论文检索

Deep Learning · Theory

Zhiwei Bai, Jiajie Zhao, Zhangchen Zhou, Zhi-Qin John Xu, Yaoyu Zhang

Adam is a widely used optimization algorithm in deep learning, yet the specific class of objective functions where it exhibits inherent advantages remains underexplored. Unlike prior studies requiring external schedulers and $\beta_2$ near 1 for convergence, this work investigates the ``natural'' auto-convergence properties of Adam. We identify a class of highly degenerate polynomials where Adam converges automatically without additional schedulers. Specifically, we derive theoretical conditions for local asymptotic stability on degenerate polynomials and demonstrate strong alignment between theoretical bounds and experimental results. We prove that Adam achieves local linear convergence on these degenerate functions, significantly outperforming the sub-linear convergence of Gradient Descent and Momentum. This acceleration stems from a decoupling mechanism between the second moment $v_t$ and squared gradient $g_t^2$, which exponentially amplifies the effective learning rate. Finally, we characterize Adam's hyperparameter phase diagram, identifying three distinct behavioral regimes: stable convergence, spikes, and SignGD-like oscillation.

General Machine Learning · Evaluation

Yuheng Jing, Kai Li, Jiajun Zhang, Zeyao Ma, Jiaxi Yang, Lei Zhang, zhe wu, Jinmin He, Junliang Xing, Jian Cheng

In-Context Reinforcement Learning (ICRL) has enabled foundation agents to adapt instantaneously to novel tasks, yet its efficacy in Ad-Hoc Teamwork (AHT)—where coordination with unknown partners is required—remains unexplored. To rigorously evaluate this, we introduce a large-scale benchmark **ICRL4AHT**, built upon a high-throughput JAX implementation of Overcooked-V2. Our benchmark includes a large, diverse teammate suite spanning both RL and heuristic policies, enabling controlled train-test shifts, and provides an end-to-end pipeline to generate learning histories, serialize them into reproducible datasets, and perform online multi-episode evaluation. We evaluate state-of-the-art ICRL algorithms, including Algorithm Distillation (AD) and Decision-Pretrained Transformer (DPT), across millions of transitions. Results reveal startling limitations: contrary to their success in single-agent domains, current ICRL architectures fail to exhibit test-time adaptation in multi-agent settings. Specifically, these methods frequently underperform random baselines across both unseen teammate and unseen layout tracks, with no observable in-context improvement over long horizons. These findings highlight the fundamental challenges of strategic inference under partial observability, establishing our benchmark as a critical testbed for next-generation coordination algorithms. Our repository is available at https://anonymous.4open.science/r/ICRL4AHT.

Optimization · Large Scale, Parallel and Distributed

Guang Yang, Bo Pan, Chengdi Lian, Xingcai Zhou, Linglong Kong, Yafei Wang, Bei Jiang

Federated Quantile Regression (FQR) has emerged as a powerful modelling paradigm for estimating conditional quantiles, offering a more comprehensive understanding of response distributions than standard conditional mean regression. However, achieving communication efficiency and optimal statistical guarantees for FQR remains challenging, particularly due to the nonsmooth nature of quantile loss functions and the presence of heterogeneously structured data, where each local agent trains its conditional quantile models with distinct sets of features. In this paper, we propose a data-driven, one-shot weighted ensemble estimator for FQR that incorporates scalable weighting schemes to effectively leverage the partially observed features at each local agent, thereby enjoying both communication efficiency and estimation optimality. Theoretically, we present a unified analysis of the proposed learning procedure, establishing that the resulting estimator exhibits asymptotic normality and attains uniformly minimum variance. Furthermore, we investigate the estimator's sensitivity to perturbations introduced by local agents and derive conditions under which the estimator achieves stability and enjoys strong out-of-sample generalization. Extensive simulations and real data analysis under various scenarios validate the asymptotic normality of our estimator and demonstrate its superior estimation accuracy and uniform convergence compared to several baseline methods across a range of quantile levels.

