ICLR 2026 Papers

Log-likelihood evaluation enables important capabilities in generative models, including model comparison, certain fine-tuning objectives, and many downstream applications. Yet paradoxically, some of today's best generative models -- diffusion and flow-based models -- still require hundreds to thousands of neural function evaluations (NFEs) to compute a single likelihood. While recent distillation methods have successfully accelerated sampling to just a few steps, they achieve this at the cost of likelihood tractability: existing approaches either abandon likelihood computation entirely or still require expensive integration over full trajectories. We present fast flow joint distillation (F2D2), a framework that simultaneously reduces the number of NFEs required for both sampling and likelihood evaluation by two orders of magnitude. Our key insight is that in continuous normalizing flows, the coupled ODEs for sampling and likelihood are computed from a shared underlying velocity field, allowing us to jointly distill both the sampling trajectory and cumulative divergence using a single model. F2D2 is modular, compatible with existing flow-based few-step sampling models, and requires only an additional divergence prediction head. Experiments demonstrate F2D2's capability of achieving accurate log-likelihood with few-step evaluations while maintaining high sample quality, solving a long-standing computational bottleneck in flow-based generative models.

Inspired by human SYSTEM 2 thinking, LLMs excel at complex reasoning tasks via extended Chain-of-Thought. However, similar test-time scaling for diffusion models to tackle complex reasoning remains largely unexplored. From existing work, two primary challenges emerge in this setting: (i) the dependence on an external verifier indicating a notable gap from intrinsic reasoning of human intelligence without any external feedback, and (ii) the lack of an efficient search algorithm. In this paper, we introduce the Verifier-free Test-time Scalable Diffusion Model (VFScale) to achieve scalable intrinsic reasoning, which equips number-of-sample test-time scaling with the intrinsic energy function of diffusion models as the verifier. Concretely, VFScale comprises two key innovations to address the aforementioned challenges. On the training side, VFScale consists of a novel MRNCL loss and a KL regularization to improve the energy landscape, ensuring that the learned energy function itself serves as a reliable verifier. On the inference side, VFScale integrates the denoising process with a novel hybrid Monte Carlo Tree Search (hMCTS) to improve search efficiency. On challenging reasoning tasks of Maze and Sudoku, we demonstrate the effectiveness of VFScale's training objective and scalable inference method. In particular, trained with Maze sizes of up to 6×6, our VFScale solves 88\% of Maze problems with much larger sizes of 15×15, while standard diffusion model completely fails. The code can be found at https://github.com/AI4Science-WestlakeU/VFScale.

Low-bit quantization has achieved significant progress in image super-resolution. However, existing quantization methods show evident limitations in handling the heterogeneity of different components. Particularly under extreme low-bit compression, the issue of information loss becomes especially pronounced. In this work, we present a novel low-bit post-training quantization method, namely static priority-based rectifier routing quantization (SPR$^2$Q). The starting point of this work is to attempt to inject rich and comprehensive compensation information into the model before the quantization , thereby enhancing the model's inference performance after quantization. Firstly, we constructed a low-rank rectifier group and embedded it into the model's fine-tuning process. By integrating weight increments learned from each rectifier, the model enhances the backbone network while minimizing information loss during the lightweighting process. Furthermore, we introduce a static rectifier priority routing mechanism that evaluates the offline capability of each rectifier and generates a fixed routing table. During quantisation, it updates weights based on each rectifier's priority, enhancing the model's capacity and representational power without introducing additional overhead during inference. Extensive experiments demonstrate that the proposed SPR$^2$Q significantly outperforms the state-of-the-arts in five benchmark datasets, achieving PSNR improvements of 0.55 and 1.31 dB on the Set5($\times 2$) dataset under 4-bit and 2-bit settings, respectively.

The success of machine learning for real-world robotic systems has created a new form of intellectual property: the trained policy. This raises a critical need for novel methods that verify ownership and detect unauthorized, possibly unsafe misuse. While watermarking is established in other domains, physical policies present a unique challenge: remote detection. Existing methods assume access to the robot’s internal state, but auditors are often limited to external observations (e.g., video footage). This “Physical Observation Gap” means the watermark must be detected from signals that are noisy, asynchronous, and filtered by unknown system dynamics. We formalize this challenge using the concept of a glimpse sequence, and introduce Colored Noise Coherency (CoNoCo), the first watermarking strategy designed for remote detection. CoNoCo embeds a spectral signal into the robot’s motions by leveraging the policy’s inherent stochasticity. To show it does not degrade performance, we prove CoNoCo preserves the marginal action distribution. Our experiments demonstrate strong, robust detection across various remote modalities—including motion capture and side-way/top-down video footage—in both simulated and real-world robot experiments. This work provides a necessary step toward protecting intellectual property in robotics, offering the first method for validating the provenance of physical policies non invasively, using purely remote observations.

