论文检索

Deep Learning · Theory

Hemanth Saratchandran, Simon Lucey

Transformers are a dominant architecture in modern machine learning, powering applications across vision, language, and beyond. At the core of their success lies the attention layer, where the query, key, and value matrices determine how token dependencies are captured. While considerable work has focused on scaling and optimizing Transformers, comparatively little attention has been paid to how the weights of the queries, keys and values are initialized. Common practice relies on random initialization or alternatives such as mimetic initialization, which imitates weight patterns from converged models, and weight selection, which transfers weights from a teacher model. In this paper, we argue that initialization can introduce an optimization bias that fundamentally shapes training dynamics. We propose **conditioned initialization**, a principled scheme that initializes attention weights to improve the spectral properties of the attention layer. Theoretically, we show that conditioned initialization can potentially reduce the condition number of the attention Jacobian, leading to more stable optimization. Empirically, it accelerates convergence and improves generalization across diverse applications, highlighting conditioning as a critical yet underexplored area for advancing Transformer performance. Importantly, conditioned initialization is simple to apply and integrates seamlessly into a wide range of Transformer architectures.

Deep Learning · Graph Neural Networks

Yunan Wang, Jianxin Li, Ziwei Zhang

Dynamic Text-Attribute Graphs (DyTAGs), characterized by time-evolving graph interactions and associated text attributes, are prevalent in real-world applications. Existing methods, such as Graph Neural Networks (GNNs) and Large Language Models (LLMs), mostly focus on static TAGs. Extending these existing methods to DyTAGs is challenging as they largely neglect the *recent-global temporal semantics*: the recent semantic dependencies among interaction texts and the global semantic evolution of nodes over time. Furthermore, applying LLMs to the abundant and evolving text in DyTAGs faces efficiency issues. To tackle these challenges, we propose $\underline{Dy}$namic $\underline{G}$lobal-$\underline{R}$ecent $\underline{A}$daptive $\underline{S}$emantic $\underline{P}$rocessing (DyGRASP), a novel method that leverages LLMs and temporal GNNs to efficiently and effectively reason on DyTAGs. Specifically, we first design a node-centric implicit reasoning method together with a sliding window mechanism to efficiently capture recent temporal semantics. In addition, to capture global semantic dynamics of nodes, we leverage explicit reasoning with tailored prompts and an RNN-like chain structure to infer long-term semantics. Lastly, we intricately integrate the recent and global temporal semantics as well as the dynamic graph structural information using updating and merging layers. Extensive experiments on DyTAG benchmarks demonstrate DyGRASP's superiority, achieving up to 34\% improvement in Hit@10 for destination node retrieval task. Besides, DyGRASP exhibits strong generalization across different temporal GNNs and LLMs.

Deep Learning · Graph Neural Networks

Chen Haibo, Xin Wang, Guanheng Chen, Yuan Meng, Haoyang Li, Yang Yao, Zeyang Zhang, Zhiqiang Zhang, JUN ZHOU, Ling Feng 等

Dynamic graph out-of-distribution (OOD) generalization has drawn an increasing amount of attention in the research community, given its wide applicability in real-world scenarios. Existing methods typically employ a fixed-architecture design to extract invariant patterns. However, there may exist evolving distribution shifts in dynamic graphs, leading to suboptimal performance of fixed-architecture designs. To address this issue, we propose a novel adaptive-architecture design to handle evolving distribution shifts over time, to the best of our knowledge, for the first time. The proposed adaptive-architecture design introduces an adaptive mixture of architecture experts to capture invariant patterns under evolving distribution shifts, which imposes three challenges: 1) How to detect and characterize evolving distribution shifts to inform architectural decisions; 2) How to dynamically route different expert architectures to handle varying distribution characteristics; 3) How to ensure that the adaptive mixture of experts effectively discovers invariant patterns. To solve these challenges, we propose a novel **Ada**ptive **Mix**ture of Disentangled Experts (**AdaMix**) model to adaptively route architecture experts to varying distribution shifts and jointly learn spatio-temporal invariant patterns. Specifically, we propose a spatio-temporal distribution detector to infer evolving distribution shifts by jointly leveraging historical and current information. Building upon this, we develop a prototype-guided mixture of disentangled experts that adaptively routes experts with disentangled factors to different distribution shifts. Finally, we design a distribution-aware intervention mechanism that discovers invariant patterns based on expert selection of nodes. Extensive experiments on both synthetic and real-world datasets demonstrate that our proposed **AdaMix** model significantly outperforms state-of-the-art baselines.

