论文检索

Reinforcement Learning · Multi-agent

Guanghao Li, lei yuan, Ruiqi Xue, Hengchang Zhang, Jianhong Wang, Yi-Chen Li, Yang Yu

Parameter sharing is a widely used technique in Multi-Agent Reinforcement Learning (MARL) that enhances sample efficiency by equipping agents with a unified policy. While effective in homogeneous settings, it often struggles in heterogeneous environments where agents possess diverse capabilities. Conversely, learning customized policies for agents can resolve knowledge conflicts but significantly hinders knowledge transfer, thereby reducing learning efficiency. Existing approaches attempt to balance this trade-off using clustering or agent-specific masks, but they typically rely on strong environment-specific priors and struggle in settings where the team exhibits multi-modal policies. To address these limitations, we propose Dspic, an efficient shared-policy algorithm grounded in the maximum entropy framework. Specifically, Dspic employs self-supervised learning to extract discriminative role embeddings for each agent. These embeddings guide a complete division of the observation space, providing a theoretical guarantee for the optimality of parameter sharing. Furthermore, to handle the increased observation complexity and diversity resulting from this division, Dspic incorporates a diffusion policy, enhancing the capacity to model complex action distributions while enabling efficient learning. Extensive experiments on MaMuJoCo, SMAC, SMACv2, and LBF demonstrate that Dspic achieves superior sample efficiency while maintaining asymptotic optimality.

Optimization · Large Scale, Parallel and Distributed

Andrej Jovanović, Alex Iacob, Mher Safaryan, Ionut-Vlad Modoranu, Lorenzo Sani, Shen, Xinchi Qiu, Dan Alistarh, Nicholas Lane

Distributed training of foundation models via $\texttt{DDP}$ is limited by interconnect bandwidth. While infrequent communication strategies reduce synchronization frequency, they remain bottlenecked by the memory and communication requirements of optimizer states. Low-rank optimizers can alleviate these constraints; however, in the local-update regime, workers lack access to the full-batch gradients required to compute low-rank projections, which degrades performance. We propose $\texttt{LoRDO}$, a principled framework unifying low-rank optimization with infrequent synchronization. We first demonstrate that, while global projections based on pseudo-gradients are theoretically superior, they permanently restrict the optimization trajectory to a low-rank subspace. To restore subspace exploration, we introduce a full-rank quasi-hyperbolic update. $\texttt{LoRDO}$ achieves near-parity with low-rank $\texttt{DDP}$ in language modeling and downstream tasks at model scales of $125$M--$720$M, while reducing communication by $\approx10\times$. Finally, we show that $\texttt{LoRDO}$ improves performance even more in very low-memory settings with small rank/batch size.

Theory · Game Theory

Philip Jordan, Maryam Kamgarpour

We study the existence and computation of Nash equilibria in concave games where the players' admissible strategies are subject to shared coupling constraints. Under playerwise concavity of constraints, we prove existence of Nash equilibria. Our proof leverages topological fixed point theory and novel structural insights into the contractibility of feasible sets, and relaxes strong assumptions for existence in prior work. Having established existence, we address the question of whether in the presence of coupling constraints, playerwise independent learning dynamics have convergence guarantees. We address this positively for the class of potential games by designing a convergent algorithm. To account for the possibly nonconvex feasible region, we employ a log barrier regularized gradient ascent with adaptive stepsizes. Starting from an initial feasible strategy profile and under exact gradient feedback, the proposed method converges to an $\epsilon$-approximate constrained Nash equilibrium within $\mathcal{O}(\epsilon^{-3})$ iterations.

Social Aspects · Security

Xiaozuo Shen, Yifei Cai, RUI NING, Chunsheng Xin, Hongyi "Michael" Wu

The widespread adoption of Vision Transformers (ViTs) elevates supply-chain risk on third-party model hubs, where an adversary can implant backdoors into released checkpoints. Existing ViT backdoor attacks largely rely on poisoned-data training, while prior data-free attempts typically require synthetic-data fine-tuning or extra model components. This paper introduces Data-Free Logic-Gated Backdoor Attacks (DF-LoGiT), a truly data-free backdoor attack on ViTs via direct weight editing. DF-LoGiT exploits ViT’s native multi-head architecture to realize a logic-gated compositional trigger, enabling a stealthy and effective backdoor. We validate its effectiveness through theoretical analysis and extensive experiments, showing that DF-LoGiT achieves near-100% attack success with negligible degradation in benign accuracy and remains robust against representative classical and ViT-specific defenses.

