Showing 1–50 of 192 results for author: Yi, K

From Intent to Evidence: A Categorical Approach for Structural Evaluation of Deep Research Agents

Authors: Shuoling Liu, Zhiquan Tan, Kun Yi, Hui Wu, Yihan Li, Jiangpeng Yan, Liyuan Chen, Kai Chen, Qiang Yang

Abstract: Although deep research agents (DRAs) have emerged as a promising paradigm for complex information synthesis, their evaluation remains constrained by ad hoc empirical benchmarks. These heuristic approaches do not rigorously model agent behavior or adequately stress-test long-horizon synthesis and ambiguity resolution. To bridge this gap, we formalize DRA behavior through the lens of category theory… ▽ More Although deep research agents (DRAs) have emerged as a promising paradigm for complex information synthesis, their evaluation remains constrained by ad hoc empirical benchmarks. These heuristic approaches do not rigorously model agent behavior or adequately stress-test long-horizon synthesis and ambiguity resolution. To bridge this gap, we formalize DRA behavior through the lens of category theory, modeling deep research workflow as a composition of structure-preserving maps (functors). Grounded in this theoretical framework, we introduce a novel mechanism-aware benchmark with 296 questions designed to stress-test agents along four interpretable axes: traversing sequential connectivity chains, verifying intersections within V-structure pullbacks, imposing topological ordering on retrieved substructures, and performing ontological falsification via the Yoneda Probe. Our rigorous evaluation of 11 leading models establishes a persistently low baseline, with the state-of-the-art achieving only a 19.9\% average accuracy, exposing the difficulty of formal structural stress-testing. Furthermore, our findings reveal a stark dichotomy in the current AI capabilities. While advanced deep research pipelines successfully redefine dynamic topological re-ordering and exhibit robust ontological verification -- matching pure reasoning models in falsifying hallucinated premises -- they almost universally collapse on multi-hop structural synthesis. Crucially, massive performance variance across tasks exposes a lingering reliance on brittle heuristics rather than a systemic understanding. Ultimately, this work demonstrates that while top-tier autonomous agents can now organically unify search and reasoning, achieving a generalized mastery over complex structural information remains a formidable open challenge.\footnote{Our implementation will be available at https://github.com/tzq1999/CDR. △ Less

Submitted 26 March, 2026; originally announced March 2026.

FullCircle: Effortless 3D Reconstruction from Casual 360$^\circ$ Captures

Authors: Yalda Foroutan, Ipek Oztas, Daniel Rebain, Aysegul Dundar, Kwang Moo Yi, Lily Goli, Andrea Tagliasacchi

Abstract: Radiance fields have emerged as powerful tools for 3D scene reconstruction. However, casual capture remains challenging due to the narrow field of view of perspective cameras, which limits viewpoint coverage and feature correspondences necessary for reliable camera calibration and reconstruction. While commercially available 360$^\circ$ cameras offer significantly broader coverage than perspective… ▽ More Radiance fields have emerged as powerful tools for 3D scene reconstruction. However, casual capture remains challenging due to the narrow field of view of perspective cameras, which limits viewpoint coverage and feature correspondences necessary for reliable camera calibration and reconstruction. While commercially available 360$^\circ$ cameras offer significantly broader coverage than perspective cameras for the same capture effort, existing 360$^\circ$ reconstruction methods require special capture protocols and pre-processing steps that undermine the promise of radiance fields: effortless workflows to capture and reconstruct 3D scenes. We propose a practical pipeline for reconstructing 3D scenes directly from raw 360$^\circ$ camera captures. We require no special capture protocols or pre-processing, and exhibit robustness to a prevalent source of reconstruction errors: the human operator that is visible in all 360$^\circ$ imagery. To facilitate evaluation, we introduce a multi-tiered dataset of scenes captured as raw dual-fisheye images, establishing a benchmark for robust casual 360$^\circ$ reconstruction. Our method significantly outperforms not only vanilla 3DGS for 360$^\circ$ cameras but also robust perspective baselines when perspective cameras are simulated from the same capture, demonstrating the advantages of 360$^\circ$ capture for casual reconstruction. Additional results are available at: https://theialab.github.io/fullcircle △ Less

Submitted 23 March, 2026; originally announced March 2026.

Making Video Models Adhere to User Intent with Minor Adjustments

Authors: Daniel Ajisafe, Eric Hedlin, Helge Rhodin, Kwang Moo Yi

Abstract: With the recent drastic advancements in text-to-video diffusion models, controlling their generations has drawn interest. A popular way for control is through bounding boxes or layouts. However, enforcing adherence to these control inputs is still an open problem. In this work, we show that by slightly adjusting user-provided bounding boxes we can improve both the quality of generations and the ad… ▽ More With the recent drastic advancements in text-to-video diffusion models, controlling their generations has drawn interest. A popular way for control is through bounding boxes or layouts. However, enforcing adherence to these control inputs is still an open problem. In this work, we show that by slightly adjusting user-provided bounding boxes we can improve both the quality of generations and the adherence to the control inputs. This is achieved by simply optimizing the bounding boxes to better align with the internal attention maps of the video diffusion model while carefully balancing the focus on foreground and background. In a sense, we are modifying the bounding boxes to be at places where the model is familiar with. Surprisingly, we find that even with small modifications, the quality of generations can vary significantly. To do so, we propose a smooth mask to make the bounding box position differentiable and an attention-maximization objective that we use to alter the bounding boxes. We conduct thorough experiments, including a user study to validate the effectiveness of our method. Our code is made available on the project webpage to foster future research from the community. △ Less

Submitted 20 March, 2026; originally announced March 2026.

Comments: Project page and code: https://ubc-vision.github.io/MinorAdjustVideo/docs/webpage/index.html

CARE: A Molecular-Guided Foundation Model with Adaptive Region Modeling for Whole Slide Image Analysis

Authors: Di Zhang, Zhangpeng Gong, Xiaobo Pang, Jiashuai Liu, Junbo Lu, Hao Cui, Jiusong Ge, Zhi Zeng, Kai Yi, Yinghua Li, Si Liu, Tingsong Yu, Haoran Wang, Mireia Crispin-Ortuzar, Weimiao Yu, Chen Li, Zeyu Gao

Abstract: Foundation models have recently achieved impressive success in computational pathology, demonstrating strong generalization across diverse histopathology tasks. However, existing models overlook the heterogeneous and non-uniform organization of pathological regions of interest (ROIs) because they rely on natural image backbones not tailored for tissue morphology. Consequently, they often fail to c… ▽ More Foundation models have recently achieved impressive success in computational pathology, demonstrating strong generalization across diverse histopathology tasks. However, existing models overlook the heterogeneous and non-uniform organization of pathological regions of interest (ROIs) because they rely on natural image backbones not tailored for tissue morphology. Consequently, they often fail to capture the coherent tissue architecture beyond isolated patches, limiting interpretability and clinical relevance. To address these challenges, we present Cross-modal Adaptive Region Encoder (CARE), a foundation model for pathology that automatically partitions WSIs into several morphologically relevant regions. Specifically, CARE employs a two-stage pretraining strategy: (1) a self-supervised unimodal pretraining stage that learns morphological representations from 34,277 whole-slide images (WSIs) without segmentation annotations, and (2) a cross-modal alignment stage that leverages RNA and protein profiles to refine the construction and representation of adaptive regions. This molecular guidance enables CARE to identify biologically relevant patterns and generate irregular yet coherent tissue regions, selecting the most representative area as ROI. CARE supports a broad range of pathology-related tasks, using either the ROI feature or the slide-level feature obtained by aggregating adaptive regions. Based on only one-tenth of the pretraining data typically used by mainstream foundation models, CARE achieves superior average performance across 33 downstream benchmarks, including morphological classification, molecular prediction, and survival analysis, and outperforms other foundation model baselines overall. △ Less

Submitted 17 March, 2026; v1 submitted 25 February, 2026; originally announced February 2026.

Comments: Accepted to CVPR 2026

TimeRadar: A Domain-Rotatable Foundation Model for Time Series Anomaly Detection

Authors: Hui He, Hezhe Qiao, Yutong Chen, Kun Yi, Guansong Pang

Abstract: Current time series foundation models (TSFMs) primarily focus on learning prevalent and regular patterns within a predefined time or frequency domain to enable supervised downstream tasks (e.g., forecasting). Consequently, they are often ineffective for inherently unsupervised downstream tasks-such as time series anomaly detection (TSAD), which aims to identify rare, irregular patterns. This limit… ▽ More Current time series foundation models (TSFMs) primarily focus on learning prevalent and regular patterns within a predefined time or frequency domain to enable supervised downstream tasks (e.g., forecasting). Consequently, they are often ineffective for inherently unsupervised downstream tasks-such as time series anomaly detection (TSAD), which aims to identify rare, irregular patterns. This limitation arises because such abnormal patterns can closely resemble the regular patterns when presented in the same time/frequency domain. To address this issue, we introduce TimeRadar, an innovative TSFM built in a fractional time-frequency domain to support generalist TSAD across diverse unseen datasets. Our key insight is that rotating a time series into a data-dependent fractional time-frequency representation can adaptively differentiate the normal and abnormal signals across different datasets. To this end, a novel component, namely Fractionally modulated Time-Frequency Reconstruction (FTFRecon), is proposed in TimeRadar to leverage a learnable fractional order to rotate the time series to the most pronounced angle between a continuous time and frequency domain for accurate data reconstruction. This provides adaptive data reconstruction in an optimal time-frequency domain for each data input, enabling effective differentiation of the unbounded abnormal patterns from the regular ones across datasets, including unseen datasets. To allow TimeRadar to model local abnormality that is not captured by the global data reconstruction, we further introduce a Contextual Deviation Learning (CDL) component to model the local deviation of the input relative to its contextual time series data in the rotatable domain. △ Less

Submitted 22 February, 2026; originally announced February 2026.