Deep Learning · Theory

Zhiwei Bai, Zhangchen Zhou, Jiajie Zhao, Xiaolong Li, Zhiyu li, Feiyu Xiong, Hongkang Yang, Yaoyu Zhang, Zhi-Qin John Xu

Loss spikes commonly emerge during neural network training with the Adam optimizer across diverse architectures and scales, yet their underlying mechanism remains elusive. While previous explanations attribute these phenomena to sharper loss landscapes at lower loss, we show that landscape geometry alone is insufficient to explain the phenomenon. In this work, we pinpoint the root cause in the internal dynamics of Adam's second moment estimator. We identify a critical ``decoupling'' mechanism where the adaptive preconditioner $v_t$ fails to track the instantaneous squared gradients $g_t^2$, causing the adaptive mechanism to effectively fail. This decoupling allows the preconditioner to decay autonomously despite rising gradients, which pushes the maximum eigenvalue of the preconditioned Hessian beyond the stability threshold $2/\eta$ for sustained periods, manifesting as dramatic loss spikes. Through a quadratic approximation analysis, we theoretically and experimentally characterize five distinct stages of spike evolution and propose a predictor for anticipating spikes based on gradient-directional curvature. We empirically find that the proposed loss spike mechanism, although derived from simplified models, generalizes well to practical scenarios ranging from small neural networks to large-scale Transformers.

Jiajun Zhang, Yuheng Jing, Zeyu Cui, Hao Zheng, Wentao Chen, Kaixin LI, Jiaxi Yang, Tianbao Xie, Zeyao Ma, Tianyi Bai 等

The rapid evolution of Large Language Models (LLMs) has empowered even non-programmers to create visually appealing frontend mini-games with a single instruction. However, open-source models significantly lag behind proprietary counterparts in this domain. The core bottleneck is the lack of an evaluation mechanism that balances reliability with scalability, as existing methods either fail to verify dynamic interactivity or incur prohibitive computational costs. To bridge this gap, we introduce ALIVE (Aligning LLMs via Interactive Visual Execution), a high-throughput framework that leverages one-shot planning and DOM-based analysis to automatically evaluate generated games at scale. Extensive experiments demonstrate that ALIVE significantly outperforms static judge baselines in identifying functional flaws while remaining orders of magnitude more efficient than GUI agents. Functioning as a scalable `pre-flight' evaluation layer, it curates high-quality data for Supervised Fine-Tuning (SFT) and provides a consistent reward signal for Reinforcement Learning (RL). We leverage this pipeline to train ALIVE-Coder, a model achieving superior performance in interactive frontend generation. To the best of our knowledge, our work offers the first scalable path to evaluate and optimize interactive code, substantially advancing open-source capabilities.

Jiajun Zhang, Jianke Zhang, Zeyu Cui, Jiaxi Yang, Lei Zhang, Zilei Wang, Qiang Liu, Liang Wang, Binyuan Hui, Junyang Lin

Recent Large Language Models (LLMs) have demonstrated remarkable proficiency in code generation. However, their ability to create complex visualizations for scaled and structured data remains largely unevaluated and underdeveloped. To address this gap, we introduce **PlotCraft**, a new benchmark featuring 1k challenging visualization tasks that cover a wide range of topics, such as finance, scientific research, and sociology. The benchmark is structured around seven high-level visualization tasks and encompasses 48 distinct chart types. Crucially, it is the first to systematically evaluate both single-turn generation and multi-turn refinement across a diverse spectrum of task complexities. Our comprehensive evaluation of 23 leading LLMs on PlotCraft reveals obvious performance deficiencies in handling sophisticated visualization tasks. To bridge this performance gap, we develope **SynthVis-30K**, a large-scale, high-quality dataset of complex visualization code synthesized via a collaborative agent framework. Building upon this dataset, we develope **PlotCraftor**, a novel code generation model that achieves strong capabilities in complex data visualization with a remarkably small size. Across VisEval, PandasPlotBench, and our proposed PlotCraft, PlotCraftor shows performance comparable to that of leading proprietary approaches. Especially, on hard task, Our model achieves over 50\% performance improvement. We will release the benchmark, dataset, and code at \href{https://anonymous.4open.science/r/PlotCraft-E320}{PlotCraft anonymous repository}.

