease outbreak dynamics, opponent strategies) that a stateful system can discover online but a stateless one cannot. We evaluate frontier models across several agent architectures, from naive in-context learning (ICL) to dedicated memory systems, introducing a gain metric to isolate learning from prior capabilities. We find that these systems leave headroom for improved continual learning: agents frequently overfit to immediate observations or fail to reuse knowledge across instances, and dedicated memory systems do not fix this---in fact, naive ICL outperforms systems dedicated to memory management. CL-Bench is the first benchmark to evaluate continual learning across diverse real-world domains with expert-validated tasks and isolate online learning from underlying model capability, showing a need for better continual learning systems.

Multi-modal Large Language Models (MLLMs) have made substantial advances on benchmarks, yet their real-world effectiveness remains uncertain. This gap stems from the fundamental misalignment between benchmarks in controlled, static settings and the dynamic, interactive, and contextualized nature of real-world applications. To bridge this gap, we propose CEDI (Contextualized Evaluations of MLLMs through a Dynamic multi-round Interview, a framework that recasts evaluation as a three-party interaction between an evaluatee model, an automated examiner, and a grader. The examiner conducts multi-turn, semi-structured interviews guided by a graph-based representation of the task. By navigating state-space transitions, CEDI deploys diverse strategies—from clarification requests to adversarial probes—to elicit performance evidence.

Flow Matching enables high-quality visual generation via continuous-time dynamics, but inference remains costly due to multiple sequential function evaluations. Existing acceleration methods reduce the number of function evaluations but often introduce additional training overhead, degrade quality, or fail to account for input-dependent variability. We propose an inference-time method, CoFlow, that adaptively selects the step counts for each generation based on the prompt features. Our context-aware CoFlow is trained online with an unsupervised reward that balances efficiency and fidelity. Our method is plug-and-play, requiring no retraining of the generative model. It generalizes to image and video generation, achieving over $2.5\times$ speedup while preserving perceptual and semantic quality. We also provide theoretical insights into the link between adaptive step allocation and discretization error. The anonymized source code is available at \url{https://anonymous.4open.science/r/Contextual_Flow_Matching-9970}.

Standard Flow Matching (FM) models typically employ a pointwise loss function, effectively assuming that the velocity vector at each spatial position is pointwise decomposed supervision given the conditioning. We argue that this Pointwise Independence Assumption is suboptimal for image generation, where strong local correlations exist across space. Neglecting these dependencies leads to artifacts such as structural inconsistency. In this paper, we introduce Contextual Flow Matching (CFM), a generalized framework that enforces consistency not just on individual pixels, but on the contextual relationships within the velocity field. We formulate the training objective using a set of generalized Context Operators---akin to convolution kernels---that abstract relationship constraints. Specifically, we instantiate a Differential Operator to capture high-frequency motion dynamics and an Aggregate Operator to stabilize low-frequency structural evolution. Extensive experiments on ImageNet demonstrate that CFM significantly accelerates convergence and enhances generation fidelity by explicitly modeling spatial dependencies.

Modern object detectors achieve strong performance on standard benchmarks, yet their robustness to contextual variation remains insufficiently investigated. Prior evaluations largely rely on aggregate metrics such as AP on uncontrolled distribution shifts, which conflate multiple factors and can obscure how performance degrades under context change. We introduce \textsc{ContextShift}, a controlled benchmark for evaluating context dependence by systematically manipulating object--context relationships while preserving object appearance. Built on COCO 2017, it isolates context as an independent variable both implicitly, through geometric transformations and explicitly via synthetic and natural background substitutions - with a compatibility axis based on normalized pointwise mutual information (NPMI) for continuous evaluation. Across diverse detector architectures, we observe a consistent degradation pattern: false negatives increase up to 227\% and prediction volume decreases down to -44\%, while false positives remain relatively stable or decline. This observed suppression behavior is not revealed by aggregate metrics such as AP, which can mask substantial recall loss and changes in prediction dynamics. Further analysis suggests that degradation is not primarily explained by reduced confidence, but is instead consistent with a reduced formation of valid detection candidates. Moreover, we find that performance along the statistical compatibility axis is non-monotonic, peaking at intermediate NPMI and degrading toward both extremes, indicating that statistical co-occurrence does not correlate linearly with effective visual context. Finally, we show that a training methodology based on context-aware augmentations rather than the dataset alone, which yields overall better models: every augmented variant outperforms the dataset-only baseline on both original (unmanipulated) test images as well as manipulated images, indicating that data-oriented augmentation can partially recover performance lost to prediction-suppression failures by exposing the model to object--context decoupling during training.

