论文检索

Theory · Reinforcement Learning and Planning

Pedro Santos, Alberto Sardinha, Francisco S. Melo

In this work, we contribute the first approach to solve infinite-horizon discounted general-utility Markov decision processes (GUMDPs) in the single-trial regime, i.e., when the agent's performance is evaluated based on a single trajectory. First, we provide some fundamental results regarding policy optimization in the single-trial regime, investigating which class of policies suffices for optimality, casting our problem as a particular MDP that is equivalent to our original problem, as well as studying the computational hardness of policy optimization in the single-trial regime. Second, we show how we can leverage online planning techniques, in particular a Monte-Carlo tree search algorithm, to solve GUMDPs in the single-trial regime. Third, we provide experimental results showcasing the superior performance of our approach in comparison to relevant baselines.

Applications · Time Series

Huiqiang Wang, Jieming Shi, Qing Li

Modeling the relationships among variables has become increasingly important, particularly in high-dimensional multivariate time series forecasting tasks. However, most existing methods primarily focus on capturing coarse-grained correlations between variables, overlooking a finer and more dynamic aspect: the variable interactions often manifest differently as time progresses. To address this limitation, we propose FACT, an Fine-grained Across-variable Convolution architecture for multivariate Time series forecasting that explicitly models fine-grained variable interactions from both the time and frequency domains. Technically, we introduce a depth-wise convolution block DConvBlock, which leverages a depth-wise convolution architecture with channel-specific kernels to model dynamic variable interactions at each granularity. To further enhance efficiency, we reconfigure the original one-dimensional variables into a two-dimensional space, reducing the variable distance and the required model layers. Then DConvBlock incorporates multi-dilated 2D convolutions with progressively increasing dilation rates, enabling the model to capture fine-grained and dynamic variable interactions while efficiently attaining a global reception field. Extensive experiments on twelve benchmark datasets demonstrate that FACT not only achieves state-of-the-art forecasting accuracy but also delivers substantial efficiency gains, significantly reducing both training time and memory consumption compared to attention mechanism.

Applications · Time Series

Xiannan Huang, Shuhan Qiu, Jiayuan Du, Chao Yang

Time series forecasting is of significant importance across various domains. However, it faces significant challenges due to distribution shift. This issue becomes particularly pronounced in online deployment scenarios where data arrives sequentially, requiring models to adapt continually to evolving patterns. Current time series online learning methods focus on two main aspects: selecting suitable parameters to update (e.g., final layer weights or adapter modules) and devising suitable update strategies (e.g., using recent batches, replay buffers, or averaged gradients). We challenge the conventional parameter selection approach, proposing that distribution shifts stem from changes in underlying latent factors influencing the data. Consequently, updating the feature representations of these latent factors may be more effective. To address the critical problem of delayed feedback in multi-step forecasting (where true values arrive much later than predictions), we introduce ADAPT-Z (Automatic Delta Adjustment via Persistent Tracking in Z-space). ADAPT-Z utilizes an adapter module that leverages current feature representations combined with historical gradient information to enable robust parameter updates despite the delay. Extensive experiments demonstrate that our method consistently outperforms standard base models without adaptation and surpasses state-of-the-art online learning approaches across multiple datasets.

Reinforcement Learning · Deep RL

Thanh-Long V. Le, Myeongho Jeon, Kim Vu, Viet Lai, Eunho Yang

Reinforcement Learning with Verifiable Rewards (RLVR) is a powerful framework for improving the reasoning abilities of Large Language Models (LLMs). However, current methods such as GRPO rely only on problems where the model responses to the same input differ in correctness, while ignoring those where all responses receive the same reward — so-called zero-variance prompts. In this work, we argue that such prompts are not useless but can, in fact, provide meaningful feedback for policy optimization. To this end, we introduce Reinforcement Learning with Zero-Variance Prompts (RL-ZVP), a novel algorithm that extract learning signals from zero-variance prompts. RL-ZVP directly rewards correctness and penalizes errors even without contrasting responses, modulating feedback with token-level characteristics to preserve informative, nuanced signals. Across six math reasoning benchmarks, RL-ZVP achieves significant improvements of up to 8.61 points in accuracy and 7.77 points in pass rate over GRPO, while consistently outperforming other baselines that filter out zero-variance prompts. These results highlight the untapped potential of learning from zero-variance prompts in RLVR.