Adaptive Privacy Budgeting

Authors: Yuting Liang, Ke Yi

Abstract: We study the problem of adaptive privacy budgeting under generalized differential privacy. Consider the setting where each user $i\in [n]$ holds a tuple $x_i\in U:=U_1\times \dotsb \times U_T$, where $x_i(l)\in U_l$ represents the $l$-th component of their data. For every $l\in [T]$ (or a subset), an untrusted analyst wishes to compute some $f_l(x_1(l),\dots,x_n(l))$, while respecting the privacy… ▽ More We study the problem of adaptive privacy budgeting under generalized differential privacy. Consider the setting where each user $i\in [n]$ holds a tuple $x_i\in U:=U_1\times \dotsb \times U_T$, where $x_i(l)\in U_l$ represents the $l$-th component of their data. For every $l\in [T]$ (or a subset), an untrusted analyst wishes to compute some $f_l(x_1(l),\dots,x_n(l))$, while respecting the privacy of each user. For many functions $f_l$, data from the users are not all equally important, and there is potential to use the privacy budgets of the users strategically, leading to privacy savings that can be used to improve the utility of later queries. In particular, the budgeting should be adaptive to the outputs of previous queries, so that greater savings can be achieved on more typical instances. In this paper, we provide such an adaptive budgeting framework, with various applications demonstrating its applicability. △ Less

Submitted 15 January, 2026; originally announced January 2026.

SONIC: Spectral Optimization of Noise for Inpainting with Consistency

Authors: Seungyeon Baek, Erqun Dong, Shadan Namazifard, Mark J. Matthews, Kwang Moo Yi

Abstract: We propose a novel training-free method for inpainting with off-the-shelf text-to-image models. While guidance-based methods in theory allow generic models to be used for inverse problems such as inpainting, in practice, their effectiveness is limited, leading to the necessity of specialized inpainting-specific models. In this work, we argue that the missing ingredient for training-free inpainting… ▽ More We propose a novel training-free method for inpainting with off-the-shelf text-to-image models. While guidance-based methods in theory allow generic models to be used for inverse problems such as inpainting, in practice, their effectiveness is limited, leading to the necessity of specialized inpainting-specific models. In this work, we argue that the missing ingredient for training-free inpainting is the optimization (guidance) of the initial seed noise. We propose to optimize the initial seed noise to approximately match the unmasked parts of the data - with as few as a few tens of optimization steps. We then apply conventional training-free inpainting methods on top of our optimized initial seed noise. Critically, we propose two core ideas to effectively implement this idea: (i) to avoid the costly unrolling required to relate the initial noise and the generated outcome, we perform linear approximation; and (ii) to stabilize the optimization, we optimize the initial seed noise in the spectral domain. We demonstrate the effectiveness of our method on various inpainting tasks, outperforming the state of the art. Project page: https://ubc-vision.github.io/sonic/ △ Less

Submitted 26 November, 2025; v1 submitted 25 November, 2025; originally announced November 2025.

MTP: Exploring Multimodal Urban Traffic Profiling with Modality Augmentation and Spectrum Fusion

Authors: Haolong Xiang, Peisi Wang, Xiaolong Xu, Kun Yi, Xuyun Zhang, Quanzheng Sheng, Amin Beheshti, Wei Fan

Abstract: With rapid urbanization in the modern era, traffic signals from various sensors have been playing a significant role in monitoring the states of cities, which provides a strong foundation in ensuring safe travel, reducing traffic congestion and optimizing urban mobility. Most existing methods for traffic signal modeling often rely on the original data modality, i.e., numerical direct readings from… ▽ More With rapid urbanization in the modern era, traffic signals from various sensors have been playing a significant role in monitoring the states of cities, which provides a strong foundation in ensuring safe travel, reducing traffic congestion and optimizing urban mobility. Most existing methods for traffic signal modeling often rely on the original data modality, i.e., numerical direct readings from the sensors in cities. However, this unimodal approach overlooks the semantic information existing in multimodal heterogeneous urban data in different perspectives, which hinders a comprehensive understanding of traffic signals and limits the accurate prediction of complex traffic dynamics. To address this problem, we propose a novel Multimodal framework, MTP, for urban Traffic Profiling, which learns multimodal features through numeric, visual, and textual perspectives. The three branches drive for a multimodal perspective of urban traffic signal learning in the frequency domain, while the frequency learning strategies delicately refine the information for extraction. Specifically, we first conduct the visual augmentation for the traffic signals, which transforms the original modality into frequency images and periodicity images for visual learning. Also, we augment descriptive texts for the traffic signals based on the specific topic, background information and item description for textual learning. To complement the numeric information, we utilize frequency multilayer perceptrons for learning on the original modality. We design a hierarchical contrastive learning on the three branches to fuse the spectrum of three modalities. Finally, extensive experiments on six real-world datasets demonstrate superior performance compared with the state-of-the-art approaches. △ Less

Submitted 16 November, 2025; v1 submitted 13 November, 2025; originally announced November 2025.

SEMPO: Lightweight Foundation Models for Time Series Forecasting

Authors: Hui He, Kun Yi, Yuanchi Ma, Qi Zhang, Zhendong Niu, Guansong Pang

Abstract: The recent boom of large pre-trained models witnesses remarkable success in developing foundation models (FMs) for time series forecasting. Despite impressive performance across diverse downstream forecasting tasks, existing time series FMs possess massive network architectures and require substantial pre-training on large-scale datasets, which significantly hinders their deployment in resource-co… ▽ More The recent boom of large pre-trained models witnesses remarkable success in developing foundation models (FMs) for time series forecasting. Despite impressive performance across diverse downstream forecasting tasks, existing time series FMs possess massive network architectures and require substantial pre-training on large-scale datasets, which significantly hinders their deployment in resource-constrained environments. In response to this growing tension between versatility and affordability, we propose SEMPO, a novel lightweight foundation model that requires pretraining on relatively small-scale data, yet exhibits strong general time series forecasting. Concretely, SEMPO comprises two key modules: 1) energy-aware SpEctral decomposition module, that substantially improves the utilization of pre-training data by modeling not only the high-energy frequency signals but also the low-energy yet informative frequency signals that are ignored in current methods; and 2) Mixture-of-PrOmpts enabled Transformer, that learns heterogeneous temporal patterns through small dataset-specific prompts and adaptively routes time series tokens to prompt-based experts for parameter-efficient model adaptation across different datasets and domains. Equipped with these modules, SEMPO significantly reduces both pre-training data scale and model size, while achieving strong generalization. Extensive experiments on two large-scale benchmarks covering 16 datasets demonstrate the superior performance of SEMPO in both zero-shot and few-shot forecasting scenarios compared with state-of-the-art methods. Code and data are available at https://github.com/mala-lab/SEMPO. △ Less

Submitted 22 October, 2025; originally announced October 2025.

Comments: Accepted by NeurIPS 2025

Comparing LSTM-Based Sequence-to-Sequence Forecasting Strategies for 24-Hour Solar Proton Flux Profiles Using GOES Data

Authors: Kangwoo Yi, Bo Shen, Qin Li, Haimin Wang, Yong-Jae Moon, Jaewon Lee, Hwanhee Lee

Abstract: Solar Proton Events (SPEs) cause significant radiation hazards to satellites, astronauts, and technological systems. Accurate forecasting of their proton flux time profiles is crucial for early warnings and mitigation. This paper explores deep learning sequence-to-sequence (seq2seq) models based on Long Short-Term Memory networks to predict 24-hour proton flux profiles following SPE onsets. We use… ▽ More Solar Proton Events (SPEs) cause significant radiation hazards to satellites, astronauts, and technological systems. Accurate forecasting of their proton flux time profiles is crucial for early warnings and mitigation. This paper explores deep learning sequence-to-sequence (seq2seq) models based on Long Short-Term Memory networks to predict 24-hour proton flux profiles following SPE onsets. We used a dataset of 40 well-connected SPEs (1997-2017) observed by NOAA GOES, each associated with a >=M-class western-hemisphere solar flare and undisturbed proton flux profiles. Using 4-fold stratified cross-validation, we evaluate seq2seq model configurations (varying hidden units and embedding dimensions) under multiple forecasting scenarios: (i) proton-only input vs. combined proton+X-ray input, (ii) original flux data vs. trend-smoothed data, and (iii) autoregressive vs. one-shot forecasting. Our major results are as follows: First, one-shot forecasting consistently yields lower error than autoregressive prediction, avoiding the error accumulation seen in iterative approaches. Second, on the original data, proton-only models outperform proton+X-ray models. However, with trend-smoothed data, this gap narrows or reverses in proton+X-ray models. Third, trend-smoothing significantly enhances the performance of proton+X-ray models by mitigating fluctuations in the X-ray channel. Fourth, while models trained on trendsmoothed data perform best on average, the best-performing model was trained on original data, suggesting that architectural choices can sometimes outweigh the benefits of data preprocessing. △ Less

Submitted 6 October, 2025; originally announced October 2025.