Current visual reasoning methods mainly focus on exploring specific reasoning modes. Although improvements can be achieved in particular domains, they struggle to develop general reasoning capabilities. Inspired by this, we propose a novel adaptive reasoning paradigm, $\underline{\text{M}}$ixture-$\underline{\text{o}}$f-$\underline{\text{V}}$isual-$\underline{\text{T}}$houghts (**MoVT**), which unifies different reasoning modes within a single model and guides it to select the appropriate mode based on context. To achieve this, we introduce **AdaVaR**, a two-stage $\underline{\text{Ada}}$ptive $\underline{\text{V}}$isu$\underline{\text{a}}$l $\underline{\text{R}}$easoning learning framework: different modes are unified and learned during the supervised cold-start stage, and the mode selection capability is induced via an RL process with a carefully designed AdaGRPO algorithm. Extensive experiments show that AdaVaR effectively guides the model to learn and differentiate multiple modes and perform context-adaptive mode selection, achieving consistent improvement across various scenarios, highlighting MoVT as an effective solution for building general visual reasoning models.

General continual learning (GCL) challenges intelligent systems to learn from single-pass, non-stationary data streams without clear task boundaries. While recent advances in continual parameter-efficient tuning (PET) of pretrained models show promise, they typically rely on multiple training epochs and explicit task cues, limiting their effectiveness in GCL scenarios. Moreover, existing methods often lack targeted design and fail to address two fundamental challenges in continual PET: how to allocate expert parameters to evolving data distributions, and how to improve their representational capacity under limited supervision. Inspired by the fruit fly's hierarchical memory system characterized by sparse expansion and modular ensembles, we propose FlyPrompt, a brain-inspired framework that decomposes GCL into two subproblems: expert routing and expert competence improvement. FlyPrompt introduces a randomly expanded analytic router for instance-level expert activation and a temporal ensemble of output heads to dynamically adapt decision boundaries over time. Extensive theoretical and empirical evaluations demonstrate FlyPrompt's superior performance, achieving up to 11.23%, 12.43%, and 7.62% gains over state-of-the-art baselines on CIFAR-100, ImageNet-R, and CUB-200, respectively. Our source code is available at https://github.com/AnAppleCore/FlyGCL.

Fast convergence and high-quality image recovery are two essential features of algorithms for solving ill-posed imaging inverse problems. Existing methods, such as regularization by denoising (RED), often focus on designing sophisticated image priors to improve reconstruction quality, while leaving convergence acceleration to heuristics. To bridge the gap, we propose Restarted Inertia with Score-based Priors (RISP) as a principled extension of RED. RISP incorporates a restarting inertia for fast convergence, while still allowing score-based image priors for high-quality reconstruction. We prove that RISP attains a faster stationary-point convergence rate than RED, without requiring the convexity of the image prior. We further derive and analyze the associated continuous-time dynamical system, offering insight into the connection between RISP and the heavy-ball ordinary differential equation (ODE). Experiments across a range of imaging inverse problems demonstrate that RISP enables fast convergence while achieving high-quality reconstructions.

Subject-consistent generation (SCG)-aiming to maintain a consistent subject identity across diverse scenes-remains a challenge for text-to-image (T2I) models. Existing training-free SCG methods often achieve consistency at the cost of layout and pose diversity, hindering expressive visual storytelling. To address the limitation, we propose subject-Consistent and pose-Diverse T2I framework, dubbed as CoDi, that enables consistent subject generation with diverse pose and layout. Motivated by the progressive nature of diffusion, where coarse structures emerge early and fine details are refined later, CoDi adopts a two-stage strategy: Identity Transport (IT) and Identity Refinement (IR). IT operates in the early denoising steps, using optimal transport to transfer identity features to each target image in a pose-aware manner. This promotes subject consistency while preserving pose diversity. IR is applied in the later denoising steps, selecting the most salient identity features to further refine subject details. Extensive qualitative and quantitative results on subject consistency, pose diversity, and prompt fidelity demonstrate that CoDi achieves both better visual perception and stronger performance across all metrics. The code is provided in the supplementary material.