General Machine Learning · Probabilistic Methods

Yang Yang, Severi Rissanen, Paul Chang, Nasrulloh Satrio, Daolang Huang, Arno Solin, Markus Heinonen, Luigi Acerbi

Amortized simulator-based inference offers a powerful framework for tackling Bayesian inference in computational fields such as engineering or neuroscience, increasingly leveraging modern generative methods like diffusion models to map observed data to model parameters or future predictions. These approaches yield posterior or posterior-predictive samples for new datasets without requiring further simulator calls after training on simulated parameter-data pairs. However, their applicability is often limited by the prior distribution(s) used to generate model parameters during this training phase. To overcome this constraint, we introduce *PriorGuide*, a technique specifically designed for diffusion-based amortized inference methods. PriorGuide leverages a novel guidance approximation that enables flexible adaptation of the trained diffusion model to new priors at test time, crucially without costly retraining. This allows users to readily incorporate updated information or expert knowledge post-training, enhancing the versatility of pre-trained inference models.

Applications · Neuroscience, Cognitive Science

Nathaniel Imel, Noga Zaslavsky

Converging evidence suggests that human systems of semantic categories achieve near-optimal compression via the Information Bottleneck (IB) complexity-accuracy tradeoff. Large language models (LLMs) are not trained for this objective, which raises the question: are LLMs capable of evolving efficient human-aligned semantic systems? To address this question, we focus on color categorization --- a key testbed of cognitive theories of categorization with uniquely rich human data --- and replicate with LLMs two influential human studies. First, we conduct an English color-naming study, showing that LLMs vary widely in their complexity and English-alignment, with larger instruction-tuned models achieving better alignment and IB-efficiency. Second, to test whether these LLMs simply mimic patterns in their training data or actually exhibit a human-like inductive bias toward IB-efficiency, we simulate cultural evolution of pseudo color-naming systems in LLMs via a method we refer to as Iterated in-Context Language Learning (IICLL). We find that akin to humans, LLMs iteratively restructure initially random systems towards greater IB-efficiency. However, only a model with strongest in-context capabilities (Gemini 2.0) is able to recapitulate the wide range of near-optimal IB-tradeoffs observed in humans, while other state-of-the-art models converge to low-complexity solutions. These findings demonstrate how human-aligned semantic categories can emerge in LLMs via the same fundamental principle that underlies semantic efficiency in humans.

General Machine Learning · Probabilistic Methods

Conor Hassan, Nasrulloh Satrio, Cen-You Li, Daolang Huang, Paul Chang, Yang Yang, Francesco Silvestrin, Samuel Kaski, Luigi Acerbi

Set-based transformer models for amortized probabilistic inference and meta-learning, such as neural processes, prior-fitted networks, and tabular foundation models, excel at single-pass _marginal_ prediction. However, many applications require _joint distributions_ over multiple predictions. Purely autoregressive architectures generate these efficiently but sacrifice flexible set-conditioning. Obtaining joint distributions from set-based models requires re-encoding the entire context at each autoregressive step, which scales poorly. We introduce a _causal autoregressive buffer_ that combines the strengths of both paradigms. The model encodes the context once and caches it; a lightweight causal buffer captures dependencies among generated targets, with each new prediction attending to both the cached context and all previously predicted targets added to the buffer. This enables efficient batched autoregressive sampling and joint predictive density evaluation. Training integrates set-based and autoregressive modes through masked attention at minimal overhead. Across synthetic functions, EEG time series, a Bayesian model comparison task, and tabular regression, our method closely matches the performance of full context re-encoding while delivering up to $20\times$ faster joint sampling and density evaluation, and up to $7\times$ lower memory usage.