Ionut-Vlad Modoranu, Philip Zmushko, Erik Schultheis, Mher Safaryan, Dan Alistarh

Shampoo is one of the leading approximate second-order optimizers: a variant of it has won the MLCommons AlgoPerf competition, and it has been shown to produce models with lower activation outliers that are easier to compress. Yet, applying Shampoo currently comes at the cost of significant computational slowdown, due to its expensive internal operations. In this paper, we take a significant step to address this shortcoming by proposing \method (for Distributed Accelerated SHampoo), a faster implementation of Distributed Shampoo based on two main new techniques: First, we show that preconditioner blocks can be stacked into 3D tensors to significantly improve GPU utilization; second, we introduce the Newton-DB iteration and the Chebyshev polynomial approximations as novel and faster approaches for computing the inverse matrix roots required by Shampoo. Along with these algorithmic contributions, we provide a first in-depth analysis of how matrix scaling critically affects Shampoo convergence. On the practical side, our GPU-aware implementation achieves up to $4.83\times$ faster optimizer steps compared to the well-optimized Distributed Shampoo, while Newton-DB attains the lowest validation perplexity per iteration among all tested methods.

Reinforcement Learning · Deep RL

Mahsa Bastankhah, Sophie Broderick, Benjamin Eysenbach

In many practical reinforcement learning (RL) environments, observations are far higher-dimensional than the variables that matter for control. In this work, we ask: can we learn representations that capture only control-relevant features of the environment? We study this question through the \emph{empowerment} objective, which maximizes an agent’s influence over the environment and is widely used for unsupervised skill learning. We show that empowerment agents induce two distinct representations --- forward and backward --- that capture complementary aspects of the state, and both of which are invariant to control-irrelevant features. Thus, empowerment maximization leads agents to learn an implicit, \emph{control-centric} model of the world. Our analysis highlights the importance of learning representations through interaction rather than from passive datasets: interaction aimed at maximizing control is essential for learning useful invariance properties, a perspective that aligns closely with the causal learning literature.

Deep Learning · Large Language Models

Parth Asawa, Alan Zhu, Abigail O'Neill, Matei Zaharia, Alex Dimakis, Joseph E Gonzalez

Frontier language models are deployed as black-box services, where model weights cannot be modified and customization is limited to prompting. We introduce Advisor Models, a method to train small open-weight models to generate dynamic, per-instance natural language advice that improves the capabilities of black-box frontier models. Advisor Models improve GPT-5's performance on RuleArena (Taxes) by 71\%, reduce Gemini 3 Pro's steps taken in SWE agent tasks by 24.6\%, and outperform static prompt optimizers in personalizing GPT-5 to user preferences (85-100\% vs. 40-60\%). We also find that advisors are transferable: an advisor trained with a low-cost student model still transfers improvements to a frontier model. Moreover, Advisor Models are robust: we observe no degradation on other benchmarks than the pipeline is trained on. Our method shows how to perform parametric optimization for black-box frontier models in a practical and cost-effective way.

Deep Learning · Large Language Models

Yang Yue, Xuancheng Zhu, YuYang Ma, Guoshun Nan, Zihan Dou, JingRu Shan, Congyu Guo, Ji Zhang, Hua Wang, Jingfeng Zhang

The automated design of agentic systems offers a promising pathway for scaling large language models (LLMs) beyond single-agent reasoning. While prior work has advanced task performance through handcrafted or automatically generated multi-agent workflows, robustness is often treated as an afterthought, leaving systems vulnerable to external adversaries and internal failures. We propose AutoRAS, a framework for the Automated design of Robust Agentic Systems. AutoRAS formulates system design as generating a sequence of symbolic primitives that jointly encode structural connectivity and behavioral actions, and learns to optimize this sequence using execution-derived safety signals and flow-based sequence-level objectives. Extensive experiments show that AutoRAS achieves the best performance in both vanilla and adversarial settings, with the smallest performance degradation under attacks. Further analyses demonstrate strong transferability, stable optimization behavior, stability across primitive sets, and favorable cost trade-offs. Our code is available at [this link](https://anonymous.4open.science/r/AutoRAS-56C8/).