Comments: 7 pages; accepted as a workshop paper at ICDM 2025

Neural Networks as Surrogate Solvers for Time-Dependent Accretion Disk Dynamics

Authors: Shunyuan Mao, Weiqi Wang, Sifan Wang, Ruobing Dong, Lu Lu, Kwang Moo Yi, Paris Perdikaris, Andrea Isella, Sébastien Fabbro, Lile Wang

Abstract: Accretion disks are ubiquitous in astrophysics, appearing in diverse environments from planet-forming systems to X-ray binaries and active galactic nuclei. Traditionally, modeling their dynamics requires computationally intensive (magneto)hydrodynamic simulations. Recently, Physics-Informed Neural Networks (PINNs) have emerged as a promising alternative. This approach trains neural networks direct… ▽ More Accretion disks are ubiquitous in astrophysics, appearing in diverse environments from planet-forming systems to X-ray binaries and active galactic nuclei. Traditionally, modeling their dynamics requires computationally intensive (magneto)hydrodynamic simulations. Recently, Physics-Informed Neural Networks (PINNs) have emerged as a promising alternative. This approach trains neural networks directly on physical laws without requiring data. We for the first time demonstrate PINNs for solving the two-dimensional, time-dependent hydrodynamics of non-self-gravitating accretion disks. Our models provide solutions at arbitrary times and locations within the training domain, and successfully reproduce key physical phenomena, including the excitation and propagation of spiral density waves and gap formation from disk-companion interactions. Notably, the boundary-free approach enabled by PINNs naturally eliminates the spurious wave reflections at disk edges, which are challenging to suppress in numerical simulations. These results highlight how advanced machine learning techniques can enable physics-driven, data-free modeling of complex astrophysical systems, potentially offering an alternative to traditional numerical simulations in the future. △ Less

Submitted 24 September, 2025; originally announced September 2025.

Comments: Astrophysical Journal Letters accepted; associate animations are available at https://doi.org/10.6084/m9.figshare.30192904

Strategies for Improving Communication Efficiency in Distributed and Federated Learning: Compression, Local Training, and Personalization

Authors: Kai Yi

Abstract: Distributed and federated learning are essential paradigms for training models across decentralized data sources while preserving privacy, yet communication overhead remains a major bottleneck. This dissertation explores strategies to improve communication efficiency, focusing on model compression, local training, and personalization. We establish a unified framework for biased and unbiased compre… ▽ More Distributed and federated learning are essential paradigms for training models across decentralized data sources while preserving privacy, yet communication overhead remains a major bottleneck. This dissertation explores strategies to improve communication efficiency, focusing on model compression, local training, and personalization. We establish a unified framework for biased and unbiased compression operators with convergence guarantees, then propose adaptive local training strategies that incorporate personalization to accelerate convergence and mitigate client drift. In particular, Scafflix balances global and personalized objectives, achieving superior performance under both IID and non-IID settings. We further introduce privacy-preserving pruning frameworks that optimize sparsity while minimizing communication costs, with Cohort-Squeeze leveraging hierarchical aggregation to reduce cross-device overhead. Finally, SymWanda, a symmetric post-training pruning method, enhances robustness under high sparsity and maintains accuracy without retraining. Extensive experiments on benchmarks and large-scale language models demonstrate favorable trade-offs among accuracy, convergence, and communication, offering theoretical and practical insights for scalable, efficient distributed learning. △ Less

Submitted 9 September, 2025; originally announced September 2025.

Comments: PhD Dissertation

A Lightweight Convolution and Vision Transformer integrated model with Multi-scale Self-attention Mechanism

Authors: Yi Zhang, Lingxiao Wei, Bowei Zhang, Ziwei Liu, Kai Yi, Shu Hu

Abstract: Vision Transformer (ViT) has prevailed in computer vision tasks due to its strong long-range dependency modelling ability. \textcolor{blue}{However, its large model size and weak local feature modeling ability hinder its application in real scenarios. To balance computation efficiency and performance in downstream vision tasks, we propose an efficient ViT model with sparse attention (dubbed SAEViT… ▽ More Vision Transformer (ViT) has prevailed in computer vision tasks due to its strong long-range dependency modelling ability. \textcolor{blue}{However, its large model size and weak local feature modeling ability hinder its application in real scenarios. To balance computation efficiency and performance in downstream vision tasks, we propose an efficient ViT model with sparse attention (dubbed SAEViT) and convolution blocks. Specifically, a Sparsely Aggregated Attention (SAA) module has been proposed to perform adaptive sparse sampling and recover the feature map via deconvolution operation,} which significantly reduces the computational complexity of attention operations. In addition, a Channel-Interactive Feed-Forward Network (CIFFN) layer is developed to enhance inter-channel information exchange through feature decomposition and redistribution, which mitigates the redundancy in traditional feed-forward networks (FFN). Finally, a hierarchical pyramid structure with embedded depth-wise separable convolutional blocks (DWSConv) is devised to further strengthen convolutional features. Extensive experiments on mainstream datasets show that SAEViT achieves Top-1 accuracies of 76.3\% and 79.6\% on the ImageNet-1K classification task with only 0.8 GFLOPs and 1.3 GFLOPs, respectively, demonstrating a lightweight solution for fundamental vision tasks. △ Less

Submitted 11 September, 2025; v1 submitted 22 August, 2025; originally announced August 2025.

Approximate DBSCAN under Differential Privacy

Authors: Yuan Qiu, Ke Yi

Abstract: This paper revisits the DBSCAN problem under differential privacy (DP). Existing DP-DBSCAN algorithms aim at publishing the cluster labels of the input points. However, we show that both empirically and theoretically, this approach cannot offer any utility in the published results. We therefore propose an alternative definition of DP-DBSCAN based on the notion of spans. We argue that publishing th… ▽ More This paper revisits the DBSCAN problem under differential privacy (DP). Existing DP-DBSCAN algorithms aim at publishing the cluster labels of the input points. However, we show that both empirically and theoretically, this approach cannot offer any utility in the published results. We therefore propose an alternative definition of DP-DBSCAN based on the notion of spans. We argue that publishing the spans actually better serves the purposes of visualization and classification of DBSCAN. Then we present a linear-time DP-DBSCAN algorithm achieving the sandwich quality guarantee in any constant dimensions, as well as matching lower bounds on the approximation ratio. A key building block in our algorithm is a linear-time algorithm for constructing a histogram under pure-DP, which is of independent interest. Finally, we conducted experiments on both synthetic and real-world datasets to verify the practical performance of our DP-DBSCAN algorithm. △ Less

Submitted 13 August, 2025; v1 submitted 12 August, 2025; originally announced August 2025.

All-atom inverse protein folding through discrete flow matching

Authors: Kai Yi, Kiarash Jamali, Sjors H. W. Scheres

Abstract: The recent breakthrough of AlphaFold3 in modeling complex biomolecular interactions, including those between proteins and ligands, nucleotides, or metal ions, creates new opportunities for protein design. In so-called inverse protein folding, the objective is to find a sequence of amino acids that adopts a target protein structure. Many inverse folding methods struggle to predict sequences for com… ▽ More The recent breakthrough of AlphaFold3 in modeling complex biomolecular interactions, including those between proteins and ligands, nucleotides, or metal ions, creates new opportunities for protein design. In so-called inverse protein folding, the objective is to find a sequence of amino acids that adopts a target protein structure. Many inverse folding methods struggle to predict sequences for complexes that contain non-protein components, and perform poorly with complexes that adopt multiple structural states. To address these challenges, we present ADFLIP (All-atom Discrete FLow matching Inverse Protein folding), a generative model based on discrete flow-matching for designing protein sequences conditioned on all-atom structural contexts. ADFLIP progressively incorporates predicted amino acid side chains as structural context during sequence generation and enables the design of dynamic protein complexes through ensemble sampling across multiple structural states. Furthermore, ADFLIP implements training-free classifier guidance sampling, which allows the incorporation of arbitrary pre-trained models to optimise the designed sequence for desired protein properties. We evaluated the performance of ADFLIP on protein complexes with small-molecule ligands, nucleotides, or metal ions, including dynamic complexes for which structure ensembles were determined by nuclear magnetic resonance (NMR). Our model achieves state-of-the-art performance in single-structure and multi-structure inverse folding tasks, demonstrating excellent potential for all-atom protein design. The code is available at https://github.com/ykiiiiii/ADFLIP. △ Less

Submitted 4 July, 2025; originally announced July 2025.