Recently, large time series models (LTSM) have become popular and important because they exhibit characteristics similar to large language models, such as flexible context length, scalability, and task generality, outperforming the advanced task-specific models in the domain. However, existing research indicates that the pre-trained LTSM can show a poor non-convex loss landscape (indicating poor trainability). Hence, directly fine-tuning pre-trained LTSM shows overfitting, which leads to poor fine-tuning performance, even worse than training from scratch on the downstream datasets. This severely diminishes the value of the pre-trained LTSM. To address this, we propose a new fine-tuning method called Smoothed Full Fine-tuning (SFF). Specifically, before fine-tuning, we first construct an auxiliary LTSM with a smooth loss landscape (indicating good trainability) through random initialization. Second, we utilize it to smooth the loss landscape of the pre-trained LTSM through linear interpolation between their weights. As a result, the smoothed LTSM acquires good trainability while retaining good pre-training knowledge, thereby achieving better performance when fine-tuned on the downstream dataset. We also explain why SFF is effective from the perspective of optimization theory: interpolation perturbs sharp minima without obviously harming originally flat regions, thereby aiding sharp minima escape to better and smoother basins. Extensive experiments on popular datasets show that our method indeed improves the performance of eight popular LTSMs, e.g., Timer, TimesFM, MOMENT, UniTS, MOIRAI, Chronos, TTMs, and Sundial, in different downstream tasks.

Next-token prediction serves as the foundational learning task that enables reasoning in LLMs. But what should the learning task be when aiming to equip MLLMs with temporal reasoning capabilities over video inputs? Existing tasks such as video captioning primarily promote modality alignment, while video question answering typically relies on annotations from humans or much stronger MLLMs. To address this gap, we propose next-event prediction (NEP), a learning task that harnesses future video segments as a rich, self-supervised signal to foster temporal reasoning. We segment each video into past and future frames: the MLLM takes the past frames as input and predicts events in the future, thereby encouraging the model to reason temporally in order to complete the task. To study this learning task, we curate V1-33K, a dataset comprising 33,000 automatically extracted videos spanning diverse real-world scenarios. Using the same videos, we further explore a range of video instruction-tuning tasks data to provide controlled comparisons and isolate the effect of NEP. To evaluate progress, we introduce FutureBench to assess coherence in predicting unseen future events. Experiments validate that NEP offers a scalable and effective training task for fostering temporal reasoning in MLLMs.

Preserving identity while precisely manipulating attributes is a central challenge in face editing for both images and videos. Existing methods often introduce visual artifacts or fail to maintain temporal consistency. We present **FlowGuide**, a unified framework that achieves fine-grained control over face editing in diffusion models. Our approach is founded on the local linearity of the UNet bottleneck’s latent space, which allows us to treat semantic attributes as corresponding to specific linear subspaces, providing a mathematically sound basis for disentanglement. FlowGuide first identifies a set of orthogonal basis vectors that span these semantic subspaces for both the original content and the target edit, a representation that efficiently captures the most salient features of each. We then introduce a novel guidance mechanism that quantifies the geometric alignment between these bases to dynamically steer the denoising trajectory at each step. This approach offers superior control by ensuring edits are confined to the desired attribute’s semantic axis while preserving orthogonal components related to identity. Extensive experiments demonstrate that FlowGuide achieves state-of-the-art performance, producing high-quality edits with superior identity preservation and temporal coherence.

Web agents such as deep research have demonstrated superhuman cognitive abilities, capable of solving highly challenging information-seeking problems. However, most research remains largely text-centric, overlooking visual information in the real world. This makes multimodal deep research highly challenging, as such agents require much stronger perceptual, logical, and knowledge-based reasoning abilities, as well as proficiency in more sophisticated tools. To address this limitation, we introduce WebWatcher, a multimodal agent for deep research with joint reasoning ability across both visual and textual modalities. It uses high-quality synthetic trajectories for efficient cold start training, utilizes various tools for deep reasoning, and further enhances generalization through reinforcement learning. To better evaluate the capabilities of multimodal agents, we propose BrowseComp-VL, a benchmark with the style of BrowseComp that requires complex information retrieval involving both visual and textual information. Experimental results show that WebWatcher outperforms the prompt-based workflow and open-source agents on HLE and BrowseComp-VL, and demonstrates its perception, multimodal reasoning, and searching capabilities across the other three benchmarks, respectively.