Deep Learning · Graph Neural Networks

Caiyang Yu, Wei Ju, Haixin Wang, Yifan Wang, Ziyue Qiao

This paper studies the problem of open-set graph anomaly detection, which aims to generalize a graph neural network (GNN) trained with a small number of both normal and abnormal nodes to detect unseen anomalies different from training anomalies during inference. This problem is highly challenging due to both the data scarcity of unseen anomalies and the label scarcity for training nodes. Towards this end, we propose a novel approach named Dynamic Multi-sample Mixup with Gradient Exploration (DEMO) for open-set graph anomaly detection. The core of our proposed DEMO is to leverage a dynamic framework to adapt the optimization procedure with high generalizability. In particular, our DEMO first adaptively fuses multiple seen nodes to simulate the unseen anomalies, which expands the decision boundary for the detection model with enhanced generalizability. Moreover, we dynamically adjust sample weights based on their energy gradients to prioritize uncertain and informative nodes, ensuring a robust optimization procedure. To further address both label scarcity and severe class imbalance, we maintain a memory bank of historical records to guide the pseudo-labeling process of unlabeled nodes. Extensive experiments on various benchmark datasets validate the superiority of the proposed DEMO in comparison to various baselines.

Applications · Genetics, Cell Biology, Health, etc

Jiahao Zhang, ZEQING ZHANG, Di Wang, Lijie Hu

Protein language models (PLMs) have enabled advances in structure prediction and de novo protein design, yet they frequently collapse into pathological repetition during generation. Unlike in text, where repetition merely reduces readability, in proteins it undermines structural confidence and functional viability. To unify this problem, we present the first systematic study of repetition in PLMs. We first propose quantitative metrics to characterize motif-level and homopolymer repetition and then demonstrate their negative impact on folding reliability. To address this challenge, we propose UCCS (Utility-Controlled Contrastive Steering), which steers protein generation with a constrained dataset. Instead of naively contrasting high- vs. low-repetition sequences, we construct contrastive sets that maximize differences in repetition while tightly controlling for structural utility. This disentanglement yields steering vectors that specifically target repetition without degrading foldability. Injected at inference, these vectors consistently reduce repetition without retraining or heuristic decoding. Experiments with ESM-3 and ProtGPT2 in CATH, UniRef50, and SCOP show that our method outperforms decoding penalties and other baselines, substantially lowering repetition while preserving AlphaFold confidence scores. Our results establish repetition control as a central challenge for PLMs and highlight dataset-guided steering as a principled approach for reliable protein generation.

Deep Learning · Generative Models and Autoencoders

WENBO WU, Qingyi Si, Xiurui Pan, Ye Wang, Jie Zhang

While Key-Value (KV) cache succeeds in reducing redundant computations in auto-regressive models, it introduces significant memory overhead, limiting its practical deployment in long-sequence scenarios. Existing KV retrieval methods attempt to mitigate this by dynamically retaining only a subset of KV entries on the GPU. However, they still suffer from notable efficiency and accuracy bottlenecks due to per-token retrieval and coarse-grained page-level KV management strategy, especially in long-output reasoning scenarios. With the emergence of large reasoning models, efficiently handling such scenarios has become increasingly important. To address this issue, we present two key observations: (1) critical KVs exhibit strong temporal locality during decoding, and (2) these KVs exhibit distinct distribution patterns across the input prompt and the generated output. Building on these observations, we propose \emph{LouisKV}, an efficient KV cache retrieval framework designed for various long-sequence scenarios. Specifically, LouisKV introduces a semantic-aware retrieval strategy that leverages temporal locality to trigger retrieval only at semantic boundaries, drastically reducing computation and data transfer overhead. LouisKV also designs a decoupled, fine-grained management scheme that tailors differentiated strategies for input and output sequences to create retrieval units that better match the model's attention patterns, thereby enabling the precise identification of critical KVs. Furthermore, to boost system efficiency, LouisKV incorporates several kernel-level optimizations, including custom Triton and CUDA kernels to accelerate the KV clustering and retrieval. Evaluation results show that LouisKV achieves up to 4.7$\times$ speedup over state-of-the-art KV retrieval methods while maintaining near-lossless accuracy across diverse long-sequence tasks, including long-input short-output, short-input long-output, and long-input long-output scenarios.