Comments: ICML2025

React-tRace: A Semantics for Understanding React Hooks

Authors: Jay Lee, Joongwon Ahn, Kwangkeun Yi

Abstract: React has become the most widely used web front-end framework, enabling the creation of user interfaces in a declarative and compositional manner. Hooks are a set of APIs that manage side effects in function components in React. However, their semantics are often seen as opaque to developers, leading to UI bugs. We introduce React-tRace, a formalization of the semantics of the essence of React Hoo… ▽ More React has become the most widely used web front-end framework, enabling the creation of user interfaces in a declarative and compositional manner. Hooks are a set of APIs that manage side effects in function components in React. However, their semantics are often seen as opaque to developers, leading to UI bugs. We introduce React-tRace, a formalization of the semantics of the essence of React Hooks, providing a semantics that clarifies their behavior. We demonstrate that our model captures the behavior of React, by theoretically showing that it embodies essential properties of Hooks and empirically comparing our React-tRace-definitional interpreter against a test suite. Furthermore, we showcase a practical visualization tool based on the formalization to demonstrate how developers can better understand the semantics of Hooks. △ Less

Submitted 21 August, 2025; v1 submitted 7 July, 2025; originally announced July 2025.

Comments: To be published in OOPSLA2 2025

How Particle System Theory Enhances Hypergraph Message Passing

Authors: Yixuan Ma, Kai Yi, Pietro Lio, Shi Jin, Yu Guang Wang

Abstract: Hypergraphs effectively model higher-order relationships in natural phenomena, capturing complex interactions beyond pairwise connections. We introduce a novel hypergraph message passing framework inspired by interacting particle systems, where hyperedges act as fields inducing shared node dynamics. By incorporating attraction, repulsion, and Allen-Cahn forcing terms, particles of varying classes… ▽ More Hypergraphs effectively model higher-order relationships in natural phenomena, capturing complex interactions beyond pairwise connections. We introduce a novel hypergraph message passing framework inspired by interacting particle systems, where hyperedges act as fields inducing shared node dynamics. By incorporating attraction, repulsion, and Allen-Cahn forcing terms, particles of varying classes and features achieve class-dependent equilibrium, enabling separability through the particle-driven message passing. We investigate both first-order and second-order particle system equations for modeling these dynamics, which mitigate over-smoothing and heterophily thus can capture complete interactions. The more stable second-order system permits deeper message passing. Furthermore, we enhance deterministic message passing with stochastic element to account for interaction uncertainties. We prove theoretically that our approach mitigates over-smoothing by maintaining a positive lower bound on the hypergraph Dirichlet energy during propagation and thus to enable hypergraph message passing to go deep. Empirically, our models demonstrate competitive performance on diverse real-world hypergraph node classification tasks, excelling on both homophilic and heterophilic datasets. △ Less

Submitted 24 May, 2025; originally announced May 2025.

Yannakakis+: Practical Acyclic Query Evaluation with Theoretical Guarantees

Authors: Qichen Wang, Bingnan Chen, Binyang Dai, Ke Yi, Feifei Li, Liang Lin

Abstract: Acyclic conjunctive queries form the backbone of most analytical workloads, and have been extensively studied in the literature from both theoretical and practical angles. However, there is still a large divide between theory and practice. While the 40-year-old Yannakakis algorithm has strong theoretical running time guarantees, it has not been adopted in real systems due to its high hidden consta… ▽ More Acyclic conjunctive queries form the backbone of most analytical workloads, and have been extensively studied in the literature from both theoretical and practical angles. However, there is still a large divide between theory and practice. While the 40-year-old Yannakakis algorithm has strong theoretical running time guarantees, it has not been adopted in real systems due to its high hidden constant factor. In this paper, we strive to close this gap by proposing Yannakakis+, an improved version of the Yannakakis algorithm, which is more practically efficient while preserving its theoretical guarantees. Our experiments demonstrate that Yannakakis+ consistently outperforms the original Yannakakis algorithm by 2x to 5x across a wide range of queries and datasets. Another nice feature of our new algorithm is that it generates a traditional DAG query plan consisting of standard relational operators, allowing Yannakakis+ to be easily plugged into any standard SQL engine. Our system prototype currently supports four different SQL engines (DuckDB, PostgreSQL, SparkSQL, and AnalyticDB from Alibaba Cloud), and our experiments show that Yannakakis+ is able to deliver better performance than their native query plans on 160 out of the 162 queries tested, with an average speedup of 2.41x and a maximum speedup of 47,059x. △ Less

Submitted 4 April, 2025; originally announced April 2025.

Comments: Technical report for the SIGMOD 2025 paper

ACM Class: H.2.4

StochasticSplats: Stochastic Rasterization for Sorting-Free 3D Gaussian Splatting

Authors: Shakiba Kheradmand, Delio Vicini, George Kopanas, Dmitry Lagun, Kwang Moo Yi, Mark Matthews, Andrea Tagliasacchi

Abstract: 3D Gaussian splatting (3DGS) is a popular radiance field method, with many application-specific extensions. Most variants rely on the same core algorithm: depth-sorting of Gaussian splats then rasterizing in primitive order. This ensures correct alpha compositing, but can cause rendering artifacts due to built-in approximations. Moreover, for a fixed representation, sorted rendering offers little… ▽ More 3D Gaussian splatting (3DGS) is a popular radiance field method, with many application-specific extensions. Most variants rely on the same core algorithm: depth-sorting of Gaussian splats then rasterizing in primitive order. This ensures correct alpha compositing, but can cause rendering artifacts due to built-in approximations. Moreover, for a fixed representation, sorted rendering offers little control over render cost and visual fidelity. For example, and counter-intuitively, rendering a lower-resolution image is not necessarily faster. In this work, we address the above limitations by combining 3D Gaussian splatting with stochastic rasterization. Concretely, we leverage an unbiased Monte Carlo estimator of the volume rendering equation. This removes the need for sorting, and allows for accurate 3D blending of overlapping Gaussians. The number of Monte Carlo samples further imbues 3DGS with a way to trade off computation time and quality. We implement our method using OpenGL shaders, enabling efficient rendering on modern GPU hardware. At a reasonable visual quality, our method renders more than four times faster than sorted rasterization. △ Less

Submitted 31 March, 2025; originally announced March 2025.

ROODI: Reconstructing Occluded Objects with Denoising Inpainters

Authors: Yeonjin Chang, Erqun Dong, Seunghyeon Seo, Nojun Kwak, Kwang Moo Yi

Abstract: While the quality of novel-view images has improved dramatically with 3D Gaussian Splatting, extracting specific objects from scenes remains challenging. Isolating individual 3D Gaussian primitives for each object and handling occlusions in scenes remains far from being solved. We propose a novel object extraction method based on two key principles: (1) object-centric reconstruction through remova… ▽ More While the quality of novel-view images has improved dramatically with 3D Gaussian Splatting, extracting specific objects from scenes remains challenging. Isolating individual 3D Gaussian primitives for each object and handling occlusions in scenes remains far from being solved. We propose a novel object extraction method based on two key principles: (1) object-centric reconstruction through removal of irrelevant primitives; and (2) leveraging generative inpainting to compensate for missing observations caused by occlusions. For pruning, we propose to remove irrelevant Gaussians by looking into how close they are to its K-nearest neighbors and removing those that are statistical outliers. Importantly, these distances must take into account the actual spatial extent they cover -- we thus propose to use Wasserstein distances. For inpainting, we employ an off-the-shelf diffusion-based inpainter combined with occlusion reasoning, utilizing the 3D representation of the entire scene. Our findings highlight the crucial synergy between proper pruning and inpainting, both of which significantly enhance extraction performance. We evaluate our method on a standard real-world dataset and introduce a synthetic dataset for quantitative analysis. Our approach outperforms the state-of-the-art, demonstrating its effectiveness in object extraction from complex scenes. △ Less

Submitted 9 August, 2025; v1 submitted 13 March, 2025; originally announced March 2025.

Comments: Project page: https://yeonjin-chang.github.io/ROODI/

NoKSR: Kernel-Free Neural Surface Reconstruction via Point Cloud Serialization

Authors: Zhen Li, Weiwei Sun, Shrisudhan Govindarajan, Shaobo Xia, Daniel Rebain, Kwang Moo Yi, Andrea Tagliasacchi

Abstract: We present a novel approach to large-scale point cloud surface reconstruction by developing an efficient framework that converts an irregular point cloud into a signed distance field (SDF). Our backbone builds upon recent transformer-based architectures (i.e., PointTransformerV3), that serializes the point cloud into a locality-preserving sequence of tokens. We efficiently predict the SDF value at… ▽ More We present a novel approach to large-scale point cloud surface reconstruction by developing an efficient framework that converts an irregular point cloud into a signed distance field (SDF). Our backbone builds upon recent transformer-based architectures (i.e., PointTransformerV3), that serializes the point cloud into a locality-preserving sequence of tokens. We efficiently predict the SDF value at a point by aggregating nearby tokens, where fast approximate neighbors can be retrieved thanks to the serialization. We serialize the point cloud at different levels/scales, and non-linearly aggregate a feature to predict the SDF value. We show that aggregating across multiple scales is critical to overcome the approximations introduced by the serialization (i.e. false negatives in the neighborhood). Our frameworks sets the new state-of-the-art in terms of accuracy and efficiency (better or similar performance with half the latency of the best prior method, coupled with a simpler implementation), particularly on outdoor datasets where sparse-grid methods have shown limited performance. △ Less

Submitted 18 February, 2025; v1 submitted 17 February, 2025; originally announced February 2025.