Autoregressive image generation has recently emerged as a competitive visual generation paradigm, yet its generation order is often predefined or heuristic, such as next-patch prediction, random-order prediction, or one-step generation for specific scales. We observe that these strategies can cause models to overlook important structural dependencies in images, thereby limiting both structural robustness and reasoning capability. In this work, we propose a context-aware autoregressive generation framework, where the model dynamically determines the next token location based on global context and current local information. Rather than following a fixed or random order, our method allows the generation process to adapt to image structure and semantic dependencies. Extensive experiments show that context-aware generation significantly improves structural robustness across different image AR paradigms, including masked autoregressive and scale-wise autoregressive models. Beyond quantitative improvements, we further observe emerging reasoning properties: the model can better understand complex semantic instructions and generate images that more faithfully follow the given guidance. These findings suggest that generation order is a critical yet underexplored factor in image autoregressive modeling, and that context-aware decoding can unlock stronger reasoning-aware visual generation capabilities.

Transformers rely on a growing key–value (KV) cache to store context, causing linear memory growth and limited generalization beyond the training window. We show that contextual influence can instead be viewed as updates to a low-dimensional subspace in the model’s weight space, meaning context can be represented as a bounded, low-rank parameter update rather than token-level storage. Motivated by this, we propose PARADE, which internalizes context as parametric memory. It compresses past inputs into a fixed set of weight-space basis vectors and composes them via query-dependent routing into per-query weight updates, enabling streaming inference with constant memory and effectively unbounded context. Experiments show that PARADE matches full attention on long-context tasks and outperforms efficient baselines, especially when relevant information lies far beyond the attention window, while improving as context exceeds the model’s training length.

In-context reinforcement learning (ICRL) has emerged as an effective paradigm for test time adaptation to unseen tasks without parameter updates. However, existing ICRL methods can exhibit brittle and unstable adaptions, and the mechanisms underlying such adaptions remain poorly understood. We provide a policy-gradient view of ICRL and argue that relying on trajectory-level return feedback can lead to high-variance updates when test time rollout is limited. Motivated by the actor--critic principle, we propose **Context Value Informed ICRL (CV-ICRL)**, which equips the in-context policy with an explicit *context value*: the expected discounted return conditioned on the current state and accumulated interaction context. CV-ICRL trains a value head and writes its prediction back into the context as a value token, enabling TD-style return targets for lower-variance policy updates. Experiments on the Dark Room, Minigrid, and Procgen testbeds show that CV-ICRL substantially improves the stability of test time adaptation and achieves higher returns across tasks and environments. The source code and data of this paper are available at https://anonymous.4open.science/r/CV-ICRL-D161.

Real-world generative problems in biology, medical imaging, or robotics, rarely come with perfectly paired source and target distributions. While unbalanced Optimal Transport (uOT) provides a robust framework to bridge unpaired datasets via minimum-length paths in probability space, existing formulations based on the Wasserstein–Fisher–Rao (WFR) geometry introduce a structural bias toward high density regions, often triggering mode collapse. We introduce Contact unbalanced Optimal Transport (CuOT), a novel uOT formulation grounded in contact geometry that decouples density transport from mass growth to eliminate structural bias. This allows CuOT to adapt sampling steps to the local data structure, naturally reducing step sizes in high-density regions to prevent overshooting and ensuring stable convergence. The result is a stable, scalable path-length minimization solver that consistently outperforms WFR-based methods on biological dynamics reconstruction, unpaired image-to-image translation, and video generation.

Motivated by agentic markets -- two-sided markets in which AI tools facilitate search -- we propose a model that incorporates individual consumer search and market-wide learning, solve it to understand the long-run market outcomes, and then study the impact of improved search technologies on these outcomes. A sequence of consumers engage in costly search to acquire progressively refined signals of product fit prior to purchase. The market observes acquired signals and post-transaction feedback thereby impacting future searches. We solve for the per-consumer optimal search policy and characterize the steady-state of the learning dynamics. As search technologies reduce the cost and/or increase the informativeness of search, they cause an improvement in learning and consumer surplus. Using numerical simulations, we also find that these technologies improve the rate of learning and the trajectory of consumer utility. Notably, we show that if the market is unable to observe acquired signals, search technologies can degrade market outcomes, highlighting the importance of transparency in agentic markets.