Social Aspects · Privacy

Moshe Shenfeld, Vitaly Feldman

We consider the privacy amplification properties of a sampling scheme in which a user’s data is used in $k$ steps chosen randomly and uniformly from a sequence (or set) of $t$ steps. This sampling scheme has been recently applied in the context of differentially private optimization [Chua et al., 2024a, Choquette-Choo et al., 2025] and communication-efficient high-dimensional private aggregation [Asi et al., 2025], where it was shown to have utility advantages over the standard Poisson sampling. Theoretical analyses of this sampling scheme [Feldman and Shenfeld, 2025, Dong et al., 2025] lead to bounds that are close to those of Poisson sampling, yet still have two significant shortcomings. First, in many practical settings, the resulting privacy parameters are not tight due to the approximation steps in the analysis. Second, the computed parameters are either the hockey stick or Rényi divergence, both of which introduce overheads when used in privacy loss accounting. In this work, we demonstrate that the privacy loss distribution (PLD) of random allocation applied to any differentially private algorithm can be computed efficiently. When applied to the Gaussian mechanism, our results demonstrate that the privacy-utility trade-off for random allocation is at least as good as that of Poisson subsampling. In particular, random allocation is better suited for training via DP-SGD. To support these computations, our work develops new tools for general privacy loss accounting based on a notion of PLD realization. This notion allows us to extend accurate privacy loss accounting to subsampling which previously required manual noise-mechanism-specific analysis.

General Machine Learning · Representation Learning

Zian Zhai, Fan Li, Xingyu Tan, Xiaoyang Wang, Wenjie Zhang

Vector Quantization (VQ) has recently emerged as a promising approach for learning discrete representations of graph-structured data. However, a fundamental challenge, i.e., codebook collapse, remains underexplored in the graph domain, significantly limiting the expressiveness and generalization of graph tokens. In this paper, we present the first empirical study and observe that codebook collapse consistently occurs when applying VQ to graph data, even with mitigation strategies proposed in vision or language domains. Moreover, we provide a diagnosis of collapse from data and optimization perspectives, showing that collapse is associated with graph data properties such as feature redundancy and connectivity density, and is further reinforced by the training dynamics of deterministic hard assignment. To address these issues, we propose RGVQ, a novel framework that integrates graph topology and feature similarity as explicit regularization signals to enhance codebook utilization and promote token diversity. RGVQ introduces soft assignments via Gumbel-Softmax reparameterization, ensuring that all codewords receive gradient updates. In addition, RGVQ incorporates a structure-aware contrastive regularization to penalize assigning the same token to dissimilar node pairs. Extensive experiments demonstrate that RGVQ substantially improves codebook utilization and consistently boosts the performance of state-of-the-art graph VQ backbones across multiple downstream tasks, enabling more expressive and transferable graph token representations.

General Machine Learning · Representation Learning

Sheir A. Zaheer, Alexander Holston, Chan Youn Park

In this paper, we propose a discrete roto-reflection group equivariant vision transformer with convolutional attention. Roto-reflection equivariant networks preserve the rotational, flip and positional symmetry in feature maps, making them useful for tasks where orientation of the inputs is relevant to the model outputs. In image classification and object detection, most of the studies on roto-reflection equivariant models have focused on using convolutional neural networks rather than vision transformers. In this paper, we examine the challenges involved in achieving equivariance in vision transformers, and we propose a simpler way to implement a discretized roto-reflection group equivariant vision transformer. The experimental results demonstrate that our approach outperforms the existing approaches for developing discrete roto-reflection group equivariant neural networks for image classification.

General Machine Learning · Everything Else

Liangwei Zheng, Wei Emma Zhang, Mingyu Guo, Olaf Maennel, Weitong Chen

Effectively managing missing modalities is a fundamental challenge in real-world multimodal learning scenarios, where data incompleteness often results from systematic collection errors or sensor failures. Sparse Mixture-of-Experts (SMoE) architectures have the potential to naturally handle multimodal data, with individual experts specializing in different modalities. However, existing SMoE approach often lacks proper ability to handle missing modality, leading to performance degradation and poor generalization in real-world applications. We propose ConfSMoE to introduce a two-stage imputation module to handle the missing modality problem for the SMoE architecture by taking the opinion of experts and reveal the insight of expert collapse from theoretical analysis with strong empirical evidence. Inspired by our theoretical analysis, ConfSMoE propose a novel expert gating mechanism by detaching the softmax routing score to task confidence score w.r.t ground truth signal. This naturally relieves expert collapse without introducing additional load balance loss function. We show that the insights of expert collapse aligns with other gating mechanism such as Gaussian and Laplacian gate. The proposed method is evaluated on four different real world dataset with three distinct experiment settings to conduct comprehensive analysis of ConfSMoE on resistance to missing modality and the impacts of proposed gating mechanism.