Deep Learning · Generative Models and Autoencoders

Seonghwan Choi, Beomseok Kang, Dongwon Jo, jae-joon kim

Large Language Models (LLMs) are increasingly deployed in long-context tasks such as reasoning, code generation, and multi-turn dialogue. However, inference over extended contexts is bottlenecked by the Key-Value (KV) cache, whose memory footprint grows linearly with sequence length and dominates latency at each decoding step. While recent KV cache compression methods identify and load important few tokens, they focus predominantly on input contexts and fail to address the cumulative attention errors that arise during long decoding. In this paper, we introduce RetroAttention, a novel KV cache update technique that retrospectively revises past attention outputs using newly arrived KV entries from subsequent decoding steps. By maintaining a lightweight output cache, RetroAttention enables past queries to be efficiently supplemented with more contexts, while incurring minimal latency overhead. This breaks the fixed-attention-output paradigm and allows continual correction of prior approximations. Extensive experiments on long-generation benchmarks show that RetroAttention consistently outperforms state-of-the-art (SOTA) KV compression methods, increasing effective KV exposure by up to 1.6$\times$ and accuracy by up to 21.9\%. We provide anonymized code in the supplementary material.

Applications · Robotics

Yingyan Li, Shuyao Shang, Weisong Liu, Bing Zhan, Haochen Wang, Yuqi Wang, Yuntao Chen, Xiaoman Wang, Yasong An, Chufeng Tang 等

Scaling Vision-Language-Action (VLA) models on large-scale data offers a promising path to achieving a more generalized driving intelligence. However, VLA models are limited by a ``supervision deficit'': the vast model capacity is supervised by sparse, low-dimensional actions, leaving much of their representational power underutilized. To remedy this, we propose DriveVLA-W0, a training paradigm that employs world modeling to predict future images. This task generates a dense, self-supervised signal that compels the model to learn the underlying dynamics of the driving environment. We showcase the paradigm's versatility by instantiating it for two dominant VLA archetypes: an autoregressive world model for VLAs that use discrete visual tokens, and a diffusion world model for those operating on continuous visual features. Building on the rich representations learned from world modeling, we introduce a lightweight action expert to address the inference latency for real-time deployment. Extensive experiments on the NAVSIM v1/v2 benchmark and a 680x larger in-house dataset demonstrate that DriveVLA-W0 significantly outperforms BEV and VLA baselines. Crucially, it amplifies the data scaling law, showing that performance gains accelerate as the training dataset size increases.

Theory · Game Theory

Nina Balcan, Martino Bernasconi, Matteo Castiglioni, Andrea Celli, Keegan Harris, Steven Wu

We study the problem of online learning in Stackelberg games with side information between a leader and a sequence of followers. In every round the leader observes contextual information and commits to a mixed strategy, after which the follower best-responds. We provide learning algorithms for the leader which achieve O(T^{1/2}) regret under bandit feedback, an improvement from the previously best-known rates of O(T^{2/3}). Our algorithms rely on a reduction to linear contextual bandits in the utility space: In each round, a linear contextual bandit algorithm recommends a utility vector, which our algorithm inverts to determine the leader's mixed strategy. We extend our algorithms to the setting in which the leader's utility function is unknown, and also apply it to the problems of bidding in second-price auctions with side information and online Bayesian persuasion with public and private states. Finally, we observe that our algorithms empirically outperform previous results on numerical simulations.

Deep Learning · Generative Models and Autoencoders

Boao Kong, Junzhu Liang, Yuxi Liu, Renjia Deng, Kun Yuan

Low-rank architectures have become increasingly important for efficient large language model (LLM) pre-training, providing substantial reductions in both parameter complexity and memory/computational demands. Despite these advantages, current low-rank methods face three critical shortcomings: (1) compromised model performance, (2) considerable computational overhead, and (3) limited activation memory savings. To address these limitations, we propose **C**ross-layer Low-**R**ank residual **Net**work (**CR-Net**), an innovative parameter-efficient framework inspired by our discovery that inter-layer activation residuals possess low-rank properties. CR-Net implements this insight through a dual-path architecture that efficiently reconstructs layer activations by combining previous-layer outputs with their low-rank differences, thereby maintaining high-rank information with minimal parameters. We further develop a specialized activation recomputation strategy tailored for CR-Net that dramatically reduces memory requirements. Extensive pre-training experiments across model scales from 60M to 7B parameters demonstrate that CR-Net consistently outperforms state-of-the-art low-rank frameworks while requiring fewer computational resources and less memory.