Comments: Project page: see https://theialab.github.io/noksr/

MedGNN: Towards Multi-resolution Spatiotemporal Graph Learning for Medical Time Series Classification

Authors: Wei Fan, Jingru Fei, Dingyu Guo, Kun Yi, Xiaozhuang Song, Haolong Xiang, Hangting Ye, Min Li

Abstract: Medical time series has been playing a vital role in real-world healthcare systems as valuable information in monitoring health conditions of patients. Accurate classification for medical time series, e.g., Electrocardiography (ECG) signals, can help for early detection and diagnosis. Traditional methods towards medical time series classification rely on handcrafted feature extraction and statisti… ▽ More Medical time series has been playing a vital role in real-world healthcare systems as valuable information in monitoring health conditions of patients. Accurate classification for medical time series, e.g., Electrocardiography (ECG) signals, can help for early detection and diagnosis. Traditional methods towards medical time series classification rely on handcrafted feature extraction and statistical methods; with the recent advancement of artificial intelligence, the machine learning and deep learning methods have become more popular. However, existing methods often fail to fully model the complex spatial dynamics under different scales, which ignore the dynamic multi-resolution spatial and temporal joint inter-dependencies. Moreover, they are less likely to consider the special baseline wander problem as well as the multi-view characteristics of medical time series, which largely hinders their prediction performance. To address these limitations, we propose a Multi-resolution Spatiotemporal Graph Learning framework, MedGNN, for medical time series classification. Specifically, we first propose to construct multi-resolution adaptive graph structures to learn dynamic multi-scale embeddings. Then, to address the baseline wander problem, we propose Difference Attention Networks to operate self-attention mechanisms on the finite difference for temporal modeling. Moreover, to learn the multi-view characteristics, we utilize the Frequency Convolution Networks to capture complementary information of medical time series from the frequency domain. In addition, we introduce the Multi-resolution Graph Transformer architecture to model the dynamic dependencies and fuse the information from different resolutions. Finally, we have conducted extensive experiments on multiple medical real-world datasets that demonstrate the superior performance of our method. Our Code is available. △ Less

Submitted 6 February, 2025; originally announced February 2025.

Comments: Accepted by WWW 2025

Radiant Foam: Real-Time Differentiable Ray Tracing

Authors: Shrisudhan Govindarajan, Daniel Rebain, Kwang Moo Yi, Andrea Tagliasacchi

Abstract: Research on differentiable scene representations is consistently moving towards more efficient, real-time models. Recently, this has led to the popularization of splatting methods, which eschew the traditional ray-based rendering of radiance fields in favor of rasterization. This has yielded a significant improvement in rendering speeds due to the efficiency of rasterization algorithms and hardwar… ▽ More Research on differentiable scene representations is consistently moving towards more efficient, real-time models. Recently, this has led to the popularization of splatting methods, which eschew the traditional ray-based rendering of radiance fields in favor of rasterization. This has yielded a significant improvement in rendering speeds due to the efficiency of rasterization algorithms and hardware, but has come at a cost: the approximations that make rasterization efficient also make implementation of light transport phenomena like reflection and refraction much more difficult. We propose a novel scene representation which avoids these approximations, but keeps the efficiency and reconstruction quality of splatting by leveraging a decades-old efficient volumetric mesh ray tracing algorithm which has been largely overlooked in recent computer vision research. The resulting model, which we name Radiant Foam, achieves rendering speed and quality comparable to Gaussian Splatting, without the constraints of rasterization. Unlike ray traced Gaussian models that use hardware ray tracing acceleration, our method requires no special hardware or APIs beyond the standard features of a programmable GPU. △ Less

Submitted 3 February, 2025; originally announced February 2025.

Symmetric Pruning of Large Language Models

Authors: Kai Yi, Peter Richtárik

Abstract: Popular post-training pruning methods such as Wanda and RIA are known for their simple, yet effective, designs that have shown exceptional empirical performance. Wanda optimizes performance through calibrated activations during pruning, while RIA emphasizes the relative, rather than absolute, importance of weight elements. Despite their practical success, a thorough theoretical foundation explaini… ▽ More Popular post-training pruning methods such as Wanda and RIA are known for their simple, yet effective, designs that have shown exceptional empirical performance. Wanda optimizes performance through calibrated activations during pruning, while RIA emphasizes the relative, rather than absolute, importance of weight elements. Despite their practical success, a thorough theoretical foundation explaining these outcomes has been lacking. This paper introduces new theoretical insights that redefine the standard minimization objective for pruning, offering a deeper understanding of the factors contributing to their success. Our study extends beyond these insights by proposing complementary strategies that consider both input activations and weight significance. We validate these approaches through rigorous experiments, demonstrating substantial enhancements over existing methods. Furthermore, we introduce a novel training-free fine-tuning approach $R^2$-DSnoT that incorporates relative weight importance and a regularized decision boundary within a dynamic pruning-and-growing framework, significantly outperforming strong baselines and establishing a new state of the art. △ Less

Submitted 31 January, 2025; originally announced January 2025.

Amplifier: Bringing Attention to Neglected Low-Energy Components in Time Series Forecasting

Authors: Jingru Fei, Kun Yi, Wei Fan, Qi Zhang, Zhendong Niu

Abstract: We propose an energy amplification technique to address the issue that existing models easily overlook low-energy components in time series forecasting. This technique comprises an energy amplification block and an energy restoration block. The energy amplification block enhances the energy of low-energy components to improve the model's learning efficiency for these components, while the energy r… ▽ More We propose an energy amplification technique to address the issue that existing models easily overlook low-energy components in time series forecasting. This technique comprises an energy amplification block and an energy restoration block. The energy amplification block enhances the energy of low-energy components to improve the model's learning efficiency for these components, while the energy restoration block returns the energy to its original level. Moreover, considering that the energy-amplified data typically displays two distinct energy peaks in the frequency spectrum, we integrate the energy amplification technique with a seasonal-trend forecaster to model the temporal relationships of these two peaks independently, serving as the backbone for our proposed model, Amplifier. Additionally, we propose a semi-channel interaction temporal relationship enhancement block for Amplifier, which enhances the model's ability to capture temporal relationships from the perspective of the commonality and specificity of each channel in the data. Extensive experiments on eight time series forecasting benchmarks consistently demonstrate our model's superiority in both effectiveness and efficiency compared to state-of-the-art methods. △ Less

Submitted 22 February, 2025; v1 submitted 28 January, 2025; originally announced January 2025.

Comments: Accepted by AAAI 2025

Dual Mutual Learning Network with Global-local Awareness for RGB-D Salient Object Detection

Authors: Kang Yi, Haoran Tang, Yumeng Li, Jing Xu, Jun Zhang

Abstract: RGB-D salient object detection (SOD), aiming to highlight prominent regions of a given scene by jointly modeling RGB and depth information, is one of the challenging pixel-level prediction tasks. Recently, the dual-attention mechanism has been devoted to this area due to its ability to strengthen the detection process. However, most existing methods directly fuse attentional cross-modality feature… ▽ More RGB-D salient object detection (SOD), aiming to highlight prominent regions of a given scene by jointly modeling RGB and depth information, is one of the challenging pixel-level prediction tasks. Recently, the dual-attention mechanism has been devoted to this area due to its ability to strengthen the detection process. However, most existing methods directly fuse attentional cross-modality features under a manual-mandatory fusion paradigm without considering the inherent discrepancy between the RGB and depth, which may lead to a reduction in performance. Moreover, the long-range dependencies derived from global and local information make it difficult to leverage a unified efficient fusion strategy. Hence, in this paper, we propose the GL-DMNet, a novel dual mutual learning network with global-local awareness. Specifically, we present a position mutual fusion module and a channel mutual fusion module to exploit the interdependencies among different modalities in spatial and channel dimensions. Besides, we adopt an efficient decoder based on cascade transformer-infused reconstruction to integrate multi-level fusion features jointly. Extensive experiments on six benchmark datasets demonstrate that our proposed GL-DMNet performs better than 24 RGB-D SOD methods, achieving an average improvement of ~3% across four evaluation metrics compared to the second-best model (S3Net). Codes and results are available at https://github.com/kingkung2016/GL-DMNet. △ Less

Submitted 3 January, 2025; originally announced January 2025.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models

Authors: Hyesong Choi, Daeun Kim, Sungmin Cha, Kwang Moo Yi, Dongbo Min

Abstract: In this work, we dive deep into the impact of additive noise in pre-training deep networks. While various methods have attempted to use additive noise inspired by the success of latent denoising diffusion models, when used in combination with masked image modeling, their gains have been marginal when it comes to recognition tasks. We thus investigate why this would be the case, in an attempt to fi… ▽ More In this work, we dive deep into the impact of additive noise in pre-training deep networks. While various methods have attempted to use additive noise inspired by the success of latent denoising diffusion models, when used in combination with masked image modeling, their gains have been marginal when it comes to recognition tasks. We thus investigate why this would be the case, in an attempt to find effective ways to combine the two ideas. Specifically, we find three critical conditions: corruption and restoration must be applied within the encoder, noise must be introduced in the feature space, and an explicit disentanglement between noised and masked tokens is necessary. By implementing these findings, we demonstrate improved pre-training performance for a wide range of recognition tasks, including those that require fine-grained, high-frequency information to solve. △ Less

Submitted 26 December, 2024; originally announced December 2024.