Applications · Computer Vision

Chengyu Zheng, Songlin Yang, Jin Huang, Honghua Chen, Weiming Wang, Haoran Xie, Fu Lee Wang, Mingqiang Wei

Point cloud registration can be categorized into rigid and non-rigid settings depending on the motion characteristics of the underlying objects. Rigid alignment assumes a single global transformation under which corresponding points remain geometrically consistent across scales, whereas non-rigid alignment involves spatially varying deformations, where geometric similarity holds only locally and semantic correspondence dominates at larger scales. This multi-scale discrepancy creates an optimization gap that has made unified registration particularly challenging. To this end, we propose RGGT, a Generative-Prior-Guided Transformer that unifies rigid and non-rigid registration within a shared optimization space. Through coordinated design at the representation, architecture, and supervision levels, RGGT jointly captures local geometric details and global structural semantics: generative priors enrich point features with unified geometric–semantic cues; a Global–Self–Cross Attention module models long-range structure, local interaction, and bidirectional cross-shape reasoning; and a dual correspondence–reconstruction objective provides consistent supervision for both deformation types. Extensive experiments on rigid (ModelNet40) and non-rigid (4DMatch) benchmarks demonstrate that RGGT achieves state-of-the-art accuracy across both rigid and non-rigid settings within a single unified framework.

Deep Learning · Generative Models and Autoencoders

Marta Aparicio Rodriguez, Anastasia Borovykh, Grigorios A Pavliotis, Daniel Korchinski

Generative models have a persistent limitation: their tendency to memorize training data can create legal liabilities and erode creative diversity. Understanding which samples are memorized in whole or in part, and under what conditions, therefore remains an important open problem. Here we answer the question "Are atypical or rare samples memorized first?" in the negative. We train diffusion models on strings generated according to the production rules of the Random Hierarchy Model (RHM), and find that samples composed of *common substrings* are preferentially memorized. This holds true even if the training data consists of entirely unique samples, indicating that deduplication at the data point level does not provide a meaningful privacy guarantee. Correspondingly we predict, then observe, delayed memorization for fat-tailed datasets (i.e., those with more atypical samples). This effect is amplified when fat-tails are introduced into high-level production rules. These together suggest that *dataset diversity*, particularly at higher levels of abstraction, plays an important role in staving off memorization. Finally, we identify an intermediate regime of partial memorization in which common substrings are learned first and subsequently overproduced during generation. If training is stopped in this regime, models will exhibit the reversion-to-the-mean blandness often derided as "slop".

Deep Learning · Large Language Models

Xiandong Zou, Jianshu Li, Jing Huang, Pan Zhou

Speculative decoding accelerates inference for (M)LLMs, yet a training-decoding discrepancy persists: while existing methods optimize single greedy trajectories, decoding involves verifying and ranking multiple sampled draft paths. We propose *Variational Speculative Decoding* (VSD), formulating draft training as variational inference over latent proposals (draft paths). VSD maximizes the marginal probability of target-model acceptance, yielding an ELBO that promotes high-quality latent proposals while minimizing divergence from the target distribution. To enhance quality and reduce variance, we incorporate a path-level utility and optimize via an Expectation-Maximization procedure. The E-step draws MCMC samples from an oracle-filtered posterior, while the M-step maximizes weighted likelihood using Adaptive Rejection Weighting (ARW) and Confidence-Aware Regularization (CAR). Theoretical analysis confirms that VSD increases expected acceptance length and speedup. Extensive experiments across LLMs and MLLMs show that VSD achieves up to a 9.58\% speedup over EAGLE-3 and 8.80\% over ViSpec, significantly improving decoding efficiency.

Javier Porras-Valenzuela, Samar Hadou, Alejandro Ribeiro

We introduce a constrained optimization framework for training transformers that behave like optimization descent algorithms. Specifically, we enforce layerwise descent constraints on the objective function and replace standard empirical risk minimization (ERM) with a primal-dual training scheme. This approach yields models whose intermediate representations decrease the loss monotonically in expectation across layers. We apply our method to both unrolled transformer architectures and conventional pretrained transformers on tasks of video denoising and text classification. Across these settings, we observe that constrained transformers achieve stronger robustness to perturbations and maintain higher out-of-distribution generalization, while preserving competitive in-distribution performance.