Computer Vision · Vision Models & Multimodal

Sumin Kim, Hyemin Jeong, Mingu Kang, Yejin Kim, Yoori Oh, Joonseok Lee

The exponential growth of video content necessitates effective video summarization to efficiently extract key information from long videos. However, current approaches struggle to fully comprehend complex videos, primarily because they employ static or modality-agnostic fusion strategies. These methods fail to account for the dynamic, frame-dependent variations in modality saliency inherent in video data. To overcome these limitations, we propose **TripleSumm**, a novel architecture that adaptively weights and fuses the contributions of visual, text, and audio modalities at the frame level. Furthermore, a significant bottleneck for research into multimodal video summarization has been the lack of comprehensive benchmarks. Addressing this bottleneck, we introduce **MoSu** (Most Replayed Multimodal Video Summarization), the first large-scale benchmark that provides all three modalities. Extensive experiments demonstrate that TripleSumm achieves state-of-the-art performance, outperforming existing methods by a significant margin on four benchmarks, including MoSu. Our code and dataset are available at https://github.com/smkim37/TripleSumm.

Reinforcement Learning · Deep RL

Peter Chen, Xiaopeng Li, Ziniu Li, Wotao Yin, Xi Chen, Tianyi Lin

This paper examines the exploration–exploitation trade-off in reinforcement learning with verifiable rewards (RLVR), a framework for improving the reasoning of Large Language Models (LLMs). Recent studies suggest that RLVR can elicit strong mathematical reasoning in LLMs through two seemingly paradoxical mechanisms: \textit{spurious rewards}, which suppress exploitation by rewarding outcomes unrelated to the ground truth, and \textit{entropy minimization}, which suppresses exploration by pushing the model toward more confident and deterministic outputs, highlighting a puzzling dynamic: both discouraging exploitation and discouraging exploration improve reasoning performance, yet the underlying principles that reconcile these effects remain poorly understood. We focus on two fundamental questions: (i) how policy entropy relates to performance, and (ii) whether spurious rewards yield gains, potentially through the interplay of clipping bias and model contamination. Our results show that clipping bias under spurious rewards reduces policy entropy, leading to more confident and deterministic outputs, while entropy minimization alone is insufficient for improvement. We further propose a reward-misalignment model explaining why spurious rewards can enhance performance beyond contaminated settings. Our findings clarify the mechanisms behind spurious-reward benefits and provide principles for more effective RLVR training.

Theory · Learning Theory

Amir Carmel, Robert Krauthgamer

Uniform sampling is a highly efficient method for data summarization. However, its effectiveness in producing coresets for clustering problems is not yet well understood, primarily because it generally does not yield a strong coreset, which is the prevailing notion in the literature. We formulate \emph{stable coresets}, a notion that is intermediate between the standard notions of weak and strong coresets, and effectively combines the broad applicability of strong coresets with highly efficient constructions, through uniform sampling, of weak coresets. Our main result is that a uniform sample of size $O(\epsilon^{-2}\log d)$ yields, with high constant probability, a stable coreset for $1$-median in $\mathbb{R}^d$ under the $\ell_1$ metric. We then leverage the powerful properties of stable coresets to easily derive new coreset constructions, all through uniform sampling, for $\ell_1$ and related metrics, such as Kendall-tau and Jaccard. We also show applications to fair rank aggregation and to approximation algorithms for $k$-median problem in these metric spaces. Our experiments validate the benefits of stable coresets in practice, in terms of both construction time and approximation quality.

Deep Learning · Generative Models and Autoencoders

François Bertholom, Khalid Oublal

Denoising Diffusion Probabilistic Models (DDPMs) and Hierarchical Variational Autoencoders (HVAEs) are typically studied as distinct paradigms for high-dimensional generative modeling. In this work, we bridge this gap by establishing a formal equivalence between DDPMs and HVAEs in the limit of infinite depth with a fixed, Markovian inference process. We argue that this architectural isomorphism is not merely a mathematical curiosity but the structural key to understanding the superior generalization capabilities of diffusion models. By viewing the forward diffusion process as a fixed encoder, we elucidate how DDPMs circumvent the posterior collapse often observed in deep VAEs, effectively balancing the trade-off between structural guidance and texture synthesis. We support this theoretical unification with empirical analysis of the semantic phase transitions in latent space and demonstrate the invariance of the Variational Lower Bound under noise schedule reparameterizations, confirming the interpretation of diffusion as a continuous-time hierarchical variational framework.