Spatial embodied intelligence often operates under partial observability, where agents must act to acquire missing information rather than passively consume complete observations. In such settings, progress depends on actively selecting informative actions that reduce uncertainty and support the construction of spatial understanding. While multimodal foundation models have shown strong performance on passive multimodal perception and reasoning tasks, their ability to support active, self-directed exploration under partial observability has not been systematically studied. In particular, it remains unclear whether and how these models can decide what to observe next in order to build and maintain a coherent spatial belief over time. We therefore propose \tos, defined as an agent’s ability to actively acquire information through self-directed, active exploration and to construct, revise, and exploit a spatial belief from sequential, partial observations. We implement \tos using a benchmark with textual and visual environments. Rather than solving specific tasks, the goal is curiosity-driven exploration to build a complete, accurate spatial belief. A core innovation is spatial belief probing: we prompt it to reveal its internal spatial belief as a cognitive map at each step, letting us measure the quality of its underlying spatial model. Our evaluation of state-of-the-art models on a suite of downstream tasks reveals critical bottlenecks: (1) \textbf{The Active-Passive Gap}: Performance degrades when agents must autonomously gather information (e.g., \textsc{GPT-5.2}: $0.57{\to}0.46$); (2) \textbf{Inefficiency}: Models explore in an unsystematic way and with high redundancy, failing to match the efficiency of program-based proxies while producing no better results. Through belief probing, we diagnose that perception acts as an initial bottleneck, yet global beliefs suffer further from \textbf{instability} that causes spatial knowledge to degrade over time. Finally, using a false belief paradigm to test belief revision, we uncover \textbf{Belief Inertia} where agents fail to overwrite obsolete priors. This issue exists in text agents but is notably severe in vision-based models.

Autonomous science agents, built on large language models (LLMs), are increasingly being investigated to generate hypotheses, design experiments, and produce reports. Prior science agents primarily focus on open-ended scientific problems, where such outputs—hypotheses, experiments, or analyses are inherently subjective and thus difficult to evaluate rigorously. In contrast, existing scientific coding benchmarks provide tasks with clearly defined, executable outputs that enable objective assessment. However, current agent-based approaches to these benchmarks remain engineering-driven pipelines, lacking principled framework design. This mismatch exposes a gap: the absence of end-to-end, principled science agent frameworks for scientific coding tasks. We address this gap by focusing on scientific coding tasks, where evaluation can be made rigorously, and introducing an agent framework SciNav (Scientific Navigator) that enables more effective solution exploration. Our framework is designed to operate efficiently under constrained search budgets, moving beyond reliance on pre-defined success metrics and prolonged search cycles. Inspired by findings that comparative judgments often reveal finer-grained quality differences and therefore provide greater discriminative power than absolute scoring, our framework leverages pairwise relative judgments within a tree search process to select top-K promising solution branches, prune low-potential ones, and progressively narrow down the solution candidates on the selected branches guided by relative comparisons. We demonstrate our agent's effectiveness across different types of tasks on two benchmarks. Experiments show that SciNav significantly outperforms direct prompting and prior agents like OpenHands and Self-Debug across different base models, task types, and difficulty levels, and exceeds different frontier comparators such as random selection and LLM absolute scoring. These results confirm the strength of our agent design and highlight the effectiveness of relative judgment–guided top-K search for high-quality scientific coding, marking a step toward more practical science agents.

In a multi-follower Bayesian Stackelberg game, a leader plays a mixed strategy over $L$ actions to which $n\ge 1$ followers, each having one of $K$ possible private types, best respond. The leader's optimal strategy depends on the distribution of the followers' private types. We study an online learning problem for Bayesian Stackelberg game, where a leader interacts for $T$ rounds with $n$ followers with types sampled from an unknown distribution every round. The leader's goal is to minimize regret, defined as the difference between the cumulative utility of the optimal strategy and that of the actually chosen strategies. We design learning algorithms for the leader under different settings. Under type feedback, where the leader observes the followers' types after each round, we design algorithms that achieve $\mathcal O\big(\sqrt{\min\{L\log(nKA T), ~ nK \} \cdot T} \big)$ regret for independent type distributions and $\mathcal O\big(\sqrt{\min\{L\log(nKA T), ~ K^n \} \cdot T} \big)$ regret for general type distributions. Interestingly, these bounds do not grow with $n$ at a polynomial rate. Under action feedback, where the leader only observes the followers' actions, we design algorithms with $\mathcal O( \min\{\sqrt{ n^L K^L A^{2L} L T \log T}, ~ K^n\sqrt{ T } \log T \} )$ regret. We also provide a lower bound of $\Omega(\sqrt{\min\{L, ~ nK\}T})$, almost matching the type-feedback upper bounds.