Deep Learning · Graph Neural Networks

Ofek Amran, Tom Gilat, Ron Levie

Generalization and approximation capabilities of message passing graph neural networks (MPNNs) are often studied by defining a compact metric on a space of input graphs under which MPNNs are Hölder continuous. Such analyses are of two varieties: 1) when the metric space includes graphs of unbounded sizes, the theory is only appropriate for dense graphs, and, 2) when studying sparse graphs, the metric space only includes graphs of uniformly bounded size. In this work, we present a unified approach, defining a compact metric on the space of graphs of all sizes, both sparse and dense, under which MPNNs are Hölder continuous. This leads to more powerful universal approximation theorems and generalization bounds than previous works. The theory is based on, and extends, a recent approach to graph limit theory called graphop analysis.

Applications · Language, Speech and Dialog

Haolin Yang, Jipeng Zhang, Zhitao He, Alexander Zhou, Yi Fung

Large Language Models (LLMs) often struggle with the precise logic and schema alignment required for complex Text-to-SQL tasks. While current methods rely heavily on static prompting, they lack the ability to dynamically adapt and self-correct through environmental interaction. To bridge this gap, we propose **MARS-SQL**, a multi-agent architecture that leverages interactive Reinforcement Learning (RL) to optimize SQL generation. Unlike monolithic approaches, our method decomposes the problem into three specialized roles: schema linking, query generation, and solution validation. Central to our approach is a generation agent trained via a multi-turn RL policy, which operates within a ReAct-style loop. This agent learns to iteratively reason, execute intermediate SQL actions on a live database, and refine its strategy based on execution feedback. To ensure robustness, we introduce a validation mechanism that treats solution selection as a generative modeling task, identifying the optimal interaction trajectory through next-token prediction probabilities. Empirical evaluations demonstrate the effectiveness of coupling interactive learning with trajectory ranking. **MARS-SQL** achieves state-of-the-art performance, recording an execution accuracy of 77.84\% on the BIRD development dataset and 89.75\% on the Spider test dataset.

Deep Learning · Large Language Models

Minghao Chen, Xinyi Hu, Zhou Yu, Yufei Yin

Large Language Model (LLM) based agents have demonstrated proficiency in multi-step interactions with graphical user interfaces (GUIs). While most research focuses on improving single-task performance, practical scenarios often involve repetitive GUI tasks for which invoking LLM reasoning repeatedly, i.e., the ReAct paradigm, is inefficient. Prior to LLMs, traditional Robotic Process Automation (RPA) offers runtime efficiency but demands significant manual effort to develop and maintain. To bridge this gap, we propose \textbf{AutoRPA}, a framework that automatically distills the decision logic of ReAct-style agents into robust RPA functions. AutoRPA introduces two core innovations: (1) A \textit{translator-builder pipeline} where a translator agent converts hard-coded ReAct actions into soft-coded procedures, and a builder agent synthesizes robust RPA functions via retrieval-augmented generation over multiple trajectories; (2) A \textit{hybrid repair strategy} during code verification, combining RPA execution with ReAct-based fallback for iterative refinement. Experiments across multiple GUI environments demonstrate that RPA functions generated by AutoRPA successfully solve similar tasks while reducing token usage by 82\%\textasciitilde96\%, significantly improving runtime efficiency and reusability.