Deep Learning · Robustness

Giannis Nikolentzos, Konstantinos Skianis

The Lipschitz constant of a neural network is connected to several important properties of the network such as its robustness and generalization. It is thus useful in many settings to estimate the Lipschitz constant of a model. Prior work has focused mainly on estimating the Lipschitz constant of multi-layer perceptrons and convolutional neural networks. Here we focus on data modeled as sets or multisets of vectors and on neural networks that can handle such data. These models typically apply some permutation invariant aggregation function, such as the sum, mean or max operator, to the input multisets to produce a single vector for each input sample. In this paper, we investigate whether these aggregation functions, along with an attention-based aggregation function, are Lipschitz continuous with respect to three distance functions for unordered multisets, and we compute their Lipschitz constants. In the general case, we find that each aggregation function is Lipschitz continuous with respect to only one of the three distance functions, while the attention-based function is not Lipschitz continuous with respect to any of them. Then, we build on these results to derive upper bounds on the Lipschitz constant of neural networks that can process multisets of vectors, while we also study their stability to perturbations and generalization under distribution shifts. To empirically verify our theoretical analysis, we conduct a series of experiments on datasets from different domains.

Theory · Probabilistic Methods

Nazar Buzun, Daniil Shlenskii, Maksim Bobrin, Dmitry Dylov

Optimal transport (OT) has become a natural framework for guiding the probability flows. Yet, the majority of recent generative models assume trivial geometry (e.g., Euclidean) and rely on strong density-estimation assumptions, yielding trajectories that do not respect the true principles of optimality in the underlying manifold. We present Hamiltonian Optimal Transport Advection (HOTA), a Hamilton–Jacobi–Bellman based method that tackles the dual dynamical OT problem explicitly through Kantorovich potentials, enabling efficient and scalable trajectory optimization. Our approach effectively evades the need for explicit density modeling, performing even when the cost functionals are non-smooth. Empirically, HOTA outperforms all baselines in standard benchmarks, as well as in custom datasets with non-differentiable costs, both in terms of feasibility and optimality.

Social Aspects · Trustworthy Machine Learning

Saleh Zare Zade, Xiangyu Zhou, Sijia Liu, Dongxiao Zhu

Large Language Models are prone to memorizing sensitive, copyrighted, or hazardous content, posing significant privacy and legal concerns. Retraining from scratch is computationally infeasible, whereas current unlearning methods exhibit unstable trade-offs between forgetting and utility, frequently producing incoherent outputs on forget prompts and failing to generalize due to the persistence of lexical-level and semantic-level associations in attention. We propose Attention Smoothing Unlearning (ASU), a principled framework that casts unlearning as self-distillation from a forget-teacher derived from the model’s own attention. By increasing the softmax temperature, ASU flattens attention distributions and directly suppresses the lexical-level and semantic-level associations responsible for reconstructing memorized knowledge. This results in a bounded optimization objective that erases factual information yet maintains coherence in responses to forget prompts. Empirical evaluation on TOFU, MUSE, and WMDP, along with real-world and continual unlearning scenarios across question answering and text completion, demonstrates that ASU outperforms the baselines for most of the unlearning scenarios, delivering robust unlearning with minimal loss of model utility.