HyperNet Fields: Efficiently Training Hypernetworks without Ground Truth by Learning Weight Trajectories

Authors: Eric Hedlin, Munawar Hayat, Fatih Porikli, Kwang Moo Yi, Shweta Mahajan

Abstract: To efficiently adapt large models or to train generative models of neural representations, Hypernetworks have drawn interest. While hypernetworks work well, training them is cumbersome, and often requires ground truth optimized weights for each sample. However, obtaining each of these weights is a training problem of its own-one needs to train, e.g., adaptation weights or even an entire neural fie… ▽ More To efficiently adapt large models or to train generative models of neural representations, Hypernetworks have drawn interest. While hypernetworks work well, training them is cumbersome, and often requires ground truth optimized weights for each sample. However, obtaining each of these weights is a training problem of its own-one needs to train, e.g., adaptation weights or even an entire neural field for hypernetworks to regress to. In this work, we propose a method to train hypernetworks, without the need for any per-sample ground truth. Our key idea is to learn a Hypernetwork `Field` and estimate the entire trajectory of network weight training instead of simply its converged state. In other words, we introduce an additional input to the Hypernetwork, the convergence state, which then makes it act as a neural field that models the entire convergence pathway of a task network. A critical benefit in doing so is that the gradient of the estimated weights at any convergence state must then match the gradients of the original task -- this constraint alone is sufficient to train the Hypernetwork Field. We demonstrate the effectiveness of our method through the task of personalized image generation and 3D shape reconstruction from images and point clouds, demonstrating competitive results without any per-sample ground truth. △ Less

Submitted 19 May, 2025; v1 submitted 22 December, 2024; originally announced December 2024.

Score-matching-based Structure Learning for Temporal Data on Networks

Authors: Hao Chen, Kai Yi

Abstract: Causal discovery is a crucial initial step in establishing causality from empirical data and background knowledge. Numerous algorithms have been developed for this purpose. Among them, the score-matching method has demonstrated superior performance across various evaluation metrics, particularly for the commonly encountered Additive Nonlinear Causal Models. However, current score-matching-based al… ▽ More Causal discovery is a crucial initial step in establishing causality from empirical data and background knowledge. Numerous algorithms have been developed for this purpose. Among them, the score-matching method has demonstrated superior performance across various evaluation metrics, particularly for the commonly encountered Additive Nonlinear Causal Models. However, current score-matching-based algorithms are primarily designed to analyze independent and identically distributed (i.i.d.) data. More importantly, they suffer from high computational complexity due to the pruning step required for handling dense Directed Acyclic Graphs (DAGs). To enhance the scalability of score matching, we have developed a new parent-finding subroutine for leaf nodes in DAGs, significantly accelerating the most time-consuming part of the process: the pruning step. This improvement results in an efficiency-lifted score matching algorithm, termed Parent Identification-based Causal structure learning for both i.i.d. and temporal data on networKs, or PICK. The new score-matching algorithm extends the scope of existing algorithms and can handle static and temporal data on networks with weak network interference. Our proposed algorithm can efficiently cope with increasingly complex datasets that exhibit spatial and temporal dependencies, commonly encountered in academia and industry. The proposed algorithm can accelerate score-matching-based methods while maintaining high accuracy in real-world applications. △ Less

Submitted 12 April, 2026; v1 submitted 10 December, 2024; originally announced December 2024.

MANTA: A Large-Scale Multi-View and Visual-Text Anomaly Detection Dataset for Tiny Objects

Authors: Lei Fan, Dongdong Fan, Zhiguang Hu, Yiwen Ding, Donglin Di, Kai Yi, Maurice Pagnucco, Yang Song

Abstract: We present MANTA, a visual-text anomaly detection dataset for tiny objects. The visual component comprises over 137.3K images across 38 object categories spanning five typical domains, of which 8.6K images are labeled as anomalous with pixel-level annotations. Each image is captured from five distinct viewpoints to ensure comprehensive object coverage. The text component consists of two subsets: D… ▽ More We present MANTA, a visual-text anomaly detection dataset for tiny objects. The visual component comprises over 137.3K images across 38 object categories spanning five typical domains, of which 8.6K images are labeled as anomalous with pixel-level annotations. Each image is captured from five distinct viewpoints to ensure comprehensive object coverage. The text component consists of two subsets: Declarative Knowledge, including 875 words that describe common anomalies across various domains and specific categories, with detailed explanations for < what, why, how>, including causes and visual characteristics; and Constructivist Learning, providing 2K multiple-choice questions with varying levels of difficulty, each paired with images and corresponded answer explanations. We also propose a baseline for visual-text tasks and conduct extensive benchmarking experiments to evaluate advanced methods across different settings, highlighting the challenges and efficacy of our dataset. △ Less

Submitted 6 December, 2024; originally announced December 2024.

Comments: https://grainnet.github.io/MANTA

FilterNet: Harnessing Frequency Filters for Time Series Forecasting

Authors: Kun Yi, Jingru Fei, Qi Zhang, Hui He, Shufeng Hao, Defu Lian, Wei Fan

Abstract: While numerous forecasters have been proposed using different network architectures, the Transformer-based models have state-of-the-art performance in time series forecasting. However, forecasters based on Transformers are still suffering from vulnerability to high-frequency signals, efficiency in computation, and bottleneck in full-spectrum utilization, which essentially are the cornerstones for… ▽ More While numerous forecasters have been proposed using different network architectures, the Transformer-based models have state-of-the-art performance in time series forecasting. However, forecasters based on Transformers are still suffering from vulnerability to high-frequency signals, efficiency in computation, and bottleneck in full-spectrum utilization, which essentially are the cornerstones for accurately predicting time series with thousands of points. In this paper, we explore a novel perspective of enlightening signal processing for deep time series forecasting. Inspired by the filtering process, we introduce one simple yet effective network, namely FilterNet, built upon our proposed learnable frequency filters to extract key informative temporal patterns by selectively passing or attenuating certain components of time series signals. Concretely, we propose two kinds of learnable filters in the FilterNet: (i) Plain shaping filter, that adopts a universal frequency kernel for signal filtering and temporal modeling; (ii) Contextual shaping filter, that utilizes filtered frequencies examined in terms of its compatibility with input signals for dependency learning. Equipped with the two filters, FilterNet can approximately surrogate the linear and attention mappings widely adopted in time series literature, while enjoying superb abilities in handling high-frequency noises and utilizing the whole frequency spectrum that is beneficial for forecasting. Finally, we conduct extensive experiments on eight time series forecasting benchmarks, and experimental results have demonstrated our superior performance in terms of both effectiveness and efficiency compared with state-of-the-art methods. Code is available at this repository: https://github.com/aikunyi/FilterNet △ Less

Submitted 4 November, 2024; v1 submitted 3 November, 2024; originally announced November 2024.

Comments: Accepted by NeurIPS 2024

Rotated Runtime Smooth: Training-Free Activation Smoother for accurate INT4 inference

Authors: Ke Yi, Zengke Liu, Jianwei Zhang, Chengyuan Li, Tong Zhang, Junyang Lin, Jingren Zhou

Abstract: Large language models have demonstrated promising capabilities upon scaling up parameters. However, serving large language models incurs substantial computation and memory movement costs due to their large scale. Quantization methods have been employed to reduce service costs and latency. Nevertheless, outliers in activations hinder the development of INT4 weight-activation quantization. Existing… ▽ More Large language models have demonstrated promising capabilities upon scaling up parameters. However, serving large language models incurs substantial computation and memory movement costs due to their large scale. Quantization methods have been employed to reduce service costs and latency. Nevertheless, outliers in activations hinder the development of INT4 weight-activation quantization. Existing approaches separate outliers and normal values into two matrices or migrate outliers from activations to weights, suffering from high latency or accuracy degradation. Based on observing activations from large language models, outliers can be classified into channel-wise and spike outliers. In this work, we propose Rotated Runtime Smooth (RRS), a plug-and-play activation smoother for quantization, consisting of Runtime Smooth and the Rotation operation. Runtime Smooth (RS) is introduced to eliminate channel-wise outliers by smoothing activations with channel-wise maximums during runtime. The rotation operation can narrow the gap between spike outliers and normal values, alleviating the effect of victims caused by channel-wise smoothing. The proposed method outperforms the state-of-the-art method in the LLaMA and Qwen families and improves WikiText-2 perplexity from 57.33 to 6.66 for INT4 inference. △ Less

Submitted 11 November, 2024; v1 submitted 30 September, 2024; originally announced September 2024.

Disk2Planet: A Robust and Automated Machine Learning Tool for Parameter Inference in Disk-Planet Systems

Authors: Shunyuan Mao, Ruobing Dong, Kwang Moo Yi, Lu Lu, Sifan Wang, Paris Perdikaris

Abstract: We introduce Disk2Planet, a machine learning-based tool to infer key parameters in disk-planet systems from observed protoplanetary disk structures. Disk2Planet takes as input the disk structures in the form of two-dimensional density and velocity maps, and outputs disk and planet properties, that is, the Shakura--Sunyaev viscosity, the disk aspect ratio, the planet--star mass ratio, and the plane… ▽ More We introduce Disk2Planet, a machine learning-based tool to infer key parameters in disk-planet systems from observed protoplanetary disk structures. Disk2Planet takes as input the disk structures in the form of two-dimensional density and velocity maps, and outputs disk and planet properties, that is, the Shakura--Sunyaev viscosity, the disk aspect ratio, the planet--star mass ratio, and the planet's radius and azimuth. We integrate the Covariance Matrix Adaptation Evolution Strategy (CMA--ES), an evolutionary algorithm tailored for complex optimization problems, and the Protoplanetary Disk Operator Network (PPDONet), a neural network designed to predict solutions of disk--planet interactions. Our tool is fully automated and can retrieve parameters in one system in three minutes on an Nvidia A100 graphics processing unit. We empirically demonstrate that our tool achieves percent-level or higher accuracy, and is able to handle missing data and unknown levels of noise. △ Less

Submitted 25 September, 2024; originally announced September 2024.