Applications · Health / Medicine

Jingbo Yang, Yunfeng Zhao, Chao Qiu, Yulin Sun, Xiuyun Liu, Xiaofei Wang

Stereotactic electroencephalography (sEEG) provides temporally precise intracranial recordings but is inherently constrained by sparse and irregular spatial sampling due to clinical limitations on electrode implantation. Signal reconstruction under this setting aims to infer neural activity at unmonitored locations, potentially expanding the coverage of neural recordings without increasing the number of implanted electrodes. However, most existing sEEG reconstruction methods underutilize the spatial information of electrode contacts in both encoding and modeling, and rely on deterministic objectives that favor average patterns, leading to over-smoothed reconstructions. We propose EpiTwin, a conditional spatial graph transformer for sEEG signal reconstruction, comprising three key components. Hybrid Spatial Positional Encoding (HSPE) constructs explicit spatial identities from electrode coordinates, graph topology, and anatomical priors. Geometry–Functional Biased Attention (GFBA) incorporates geometric distance and data-driven functional similarity biases into attention computation. Adversarial Refinement Training employs a multi-scale discriminator to counter reconstruction over-smoothing. Experiments on real-world clinical sEEG data demonstrate that EpiTwin consistently achieves lower reconstruction error under electrode series-level masking, outperforming recent foundation models such as LaBraM with a 16.8\% relative reduction in RMSE. Furthermore, EpiTwin effectively mitigates spectral over-smoothing and improves reconstruction fidelity.

General Machine Learning · Transfer, Multitask and Meta-learning

Guodong Zheng, Enneng Yang, Xiaoyan Wang, Feihong He, Yihan Chen, Quan Zheng, Peng Wang, Li Shen

Continual learning (CL) seeks models that acquire new knowledge while avoiding catastrophic forgetting. However, many methods that mitigate forgetting constrain parameter updates and thereby reduce model plasticity. We revisit the singular value spectrum of gradients in representative CL methods and show that they commonly exhibit singular value collapse, where only a small subset of gradient directions drive parameter updates. Motivated by this observation, we propose \textbf{P}lasticity \textbf{A}ctivation via \textbf{P}olar \textbf{O}perator (PAPO), a plug-in that preserves the dominant directions that mitigate forgetting while activating previously suppressed directions to enhance plasticity. Concretely, PAPO modifies the gradient $\mathbf{G}$ as $\mathbf{G}\leftarrow \mathbf{G}+\lambda \cdot \operatorname{polar}(\mathbf{G})$, which uniformly increases near-zero singular values without changing the singular vectors. To avoid the cost of explicit singular value decomposition, we approximate the polar factor using the iteration-dependent Polar Express scheme, which relies only on matrix multiplications and additions. In our empirical evaluation on both vision and language benchmarks, incorporating PAPO yields consistent improvements. In particular, on MiniImageNet, integrating PAPO into ER, MAS, GPM and TRGP produces substantial accuracy gains of $9.01\%$, $4.76\%$, $8.90\%$ and $9.19\%$, respectively.

Deep Learning · Large Language Models

Chao Han, Yijuan Liang, Zihao Xuan, Daokuan Wu, Wei Zhang, Xiaoyu Shen

The deployment of large language models (LLMs) in real-world applications is increasingly limited by their high inference cost. While recent advances in dynamic token-level computation allocation attempt to improve efficiency by selectively activating model components per token, existing methods rely on greedy routing—a myopic execute-or-skip mechanism that often leads to irreversible information loss and suboptimal token selection. This paper introduces informed routing, a new paradigm that proactively addresses these issues. The key insight is to assess not only a token’s immediate importance but also its recoverability, i.e., how well its transformation can be approximated. To this end, we propose the Lightweight Feature Forecaster (LFF), a small predictive module that estimates a unit’s output before routing decisions are made. This enables a flexible execute-or-approximate policy that preserves model fidelity while drastically reducing computation. Extensive experiments show that informed routing consistently achieves state-of-the-art performance across static and dynamic pruning approaches. We further present two practical inference pipelines: a pure-PyTorch implementation and a Triton-based custom operator, that translate these gains into real-world speedups, achieving practical acceleration and consistent improvement across various batch sizes.

General Machine Learning · Transfer, Multitask and Meta-learning

Siru Jiang, Jian Liang, Ran He, Tieniu Tan

Test-time adaptation (TTA) has emerged as a popular paradigm for improving the performance of vision–language models (e.g., CLIP) on downstream tasks. Among existing CLIP-based TTA methods, Test-Time Prompt Tuning (TPT) is a pioneering work that optimizes textual prompts using multiple test-time augmentations and remains a strong baseline to date. In this work, we revisit TPT and reveal that its optimization can be interpreted as implicitly learning from self-generated pseudo labels. Building on this perspective, we propose a unified self-ensembling framework **USE** that jointly refines the optimization and inference stages. During optimization, we introduce a simple yet effective self-ensembling **SE** strategy that emphasizes the test image itself over its augmented views adaptively to obtain more reliable pseudo labels. To fully exploit the potential of augmentation, we further apply the same strategy at inference time, unifying the objectives of both stages. Notably, **SE** can also act as a lightweight training-free TTA method. Extensive experiments across multiple datasets demonstrate that **SE** and **USE** outperform their counterparts, respectively. Furthermore, **SE** yields consistent performance improvements when integrated with existing TTA methods.