Deep Learning · Generative Models and Autoencoders

Alexandre Galashov, Ashwini Pokle, Arnaud Doucet, Arthur Gretton, Mauricio Delbracio, Valentin De Bortoli

Classifier-free guidance (CFG) is a widely used technique for improving the perceptual quality of samples from conditional diffusion models. It operates by linearly combining conditional and unconditional score estimates using a *guidance weight* $\omega$. While a large, static weight can markedly improve visual results, this often comes at the cost of poorer distributional alignment. In order to better approximate the target conditional distribution, we instead learn *guidance weights* $\omega_{c,(s,t)}$, which are continuous functions of the conditioning $c$, the time $t$ from which we denoise, and the time $s$ towards which we denoise. We achieve this by minimizing the distributional mismatch between noised samples from the true conditional distribution and samples from the guided diffusion process. We extend our framework to reward guided sampling, enabling the model to target distributions tilted by a reward function $R(x_0,c)$, defined on clean data and a conditioning $c$. We demonstrate the effectiveness of our methodology on low-dimensional toy examples and high-dimensional image settings, where we observe improvements in Fréchet inception distance (FID) for image generation. In text-to-image applications, we observe that employing a reward function given by the CLIP score leads to guidance weights that improve image-prompt alignment.

Deep Learning · Generative Models and Autoencoders

Egor Sevriugov, Nikita Dragunov, Anton Razzhigaev, Andrey Kuznetsov, Ivan Oseledets

Non-autoregressive (NAR) language models offer notable efficiency in text generation by circumventing the sequential bottleneck of autoregressive decoding. However, accurately modeling dependencies in discrete sequences remains challenging in this paradigm. In this work, we advance the field of NAR generation by applying conditional flow matching (CFM) methods grounded in geometrically principled interpolation, specifically leveraging Kullback-Leibler (KL) divergence geodesics, which correspond to linear interpolation in logit space. We rigorously establish that maximizing conditional likelihood in this setting precisely recovers the flow matching velocity field, supplying the theoretical justification for this approach in sequence modeling. To address practical performance gaps of \emph{basic} inference, we propose a novel empirical \emph{sampling} strategy that iteratively denoises and re-noises, along with a \emph{hybrid} scheme that integrates our \emph{sampling} method with \emph{basic} procedure. Across unconditional and conditional text and code infilling, the approach improves perplexity and downstream metrics over prior NAR baselines under matched settings.

Social Aspects · Fairness, Equity, Justice and Safety

Vithurabiman Senthuran, Yong Xiang, Iynkaran Natgunanathan, Uthayasanker Thayasivam

Watermarking has been widely used for copyright protection of digital images. Deep learning-based (DL) watermarking systems have recently emerged as more effective than traditional methods, offering improved fidelity and resilience against attacks. Among the various threats to DL watermarking systems, self-re-watermarking attacks represent a critical and underexplored challenge. In such attacks, the same encoder is maliciously reused to embed a new message into an already watermarked image. This process effectively prevents the original decoder from retrieving the original watermark without introducing perceptual artifacts. In this work, we make two key contributions. First, we introduce the self-re-watermarking threat model as a novel attack vector and demonstrate that existing state-of-the-art watermarking methods consistently fail under such attacks. Second, we develop a self-aware watermarking framework to defend against this threat. Our key insight for mitigating this risk is to limit the sensitivity of the watermarking models to the inputs, thereby resisting re-embedding of new watermarks. To achieve this, we propose a self-aware deep watermarking framework that extends Lipschitz constraints to the watermarking process, regulating encoder–decoder sensitivity in a principled manner. In addition, the framework incorporates re-watermarking adversarial training, which further constrains sensitivity to distortions arising from re-embedding. The proposed method provides theoretical bounds on message recoverability under malicious encoder based re-watermarking and demonstrates strong empirical robustness against diverse scenarios of re-watermarking attempts. Moreover, it maintains high visual fidelity and demonstrates competitive robustness against common image processing distortions compared to state-of-the-art watermarking methods. This work establishes a robust defense against both standard distortions and self-re-watermarking attacks. Code available at https://github.com/SVithurabiman/SRW.