Reinforcement Learning · Deep RL

Jiafei Lyu, Zichuan Lin, Scott Fujimoto, Kai Yang, Yangkun Chen, Saiyong Yang, Zongqing Lu, Deheng Ye

Model-based representations recently stand out as a promising framework that embeds latent dynamics information into the representations for downstream off-policy actor-critic learning. It implicitly combines the advantages of both model-free and model-based approaches while avoiding the training costs associated with model-based methods. Nevertheless, existing model-based representation methods can fail to capture sufficient information about relevant variables and can overfit to early experiences in the replay buffer. These incur biases in representation and actor-critic learning, leading to inferior performance. To address this, we propose Debiased model-based Representations for Q-learning, tagged DR.Q algorithm. DR.Q explicitly maximizes the mutual information between the representations of the current state-action pair and the next state besides minimizing their deviations, and samples transitions with faded prioritized experience replay. We evaluate DR.Q on numerous continuous control benchmarks with a single set of hyperparameters, and the results demonstrate that DR.Q can match or surpass recent strong baselines, sometimes outperforming them by a large margin.

Deep Learning · Large Language Models

Yiqun Yao, Xiang Li, Xin Jiang, Xuezhi Fang, Naitong Yu, Siwei Dong, Wenjia Ma, Jing Li, Aixin Sun, Yequan Wang

It is widely recognized that, after generative pre-training, Transformer FeedForward layers implicitly function as semantic memory, encoding linguistic and factual knowledge, while the contexts in key–value (KV) cache contain raw events, serving as the source of models' episodic memory. In this work, we show that a same group of Transformer FeedForward-layer parameters can both be semantic and episodic memory, which is retrievable without explicitly attending to the related KV cache. To realize this idea, we introduce Hypermem, a hypernetwork that recurrently maps contexts into targeted updates of FeedForward parameters. We post-train the hypernetwork using continuation and random-access associative memory objectives, eliminating the need for test-time training. Extensive experiments demonstrate that our approach outperforms related methods, including MemoryLLM and generative adapter, on memory retrieval, long-context question answering, and personalization benchmarks, establishing a new state of the art for hypernetwork-based memory mechanisms. Our results suggest that directly bridging data and parameters provides a viable direction for exploring next-generation foundation models with more flexible and persistent memory capabilities.

Deep Learning · Generative Models and Autoencoders

Boyang Zhang, Zhiguo Wang, Ya-Feng Liu

Score-based diffusion models demonstrate superior performance in generative tasks but encounter fundamental bottlenecks in inverse problems due to the analytical intractability of the time-dependent likelihood score. To bridge this gap, we propose a novel proximal-based generative modeling (PGM) framework that rigorously circumvents explicit likelihood evaluation. Our framework is built upon a theoretical equivalence between Gaussian convolution in diffusion processes and Moreau-Yosida regularization in nonsmooth optimization. This enables a new sampling mechanism driven by the proposed Moreau score, which admits a closed-form expression via proximal operators. Moreover, we introduce Moreau score matching to learn the proximal operators that rely solely on samples drawn from the prior distribution. Theoretically, PGM eliminates the early-stopping bias inherent in the score-based diffusion model and achieves non-asymptotic convergence. Experiments demonstrate that PGM significantly surpasses state-of-the-art methods in reconstruction quality and sampling time.

Theory · Deep Learning

Yuxuan Zhao, Yulong Lu

We study the posterior contraction rate of Bayesian Physics-Informed Neural Networks (PINNs) for solving a general class of elliptic partial differential equations (PDEs). We focus on learning of the elliptic equation with a non-homogeneous Dirichlet boundary condition from independent and noisy measurements collected both inside the domain and on the boundary. Assuming that the PDE admits a strong solution in a Hölder space and using with a suitably constructed prior on the neural network weights, we prove that the posterior distribution concentrates around the exact solution at a near-minimax rate. Furthermore, the chosen prior is *rate-adaptive*: the posterior contracts at an (almost) optimal rate without prior knowledge of the smoothness level of the exact solution. Our results provide statistical guarantees for uncertainty quantification of PDEs via Bayesian PINNs.