Deep Learning · Generative Models and Autoencoders

Wenqi Guo, Shan Du

We introduce Value Sign Flip (VSF), a simple and efficient method for incorporating negative prompt guidance in few-step (1-8 steps) diffusion and flow-matching image and video generation models. Unlike existing approaches such as classifier-free guidance (CFG), NASA, and NAG, VSF dynamically suppresses undesired content by flipping the sign of attention values from negative prompts. Our method requires only a small computational overhead and integrates effectively with MMDiT-style architectures such as Stable Diffusion 3.5 Turbo and Flux Schnell, as well as cross-attention-based models like Wan. We validate VSF on a proposed challenging dataset, NegGenBench, with complex prompt pairs. Experimental results on our proposed dataset show that VSF significantly improves negative prompt adherence (reaching 0.420 negative score for quality settings and 0.545 for strong settings) compared to prior methods in few-step models (scored 0.320-0.380 negative score) and even CFG in non-few-step models (scored 0.300 negative score), while maintaining competitive image quality and positive prompt adherence. Our method also suppressed a generate-then-edit pipeline, while also having a much faster runtime. Code, ComfyUI node, and dataset are available in https://github.com/weathon/VSF/tree/main.

Lifang ZHENG, Hanmo Liu, Kani Chen

Few-shot text classification is a critical real-world task for which Large Language Models (LLMs) have shown great promise. However, their high inference costs and lack of interpretability limit their practical use. While Concept Bottleneck Models (CBMs) offer an efficient and interpretable alternative, their reliance on training surrogate models makes them incompatible with few-shot scenarios. To bridge this gap, we introduce a novel CBM paradigm that relies solely on sample-concept similarity to make predictions. We ensure the effectiveness of our concepts through a prototypical-discriminative dual-level architecture and a dynamic concept refinement mechanism. Extensive experiments show that with as few as 10 training samples, our method surpasses prior CBMs and even achieves performance comparable to LLMs. The code is available at \url{https://github.com/alexiszlf/StructCBM}.

Deep Learning · Generative Models and Autoencoders

Jiaming Fan, CAO DAMING, Xiangzhong Luo, Jiale Fu, CHONGHAN LIU, xu yang

Speculative Decoding (SD) is a key technique for accelerating Large Language Model (LLM) inference, but it typically requires training a draft model on a large dataset. We approach this problem from a data-centric perspective, finding that not all training samples contribute equally to the SD acceptance rate. Specifically, our theoretical analysis and empirical validation reveals that tokens inducing flatter predictive distributions from the target model are more valuable than those yielding sharply peaked distributions. Based on this insight, we propose flatness, a new metric to quantify this property, and develop the Sample-level-flatness-based Dataset Distillation (SFDD) approach, which filters the training data to retain only the most valuable samples. Experiments on the EAGLE framework demonstrate that SFDD can achieve over 2$\times$ training speedup using only 50\% of the data, while keeping the final model's inference speedup within 4\% of the full-dataset baseline. This work introduces an effective, data-centric approach that substantially improves the training efficiency for Speculative Decoding. Our code is available at https://github.com/fjm9933/Flatness.

Deep Learning · Generative Models and Autoencoders

Qingyuan Tian, Wenhong Zhu, Xiaoran Liu, Xiaofeng Wang, Rui Wang

Rotary Position Embedding (RoPE)-extension refers to modifying or generalizing the Rotary Position Embedding scheme to handle longer sequences than those encountered during pre-training. However, current extension strategies are highly diverse and lack a unified theoretical foundation. In this paper, we propose $\textbf{\textit{MrRoPE (Mixed-radix RoPE)}}$, a generalized encoding formulation based on a radix system conversion perspective, which elegantly unifies various RoPE-extension approaches as distinct radix conversion strategies. Based on this theory, we introduce two training-free extensions, $\textbf{\textit{MrRoPE-Uni}}$ and $\textbf{\textit{MrRoPE-Pro}}$, which leverage uniform and progressive radix conversion strategies, respectively, to achieve “train short, test long” generalization. Without fine-tuning, MrRoPE-Pro sustains over 85% recall in the 128K-context Needle-in-a-Haystack test and achieves more than double YaRN’s accuracy on Infinite-Bench retrieval and dialogue subsets. Theoretical analysis confirms that MrRoPE-Pro effectively raises the upper bound of RoPE's attainable encoding length, which further validates the reliability and utility of our theory and methodology.