Computer Vision · Vision Models & Multimodal

Keliang Li, Hongze Shen, Hao Shi, RuiBing Hou, Hong Chang, Jie Huang, Chenghao Jia, Wen Wang, Yiling Wu, Dongmei Jiang 等

The aspiration for artificial general intelligence, fueled by the rapid progress of multimodal understanding, demands models to understand humans in diverse and complex scenarios, as humans manifests intelligence and embody the world. We propose HumanPCR, an evaluation suite for probing MLLMs’ capacity in human-centric visual contexts across three hierarchical levels: Perception, Comprehension, and Reasoning (denoted by Human-P, Human-C, and Human-R, respectively). Human-P and Human-C consist of over 6,000 multiple-choice questions evaluating 34 fine-grained tasks covering 9 essential dimensions. Human-R presents a manually curated challenging video reasoning test that requires integrating multiple visual evidence, proactively extracting implicit context beyond question cues, and applying human-like expertise. Each question includes human-annotated Chain-of-Thought (CoT) rationales with key visual evidence to support further research. Extensive evaluations on over 30 state-of-the-art models exhibit significant challenges in human-centric visual understanding, particularly in tasks involving detailed space perception, temporal understanding, and mind modeling. The analysis of Human-R further exposes a critical failure in reasoning: models struggle to proactively gather necessary visual evidence, instead showing a faulty reliance on query-prompted cues, with advanced techniques offering only marginal gains. We hope HumanPCR and our findings will advance the development, evaluation, and human-centric applications of multimodal models.

Theory · Optimization

Shuichiro Haruta, Kazunori Matsumoto, Zhi Li, Yanan Wang, Mori Kurokawa

In this paper, we propose a rotation-constrained compensation method to address the errors introduced by structured pruning of large language models (LLMs). LLMs are trained on massive datasets and accumulate rich semantic knowledge in their representation space. In contrast, pruning is typically carried out with only a small amount of calibration data, which makes output mismatches unavoidable. Although direct least-squares fitting can reduce such errors, it tends to overfit to the limited calibration set, destructively modifying pretrained weights. To overcome this difficulty, we update the pruned parameters under a rotation constraint. This constrained update preserves the geometry of output representations (i.e., norms and inner products) and simultaneously re-aligns the pruned subspace with the original outputs. Furthermore, in rotation-constrained compensation, removing components that strongly contribute to the principal directions of the output makes error recovery difficult. Since input dimensions with large variance strongly affect these principal directions, we design a variance-aware importance score that ensures such dimensions are preferentially kept in the pruned model. By combining this scoring rule with rotation-constrained updates, the proposed method effectively compensates errors while retaining the components likely to be more important in a geometry-preserving manner. In the experiments, we apply the proposed method to Llama-7B and Llama-2-13B, and evaluate it on WikiText2 and multiple language understanding benchmarks. The results demonstrate consistently better perplexity and task accuracy compared with existing baselines.

Computer Vision · Vision Models & Multimodal

Hairui Ren, Zixuan Wang, Yibo Yang, He Zhao, Fan Tang, Dandan Guo, Yi Chang

Large Vision-Language Models (LVLMs) achieve impressive multimodal reasoning but remain prone to hallucinations, generating content inconsistent with visual evidence. Existing mitigation methods often rely on auxiliary modules or coarse decoding-time adjustments, overlooking the fine-grained dynamics that distinguish truthful (real) tokens from hallucinatory ones. In this paper, we introduce \textbf{AGE (Attention-aware Truth-Guided Enhancement)}, a training-free framework that performs fine-grained, layer-wise interventions guided by attention patterns of real tokens. Our analysis reveals that real and hallucinated tokens follow distinct stage-specific attention behaviors, and hallucinations emerge when models fail to reproduce these behaviors. AGE addresses this by introducing two lightweight interventions: (i) Imitating the image attention, derived from discrepancies between real and hallucinated tokens, and (ii) Imitating the text attention when semantic grounding is required. Extensive experiments on widely used benchmarks, including COCO Image Captioning, POPE, and MME, demonstrate that AGE consistently mitigates hallucinations across diverse LVLMs such as LLaVA, MiniGPT-4, and mPLUG-Owl2, without additional training or loss of fluency. Our results highlight that imitating truth-grounded attention dynamics is a simple yet powerful principle to improve the reliability of LVLMs.