Dense 4D reconstruction from unposed images remains a critical challenge, with current methods relying on slow test-time optimization or fragmented, task-specific feedforward models. We introduce UFO-4D, a unified feedforward framework to reconstruct a dense, explicit 4D representation from just a pair of unposed images. UFO-4D directly estimates dynamic 3D Gaussian Splats, enabling the joint and consistent estimation of 3D geometry, 3D motion, and camera pose in a feedforward manner. Our core insight is that differentiably rendering different signals from a single, holistic representation enables significant advantages at training time, in the form of a self-supervisory image synthesis loss as well as tightly coupling motion and depth losses. This approach mitigates data scarcity, allowing UFO-4D to achieve joint estimation of geometry, motion, and camera pose while outperforming prior work by up to a factor of three. The 4D representation also enables high-fidelity 4D spatio-temporal interpolation.

Training recurrent neural networks (RNNs) to perform neuroscience-style tasks has become a popular way to generate hypotheses for how neural circuits in the brain might perform computations. Recent work has demonstrated that task-trained RNNs possess a strong simplicity bias. In particular, this inductive bias often causes RNNs trained on the same task to collapse on effectively the same solution, typically comprised of fixed-point attractors or other low-dimensional dynamical motifs. While such solutions are readily interpretable, this collapse proves counterproductive for the sake of generating a set of genuinely unique hypotheses for how neural computations might be performed. Here we propose Iterative Neural Similarity Deflation (INSD), a simple method to break this inductive bias. By penalizing linear predictivity of neural activity produced by standard task-trained RNNs, we find an alternative class of solutions to classic neuroscience-style RNN tasks. These solutions appear distinct across a battery of analysis techniques, including representational similarity metrics, dynamical systems analysis, and the linear decodability of task-relevant variables. Moreover, these alternative solutions can sometimes achieve superior performance in difficult or out-of-distribution task regimes. Our findings underscore the importance of moving beyond the simplicity bias to uncover richer and more varied models of neural computation.

Current training data attribution (TDA) methods treat influence as static, ignoring the fact that neural networks learn in distinct stages. This stagewise development, driven by phase transitions on a degenerate loss landscape, means a sample's importance is not fixed but changes throughout training. In this work, we introduce a developmental framework for data attribution, grounded in singular learning theory. We predict that influence can change non-monotonically, including sign flips and sharp peaks at developmental transitions. We first confirm these predictions analytically and empirically in a toy model, showing that dynamic shifts in influence directly map to the model's progressive learning of a semantic hierarchy. Finally, we demonstrate these phenomena at scale in language models, where token-level influence changes align with known developmental stages.

Symbolic Regression (SR) tries to reveal the hidden equations behind observed data. However, most methods search within a discrete equation space, where the structural modifications of equations rarely align with their numerical behavior, leaving fitting error feedback too noisy to guide exploration. To address this challenge, we propose GenSR, a generative latent space–based SR framework following the "map construction $\rightarrow$ coarse localization $\rightarrow$ fine search" paradigm. Specifically, GenSR first pretrains a dual-branch Conditional Variational Autoencoder (CVAE) to reparameterize symbolic equations into a generative latent space with symbolic continuity and local numerical smoothness. This space can be regarded as a well-structured "map" of the equation space, providing directional signals for search. At inference, the CVAE coarsely localizes the input data to promising regions in the latent space. Then, a modified CMA-ES refines the candidate region, leveraging smooth latent gradients. From a Bayesian perspective, GenSR reframes SR task as maximizing the conditional distribution $p({\rm Equ.}|{\rm Num.})$, with CVAE training achieving this objective through the Evidence Lower Bound (ELBO). This new perspective provides a theoretical guarantee for the effectiveness of GenSR. Extensive experiments show that GenSR jointly optimizes predictive accuracy, expression simplicity, and computational efficiency, while remaining robust under noise.