Comments: Accepted to ApJ

Fundus image enhancement through direct diffusion bridges

Authors: Sehui Kim, Hyungjin Chung, Se Hie Park, Eui-Sang Chung, Kayoung Yi, Jong Chul Ye

Abstract: We propose FD3, a fundus image enhancement method based on direct diffusion bridges, which can cope with a wide range of complex degradations, including haze, blur, noise, and shadow. We first propose a synthetic forward model through a human feedback loop with board-certified ophthalmologists for maximal quality improvement of low-quality in-vivo images. Using the proposed forward model, we train… ▽ More We propose FD3, a fundus image enhancement method based on direct diffusion bridges, which can cope with a wide range of complex degradations, including haze, blur, noise, and shadow. We first propose a synthetic forward model through a human feedback loop with board-certified ophthalmologists for maximal quality improvement of low-quality in-vivo images. Using the proposed forward model, we train a robust and flexible diffusion-based image enhancement network that is highly effective as a stand-alone method, unlike previous diffusion model-based approaches which act only as a refiner on top of pre-trained models. Through extensive experiments, we show that FD3 establishes \add{superior quality} not only on synthetic degradations but also on in vivo studies with low-quality fundus photos taken from patients with cataracts or small pupils. To promote further research in this area, we open-source all our code and data used for this research at https://github.com/heeheee888/FD3 △ Less

Submitted 18 September, 2024; originally announced September 2024.

Comments: Published at IEEE JBHI. 12 pages, 10 figures. Code and Data: https://github.com/heeheee888/FD3

LSE-NeRF: Learning Sensor Modeling Errors for Deblured Neural Radiance Fields with RGB-Event Stereo

Authors: Wei Zhi Tang, Daniel Rebain, Kostantinos G. Derpanis, Kwang Moo Yi

Abstract: We present a method for reconstructing a clear Neural Radiance Field (NeRF) even with fast camera motions. To address blur artifacts, we leverage both (blurry) RGB images and event camera data captured in a binocular configuration. Importantly, when reconstructing our clear NeRF, we consider the camera modeling imperfections that arise from the simple pinhole camera model as learned embeddings for… ▽ More We present a method for reconstructing a clear Neural Radiance Field (NeRF) even with fast camera motions. To address blur artifacts, we leverage both (blurry) RGB images and event camera data captured in a binocular configuration. Importantly, when reconstructing our clear NeRF, we consider the camera modeling imperfections that arise from the simple pinhole camera model as learned embeddings for each camera measurement, and further learn a mapper that connects event camera measurements with RGB data. As no previous dataset exists for our binocular setting, we introduce an event camera dataset with captures from a 3D-printed stereo configuration between RGB and event cameras. Empirically, we evaluate our introduced dataset and EVIMOv2 and show that our method leads to improved reconstructions. Our code and dataset are available at https://github.com/ubc-vision/LSENeRF. △ Less

Submitted 9 September, 2024; originally announced September 2024.

NESI: Shape Representation via Neural Explicit Surface Intersection

Authors: Congyi Zhang, Jinfan Yang, Eric Hedlin, Suzuran Takikawa, Nicholas Vining, Kwang Moo Yi, Wenping Wang, Alla Sheffer

Abstract: Compressed representations of 3D shapes that are compact, accurate, and can be processed efficiently directly in compressed form, are extremely useful for digital media applications. Recent approaches in this space focus on learned implicit or parametric representations. While implicits are well suited for tasks such as in-out queries, they lack natural 2D parameterization, complicating tasks such… ▽ More Compressed representations of 3D shapes that are compact, accurate, and can be processed efficiently directly in compressed form, are extremely useful for digital media applications. Recent approaches in this space focus on learned implicit or parametric representations. While implicits are well suited for tasks such as in-out queries, they lack natural 2D parameterization, complicating tasks such as texture or normal mapping. Conversely, parametric representations support the latter tasks but are ill-suited for occupancy queries. We propose a novel learned alternative to these approaches, based on intersections of localized explicit, or height-field, surfaces. Since explicits can be trivially expressed both implicitly and parametrically, NESI directly supports a wider range of processing operations than implicit alternatives, including occupancy queries and parametric access. We represent input shapes using a collection of differently oriented height-field bounded half-spaces combined using volumetric Boolean intersections. We first tightly bound each input using a pair of oppositely oriented height-fields, forming a Double Height-Field (DHF) Hull. We refine this hull by intersecting it with additional localized height-fields (HFs) that capture surface regions in its interior. We minimize the number of HFs necessary to accurately capture each input and compactly encode both the DHF hull and the local HFs as neural functions defined over subdomains of R^2. This reduced dimensionality encoding delivers high-quality compact approximations. Given similar parameter count, or storage capacity, NESI significantly reduces approximation error compared to the state of the art, especially at lower parameter counts. △ Less

Submitted 9 September, 2024; originally announced September 2024.

Lagrangian Hashing for Compressed Neural Field Representations

Authors: Shrisudhan Govindarajan, Zeno Sambugaro, Akhmedkhan, Shabanov, Towaki Takikawa, Daniel Rebain, Weiwei Sun, Nicola Conci, Kwang Moo Yi, Andrea Tagliasacchi

Abstract: We present Lagrangian Hashing, a representation for neural fields combining the characteristics of fast training NeRF methods that rely on Eulerian grids (i.e.~InstantNGP), with those that employ points equipped with features as a way to represent information (e.g. 3D Gaussian Splatting or PointNeRF). We achieve this by incorporating a point-based representation into the high-resolution layers of… ▽ More We present Lagrangian Hashing, a representation for neural fields combining the characteristics of fast training NeRF methods that rely on Eulerian grids (i.e.~InstantNGP), with those that employ points equipped with features as a way to represent information (e.g. 3D Gaussian Splatting or PointNeRF). We achieve this by incorporating a point-based representation into the high-resolution layers of the hierarchical hash tables of an InstantNGP representation. As our points are equipped with a field of influence, our representation can be interpreted as a mixture of Gaussians stored within the hash table. We propose a loss that encourages the movement of our Gaussians towards regions that require more representation budget to be sufficiently well represented. Our main finding is that our representation allows the reconstruction of signals using a more compact representation without compromising quality. △ Less

Submitted 9 September, 2024; originally announced September 2024.

Comments: Project page: https://theialab.github.io/laghashes/

Compositional Physical Reasoning of Objects and Events from Videos

Authors: Zhenfang Chen, Shilong Dong, Kexin Yi, Yunzhu Li, Mingyu Ding, Antonio Torralba, Joshua B. Tenenbaum, Chuang Gan

Abstract: Understanding and reasoning about objects' physical properties in the natural world is a fundamental challenge in artificial intelligence. While some properties like colors and shapes can be directly observed, others, such as mass and electric charge, are hidden from the objects' visual appearance. This paper addresses the unique challenge of inferring these hidden physical properties from objects… ▽ More Understanding and reasoning about objects' physical properties in the natural world is a fundamental challenge in artificial intelligence. While some properties like colors and shapes can be directly observed, others, such as mass and electric charge, are hidden from the objects' visual appearance. This paper addresses the unique challenge of inferring these hidden physical properties from objects' motion and interactions and predicting corresponding dynamics based on the inferred physical properties. We first introduce the Compositional Physical Reasoning (ComPhy) dataset. For a given set of objects, ComPhy includes limited videos of them moving and interacting under different initial conditions. The model is evaluated based on its capability to unravel the compositional hidden properties, such as mass and charge, and use this knowledge to answer a set of questions. Besides the synthetic videos from simulators, we also collect a real-world dataset to show further test physical reasoning abilities of different models. We evaluate state-of-the-art video reasoning models on ComPhy and reveal their limited ability to capture these hidden properties, which leads to inferior performance. We also propose a novel neuro-symbolic framework, Physical Concept Reasoner (PCR), that learns and reasons about both visible and hidden physical properties from question answering. After training, PCR demonstrates remarkable capabilities. It can detect and associate objects across frames, ground visible and hidden physical properties, make future and counterfactual predictions, and utilize these extracted representations to answer challenging questions. △ Less

Submitted 26 May, 2025; v1 submitted 2 August, 2024; originally announced August 2024.