Deep Learning · Robustness

Zhaoyang Zhang, Shen Wang, Runze Liu, Guopu Zhu, Fanghui Sun, Ye Lu, Zeyue Wang, Yihan Yan

Adversarial attacks have achieved widespread success in various domains, yet existing methods suffer from significant performance degradation when adversarial examples are subjected to even minor disturbances. In this paper, we propose a novel and robust attack called IGSA (**I**nverse **G**radient **S**ample-based **A**ttack), capable of generating adversarial examples that remain effective under diverse unknown disturbances. IGSA employs an iterative two-step framework: (i) inverse gradient sampling, which searches for the most disruptive direction within the neighborhood of adversarial examples, and (ii) disturbance-guided refinement, which updates adversarial examples via gradient descent along the identified disruptive disturbance. Theoretical analysis reveals that IGSA enhances robustness by increasing the likelihood of adversarial examples within the data distribution. Extensive experiments in both white-box and black-box attack scenarios demonstrate that IGSA significantly outperforms state-of-the-art attacks in terms of robustness against various unknown disturbances. Moreover, IGSA exhibits superior performance when attacking adversarially trained defense models. Code is available at https://github.com/nimingck/IGSA.

Computer Vision · Image and Video Generation

Xinhao Cai, Liulei Li, Gensheng Pei, Tao Chen, Jinshan Pan, Yazhou Yao, Wenguan Wang

This paper presents a generation-based debiasing framework for object detection. Prior debiasing methods are often limited by the representation diversity of samples, while naive generative augmentation often preserves the biases it aims to solve. Moreover, our analysis reveals that simply generating more data for rare classes is suboptimal due to two core issues: i) instance frequency is an incomplete proxy for the true data needs of a model, and ii) current layout-to-image synthesis lacks the fidelity and control to generate high-quality, complex scenes. To overcome this, we introduce the representation score (RS) to diagnose representational gaps beyond mere frequency, guiding the creation of new, unbiased layouts. To ensure high-quality synthesis, we replace ambiguous text prompts with a precise visual blueprint and employ a generative alignment strategy, which fosters communication between the detector and generator. Our method significantly narrows the performance gap for underrepresented object groups, e.g., improving large/rare instances by 4.4/3.6 mAP over the baseline, and surpassing prior L2I synthesis models by 15.9 mAP for layout accuracy in generated images.

Deep Learning · Generative Models and Autoencoders

Jing Jia, Sifan Liu, Bowen Song, Wei Yuan, Liyue Shen, Guanyang Wang

We systematically study antithetic initial noise in diffusion models, discovering that pairing each noise sample with its negation consistently produces strong negative correlation. This universal phenomenon holds across datasets, model architectures, conditional and unconditional sampling, and even other generative models such as VAEs and Normalizing Flows. To explain it, we combine experiments and theory and propose a \textit{symmetry conjecture} that the learned score function is approximately affine antisymmetric (odd symmetry up to a constant shift), supported by empirical evidence. This negative correlation leads to substantially more reliable uncertainty quantification with up to $90\%$ narrower confidence intervals. We demonstrate these gains on tasks including estimating pixel-wise statistics and evaluating diffusion inverse solvers. We also provide extensions with randomized quasi-Monte Carlo noise designs for uncertainty quantification, and explore additional applications of the antithetic noise design to improve image editing and generation diversity. Our framework is training-free, model-agnostic, and adds no runtime overhead. Code is available at https://github.com/jjia131/Antithetic-Noise-in-Diffusion-Models-page.