Suyuan Liu, Shengfei Wei, Wenjing Yang, Shengju Yu, Siwei Wang, Xueqiong Li, Wenpeng Lu, Xinwang Liu

Existing fair multi-view clustering methods typically suffer from a severe trade-off between clustering utility and fairness, while incurring prohibitive quadratic complexity on large-scale datasets. To address these challenges, we propose Causal Disentangled Anchor Learning (CDAL), a novel framework that achieves scalable fairness via structural disentanglement. Guided by a structural causal model perspective, CDAL utilizes a dual-anchor mechanism to structurally separate latent representations into orthogonal semantic and sensitive subspaces. We further ensure statistical independence through a linearized Hilbert-Schmidt Independence Criterion (HSIC) constraint, which is optimized via an efficient alternating scheme. Theoretically, we prove the identifiability of the disentangled factors and guarantee the algorithm's global convergence and linear time complexity $\mathcal{O}(n)$. Extensive experiments on large-scale benchmarks demonstrate that CDAL outperforms state-of-the-art methods, achieving a superior utility-fairness trade-off.

General Machine Learning · Representation Learning

Haokun Liu, Zezhong Ding, Xike Xie

Graph foundation models (GFMs), pretrained on massive graph data, have transformed graph machine learning by supporting general-purpose reasoning across diverse graph tasks and domains. Existing GFMs pretrained with fixed-hop subgraph sampling impose a fixed receptive field, causing scale mismatch on diverse tasks, which often require heterogeneous and unknown structural contexts beyond a fixed sampling scale. We propose **R-GFM**, a Riemannian Graph-of-Graphs (GoG) based foundation model, that treats *structural scale* as a first-class citizen in modeling. R-GFM constructs a multi-scale GoG over-sampled subgraphs at different hop distances and learns geometry-adaptive representations from Riemannian manifolds. Theoretical analysis shows that R-GFM reduces structural domain generalization error compared to fixed-scale GFMs. Experiments on various datasets demonstrate that R-GFM achieves state-of-the-art performance, with up to a **49\%** improvement on downstream tasks.

General Machine Learning · Representation Learning

Ellina Zhang, Madhavan Iyengar, Amir Zadeh, Chuan Li, David Held, Deepak Pathak, Tal Daniel

We introduce 3D-DLP, a self-supervised object-centric representation learning model that decomposes scene-level RGB-D or voxel observations into a set of 3D latent particles. Building on the Deep Latent Particles (DLP) framework, each particle encodes disentangled attributes, including 3D keypoint position, bounding box dimensions, and appearance features, and represents a distinct entity in the scene. The model learns interpretable per-particle segmentation maps through an end-to-end self-supervised reconstruction objective. We demonstrate on both simulated and real-world datasets that the learned latent space is interpretable and controllable: by manipulating particle positions and decoding, we can generate novel scene configurations. Furthermore, we show that leveraging these compact 3D latent particles for downstream robotic manipulation improves performance over baselines that either lack explicit 3D information or rely on memory-intensive dense 3D inputs without object-centric structure. Open-source code will be made publicly available. Video results are available on the project website: https://sites.google.com/view/3d-dlp/home

Deep Learning · Sequential Models, Time series

Ruichao Guo, Xingyao Han, Wenshui Luo, Zhe Liu, Chen Gong, Hesheng Wang

Point forecasting for graph-structured multivariate time series is a fundamental problem, but rigorous uncertainty quantification for such predictions is still underexplored. Conformal prediction (CP) offers uncertainty estimation with a solid coverage guarantee under the exchangeability assumption, which requires the joint data distribution to be unchanged under permutation. However, in graph-structured time series, inherent cross-node coupling can violate the exchangeability condition, making direct application of CP unreliable. Inspired by the spectral graph theory, such coupling resides in global trends and can be characterized by the low-frequency components, while high-frequency components are nearly exchangeable. Therefore, we propose a novel concept named **S**pectral **G**raph **C**onditional **E**xchangeability (SGCE), which conditions exchangeable high-frequency components on low-frequency ones to preserve global trends and enable effective CP in the spectral domain. Based on SGCE, we further propose **S**pectral **C**onformal prediction via w**A**ve**LE**t transform (SCALE). SCALE uses graph wavelets to decompose low/high-frequency components and conformalizes high-frequency residuals via adaptive gating over a low-frequency embedding. Experimental results on real-world traffic datasets show that SCALE not only achieves valid coverage but also consistently improves the coverage-efficiency trade-off over the state-of-the-art CP methods.