The quadratic assignment problem (QAP) is widely considered one of the most difficult NP-hard combinatorial optimization problems, and one that remains challenging for neural constructive methods. We introduce CIMP, a Constructive policy trained by Imitation from Multi-expert teachers and built around an explicit Pairwise pre-conditioning block. CIMP reaches a 11.02% mean optimality gap on the 133 QAPLIB instances with published reference values, across 5 fixed same-config seeds, in a single constructive pass — without local search or per-instance refinement — with inference times between 0.1 and 3.1 seconds per instance. The model is trained on 400 synthetic instances with n ≤ 25. The most recent published neural reference reporting full QAPLIB results is SAWT [Tan and Mu, ICML 2024], a learn-to-improve (L2I) method that iteratively refines an assignment per instance after training on 5,120 synthetic instances, and reports a 26.8% mean gap. CIMP operates in a strictly more constrained learn-to-construct (L2C) regime and from a much smaller training budget, yet attains a substantially lower mean gap. The pre-block builds a state-dependent facility–location representation before scoring, a hybrid context-biased decoder mixes learned content similarity with QAP-specific algorithmic bias terms, and a sequence-distribution distillation objective is derived from a diversity-filtered pool of heuristic teachers. Family-wise and size-conditioned analyses, supported by a secondary normalized score, indicate that the gain is broadly consistent across QAPLIB families and across instance sizes beyond the training range.

Constrained learning has been increasingly applied to various domains to ensure explicit feasibility requirements due to fairness, safety, robustness, regularization, and physics or logic constraints. Understanding how training samples influence the solution (e.g., learned parameters) of constrained learning is crucial for interpretability and robustness. The classical influence function may become unreliable in constrained settings: data perturbations can reshape both the objective and the feasible region, leading to estimates that violate feasibility. In response, we propose the Directional Influence Function (DIF), a new estimator that explicitly incorporates the constraints into influence estimation. DIF formulates the optimality conditions of constrained learning as a variational inequality (VI) and analyzes how perturbing training data affects this VI. We validate DIF in constrained linear regression and demonstrate that it recovers leave-one-out retraining results, whereas IF and penalty-based IF exhibit significant bias. We further apply DIF to fairness-constrained CNNs, where DIF accurately predicts test loss changes under data removal and aligns closely with actual retraining. Our results establish DIF as an efficient and reliable tool for data attribution in constrained learning.

Prompt-level instructions are the main way users give language models preferences, safety boundaries, and content rules. But a model can remember a constraint and still violate it when generating text. This points to a gap between two abilities that are often treated as one: retrieving a constraint from context, and enforcing it during token selection. Across five model families (0.5B--32B parameters), we find a clear behavioral split: constraints that admit an alternative generation plan are largely followed, while token-level prohibitions fail whenever the prohibited continuation is locally dominant. Mechanistic analyses show that retrieval heads still attend to the constraint at the violation step, but the resulting signal either paradoxically enhances the prohibited token's logit or suppresses it too weakly to change the argmax. Decoding-time interventions can eliminate surface-form violations, but semantic compliance still requires higher-level verification. These results establish that constraint retrieval and constraint enforcement are separable capabilities, and that reliable token-level compliance requires explicit veto mechanisms beyond prompting.

In this work, we develop proximal preconditioned gradient methods with a focus on spectral gradient methods providing a proximal extension to the Muon and Scion optimizers. We introduce a family of stochastic algorithms that can handle a wide variety of convex and nonconvex constraints and study its convergence under heavy-tailed noise, through a novel analysis tailored to the geometry of the proposed methods. We further propose a variance-reduced version, which achieves faster convergence under standard noise assumptions. Finally, we show that the polynomial iterations used in Muon are more accurately captured by a nonlinear preconditioner than by the ideal matrix sign, leading to a convergence analysis that more faithfully reflects practical implementations.

Biological recurrent circuits can reuse a common substrate by changing its operating regime rather than replacing the circuit itself. This principle is difficult to isolate in fully adaptive neural models, where recurrence, controllers, readouts, and internal representations can all absorb task structure. As a result, successful multi-context behavior does not reveal which route made the computation possible. We introduce Constrained Modulatory Reservoirs (CMR), a fixed-substrate framework for studying such reconfiguration with the main bypasses removed. The primary dynamics and low-rank perturbation basis are fixed, and the readout is denied direct access to the cue, forcing input-dependent adaptation to act through a limited set of recurrent connectivity changes. In transient-cue channel-selection tasks, this restriction makes a capacity transition visible. Low-loss behavior appears only when the available perturbation directions are sufficient, the selected change is retained across the cue-to-signal gap, and the primary dynamics express it during the response window. Controls show that this effect is not explained by low-dimensional cue representation alone. Allowing the substrate to learn hides the bottleneck, while activity- and gain-level alternatives fail to reproduce the same regime. CMR therefore reframes flexible recurrent computation as a question of where adaptive influence is allowed to enter a fixed dynamical system, making capacity, memory, and expression experimentally separable.