Deep Learning · Generative Models and Autoencoders

Amrith Setlur, Matthew Yang, Charlie Snell, Jeremiah Greer, Ian Wu, Virginia Smith, Max Simchowitz, Aviral Kumar

Test-time scaling offers a promising path to improve LLM reasoning by utilizing more compute at inference time; however, the true promise of this paradigm lies in extrapolation (i.e., improvement in performance on hard problems as LLMs keep "thinking" for longer, beyond the maximum token budget they were trained on). Surprisingly, we find that most existing reasoning models do not extrapolate well. We show that one way to enable extrapolation is by training the LLM to perform in-context exploration: training the LLM to effectively spend its test time budget by chaining operations (such as generation, verification, refinement, etc.), or testing multiple hypotheses before it commits to an answer. To enable in-context exploration, we identify three key ingredients as part of our recipe e3: (1) chaining skills that the base LLM has asymmetric competence in, e.g., chaining verification (easy) with generation (hard), as a way to implement in-context search; (2) leveraging "negative" gradients from incorrect traces to amplify exploration during RL, resulting in longer search traces that chains additional asymmetries; and (3) coupling task difficulty with training token budget during training via a specifically-designed curriculum to structure in-context exploration. Our recipe e3 produces the best known 1.7B model according to AIME'25 and HMMT'25 scores, and extrapolates to 2x the training token budget. Our e3-1.7B model not only attains high pass@1 scores, but also improves pass@k over the base model.

Deep Learning · Generative Models and Autoencoders

Uriel Singer, Yaron Lipman

Transition Matching (TM) is an emerging paradigm for generative modeling that generalizes diffusion and flow-matching models as well as continuous-state autoregressive models. TM, similar to previous paradigms, gradually transforms noise samples to data samples, however it uses a second ``internal'' generative model to implement the transition steps, making the transitions more expressive compared to diffusion and flow models. To make this paradigm tractable, TM employs a large backbone network and a smaller "head" module to efficiently execute the generative transition step. In this work, we present a large-scale, systematic investigation into the design, training and sampling of the head in TM frameworks, focusing on its time-continuous bidirectional variant. Through comprehensive ablations and experimentation involving training 56 different 1.7B text-to-image models (resulting in 549 unique evaluations) we evaluate the affect of the head module architecture and modeling during training as-well as a useful family of stochastic TM samplers. We analyze the impact on generation quality, training, and inference efficiency. We find that TM with an MLP head, trained with a particular time weighting and sampled with high frequency sampler provides best ranking across all metrics reaching state-of-the-art among all tested baselines, while Transformer head with sequence scaling and low frequency sampling is a runner up excelling at image aesthetics. Lastly, we believe the experiments presented highlight the design aspects that are likely to provide most quality and efficiency gains, while at the same time indicate what design choices are not likely to provide further gains.

Deep Learning · Graph Neural Networks

Lecheng Zheng, Dongqi Fu, Zihao Li, Jingrui He

Graph structured data is commonly used to represent complex relationships such as transactions between accounts, communications between devices, and dependencies among machines or processes. Correspondingly, graph anomaly detection (GAD) plays a critical role in identifying anomalies across various domains, including finance, cybersecurity, manufacturing, etc. Facing the large-volume and multi-domain graph data, recent efforts aim to develop foundational generalist models capable of detecting anomalies in unseen graphs without retraining. To the best of our knowledge, the different feature semantics and dimensions of cross-domain graph structured data heavily hinders the development of graph foundation model, and leaves the further in-depth continual learning and inference capabilities in the evolving setting a quite nascent problem. To address these above challenges, we propose OWLEYE, a novel zero-shot GAD framework that learns transferable patterns of normal behavior from multiple graphs. Systematically, OWLEYE first introduces a cross-domain feature alignment module to harmonize feature distributions, which preserves domain-specific semantics during aligning more than the simple but widely-used Principle Component Analysis. Second, with aligned features, to enable method with continuous and scaling-up learning and inference capabilities, OWLEYE designs the multi-domain pattern dictionary learning to encode shared structural and attribute-based patterns. Third, for achieving the in-context learning ability, OWLEYE presents a truncated attention-based reconstruction module to robustly detect anomalies without requiring labeled data for unseen graph structured data. Extensive experiments on real-world datasets demonstrate that OWLEYE achieves superior performance and generalizability compared to state-of-the-art baselines, establishing a strong foundation for scalable and label-efficient anomaly detection.