General Machine Learning · Supervised Learning

Tianchi Liao, Lele Fu, Sheng Huang, Qing Hu, Hong-Ning Dai, Chuan Chen

Multimodal federated learning (MFL) has emerged as a pivotal paradigm for leveraging distributed data to enhance model performance. However, existing methods predominantly rely on idealized assumptions of model homogeneity and balanced modality distributions, rendering them ill-suited for practical scenarios characterized by heterogeneous client architectures and severe modality imbalance. To address these challenges, we propose a \textbf{M}ultimodal \textbf{Fed}erated learning Prototype-guided Bilateral Alignment (MFedPBA) framework. MFedPBA facilitates robust knowledge synergy through a dual alignment mechanism: (i) at the feature level, it aligns heterogeneous feature spaces via a projection encoder optimized by contrastive learning and the Gromov-Wasserstein distance; (ii) at the decision level, it employs an entropy-weighted aggregation of naturally aligned logit prototypes. This novel design achieves robust MFL by jointly tackling heterogeneous feature spaces and collectively aggregating decisions. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art baselines under conditions of model heterogeneity and modality imbalance.

Social Aspects · Everything Else

Guan-Ming Chiu

In this position paper, we argue that the machine learning community should adopt standardized carbon footprint reporting as part of routine scientific practice. Training large models can emit hundreds of tons of CO2, yet environmental costs remain largely invisible in publications. We contend that without energy and emissions metrics, claims of model efficiency are incomplete: a method cannot be deemed ''efficient'' without specifying efficient at what. This gap undermines scientific rigor and reproducibility, as identical experiments in different locations yield vastly different carbon footprints. We put forth reporting guidelines comprising five standardized metrics, practical measurement tools, and integration with community benchmarks, with a phased three-stage adoption process. We address alternative views, including concerns about measurement complexity and potential barriers for resource-limited researchers. To promote equity, we advocate for dual reporting of energy and carbon, reference-grid normalization, and acceptance of approximate estimates. This paper calls on venues, reviewers, authors, and institutions to establish carbon awareness as a foundational element of responsible ML research.

Applications · Computer Vision

Junwen He, Yang He, Lebing Zheng, Zirui Yin, Hong-Yu Zhang, Yulong Wang

Finding flat minima in the loss landscape is a key strategy for Domain Generalization (DG). However, its effectiveness is often limited by two crucial challenges. 1) Domain Shift: Existing methods like Sharpness-Aware Minimization (SAM) apply a uniform optimization strategy across all domains, overlooking the differences of the learning difficulties among multiple domains and thus performing poorly on challenging domains. 2) Anisotropic Sharpness: By perturbing parameters along a single gradient direction, SAM and its variants ignore multi-directional flatness, making the model converge to minima that remain sharp in other directions. The combined challenges make it more difficult for the model to find truly robust solutions in multi-domain scenarios. To overcome these limitations, we propose the Dual Adaptive Sharpness-Aware Minimization (DA-SAM), which comprises two key modules: Dynamic Adaptive Scaling (DAS) module and Adaptive Multi-Directional Flattening (AMDF) module. First, to tackle the domain shift problem, the DAS module computes the real-time loss on each domain to adaptively generate domain-specific scaling factors that guide the generation of perturbation directions. Second, the AMDF module calculates local flatness by generating multiple directions to simulate perturbations in the parameter space. Based on the learned local flatness metric, it dynamically adjusts the perturbation step size to guide the model parameters to be away from anisotropic sharp regions. Crucially, DAS provides domain-level guidance that makes AMDF’s multi-directional geometric exploration more targeted and effective. Extensive experiments on five DG benchmarks demonstrate the effectiveness of our DA-SAM algorithm.