Comments: Accepted by TPAMI 2025. arXiv admin note: text overlap with arXiv:2205.01089

Robust Multivariate Time Series Forecasting against Intra- and Inter-Series Transitional Shift

Authors: Hui He, Qi Zhang, Kun Yi, Xiaojun Xue, Shoujin Wang, Liang Hu, Longbing Cao

Abstract: The non-stationary nature of real-world Multivariate Time Series (MTS) data presents forecasting models with a formidable challenge of the time-variant distribution of time series, referred to as distribution shift. Existing studies on the distribution shift mostly adhere to adaptive normalization techniques for alleviating temporal mean and covariance shifts or time-variant modeling for capturing… ▽ More The non-stationary nature of real-world Multivariate Time Series (MTS) data presents forecasting models with a formidable challenge of the time-variant distribution of time series, referred to as distribution shift. Existing studies on the distribution shift mostly adhere to adaptive normalization techniques for alleviating temporal mean and covariance shifts or time-variant modeling for capturing temporal shifts. Despite improving model generalization, these normalization-based methods often assume a time-invariant transition between outputs and inputs but disregard specific intra-/inter-series correlations, while time-variant models overlook the intrinsic causes of the distribution shift. This limits model expressiveness and interpretability of tackling the distribution shift for MTS forecasting. To mitigate such a dilemma, we present a unified Probabilistic Graphical Model to Jointly capturing intra-/inter-series correlations and modeling the time-variant transitional distribution, and instantiate a neural framework called JointPGM for non-stationary MTS forecasting. Specifically, JointPGM first employs multiple Fourier basis functions to learn dynamic time factors and designs two distinct learners: intra-series and inter-series learners. The intra-series learner effectively captures temporal dynamics by utilizing temporal gates, while the inter-series learner explicitly models spatial dynamics through multi-hop propagation, incorporating Gumbel-softmax sampling. These two types of series dynamics are subsequently fused into a latent variable, which is inversely employed to infer time factors, generate final prediction, and perform reconstruction. We validate the effectiveness and efficiency of JointPGM through extensive experiments on six highly non-stationary MTS datasets, achieving state-of-the-art forecasting performance of MTS forecasting. △ Less

Submitted 18 July, 2024; originally announced July 2024.

Comments: 19 pages, 11 figures

MSC Class: 68Txx ACM Class: I.2.6

Deep Frequency Derivative Learning for Non-stationary Time Series Forecasting

Authors: Wei Fan, Kun Yi, Hangting Ye, Zhiyuan Ning, Qi Zhang, Ning An

Abstract: While most time series are non-stationary, it is inevitable for models to face the distribution shift issue in time series forecasting. Existing solutions manipulate statistical measures (usually mean and std.) to adjust time series distribution. However, these operations can be theoretically seen as the transformation towards zero frequency component of the spectrum which cannot reveal full distr… ▽ More While most time series are non-stationary, it is inevitable for models to face the distribution shift issue in time series forecasting. Existing solutions manipulate statistical measures (usually mean and std.) to adjust time series distribution. However, these operations can be theoretically seen as the transformation towards zero frequency component of the spectrum which cannot reveal full distribution information and would further lead to information utilization bottleneck in normalization, thus hindering forecasting performance. To address this problem, we propose to utilize the whole frequency spectrum to transform time series to make full use of data distribution from the frequency perspective. We present a deep frequency derivative learning framework, DERITS, for non-stationary time series forecasting. Specifically, DERITS is built upon a novel reversible transformation, namely Frequency Derivative Transformation (FDT) that makes signals derived in the frequency domain to acquire more stationary frequency representations. Then, we propose the Order-adaptive Fourier Convolution Network to conduct adaptive frequency filtering and learning. Furthermore, we organize DERITS as a parallel-stacked architecture for the multi-order derivation and fusion for forecasting. Finally, we conduct extensive experiments on several datasets which show the consistent superiority in both time series forecasting and shift alleviation. △ Less

Submitted 29 June, 2024; originally announced July 2024.

Comments: Accepted by IJCAI 2024

M3GIA: A Cognition Inspired Multilingual and Multimodal General Intelligence Ability Benchmark

Authors: Wei Song, Yadong Li, Jianhua Xu, Guowei Wu, Lingfeng Ming, Kexin Yi, Weihua Luo, Houyi Li, Yi Du, Fangda Guo, Kaicheng Yu

Abstract: As recent multi-modality large language models (MLLMs) have shown formidable proficiency on various complex tasks, there has been increasing attention on debating whether these models could eventually mirror human intelligence. However, existing benchmarks mainly focus on evaluating solely on task performance, such as the accuracy of identifying the attribute of an object. Combining well-developed… ▽ More As recent multi-modality large language models (MLLMs) have shown formidable proficiency on various complex tasks, there has been increasing attention on debating whether these models could eventually mirror human intelligence. However, existing benchmarks mainly focus on evaluating solely on task performance, such as the accuracy of identifying the attribute of an object. Combining well-developed cognitive science to understand the intelligence of MLLMs beyond superficial achievements remains largely unexplored. To this end, we introduce the first cognitive-driven multi-lingual and multi-modal benchmark to evaluate the general intelligence ability of MLLMs, dubbed M3GIA. Specifically, we identify five key cognitive factors based on the well-recognized Cattell-Horn-Carrol (CHC) model of intelligence and propose a novel evaluation metric. In addition, since most MLLMs are trained to perform in different languages, a natural question arises: is language a key factor influencing the cognitive ability of MLLMs? As such, we go beyond English to encompass other languages based on their popularity, including Chinese, French, Spanish, Portuguese and Korean, to construct our M3GIA. We make sure all the data relevant to the cultural backgrounds are collected from their native context to avoid English-centric bias. We collected a significant corpus of data from human participants, revealing that the most advanced MLLM reaches the lower boundary of human intelligence in English. Yet, there remains a pronounced disparity in the other five languages assessed. We also reveals an interesting winner takes all phenomenon that are aligned with the discovery in cognitive studies. Our benchmark will be open-sourced, with the aspiration of facilitating the enhancement of cognitive capabilities in MLLMs. △ Less

Submitted 14 June, 2024; v1 submitted 8 June, 2024; originally announced June 2024.

MLIP: Efficient Multi-Perspective Language-Image Pretraining with Exhaustive Data Utilization

Authors: Yu Zhang, Qi Zhang, Zixuan Gong, Yiwei Shi, Yepeng Liu, Duoqian Miao, Yang Liu, Ke Liu, Kun Yi, Wei Fan, Liang Hu, Changwei Wang

Abstract: Contrastive Language-Image Pretraining (CLIP) has achieved remarkable success, leading to rapid advancements in multimodal studies. However, CLIP faces a notable challenge in terms of inefficient data utilization. It relies on a single contrastive supervision for each image-text pair during representation learning, disregarding a substantial amount of valuable information that could offer richer s… ▽ More Contrastive Language-Image Pretraining (CLIP) has achieved remarkable success, leading to rapid advancements in multimodal studies. However, CLIP faces a notable challenge in terms of inefficient data utilization. It relies on a single contrastive supervision for each image-text pair during representation learning, disregarding a substantial amount of valuable information that could offer richer supervision. Additionally, the retention of non-informative tokens leads to increased computational demands and time costs, particularly in CLIP's ViT image encoder. To address these issues, we propose Multi-Perspective Language-Image Pretraining (MLIP). In MLIP, we leverage the frequency transform's sensitivity to both high and low-frequency variations, which complements the spatial domain's sensitivity limited to low-frequency variations only. By incorporating frequency transforms and token-level alignment, we expand CILP's single supervision into multi-domain and multi-level supervision, enabling a more thorough exploration of informative image features. Additionally, we introduce a token merging method guided by comprehensive semantics from the frequency and spatial domains. This allows us to merge tokens to multi-granularity tokens with a controllable compression rate to accelerate CLIP. Extensive experiments validate the effectiveness of our design. △ Less

Submitted 4 June, 2024; v1 submitted 3 June, 2024; originally announced June 2024.

Comments: ICML 2024

Cohort Squeeze: Beyond a Single Communication Round per Cohort in Cross-Device Federated Learning

Authors: Kai Yi, Timur Kharisov, Igor Sokolov, Peter Richtárik

Abstract: Virtually all federated learning (FL) methods, including FedAvg, operate in the following manner: i) an orchestrating server sends the current model parameters to a cohort of clients selected via certain rule, ii) these clients then independently perform a local training procedure (e.g., via SGD or Adam) using their own training data, and iii) the resulting models are shipped to the server for agg… ▽ More Virtually all federated learning (FL) methods, including FedAvg, operate in the following manner: i) an orchestrating server sends the current model parameters to a cohort of clients selected via certain rule, ii) these clients then independently perform a local training procedure (e.g., via SGD or Adam) using their own training data, and iii) the resulting models are shipped to the server for aggregation. This process is repeated until a model of suitable quality is found. A notable feature of these methods is that each cohort is involved in a single communication round with the server only. In this work we challenge this algorithmic design primitive and investigate whether it is possible to ``squeeze more juice" out of each cohort than what is possible in a single communication round. Surprisingly, we find that this is indeed the case, and our approach leads to up to 74% reduction in the total communication cost needed to train a FL model in the cross-device setting. Our method is based on a novel variant of the stochastic proximal point method (SPPM-AS) which supports a large collection of client sampling procedures some of which lead to further gains when compared to classical client selection approaches. △ Less

Submitted 3 June, 2024; originally announced June 2024.

Sparse-ProxSkip: Accelerated Sparse-to-Sparse Training in Federated Learning

Authors: Georg Meinhardt, Kai Yi, Laurent Condat, Peter Richtárik

Abstract: In Federated Learning (FL), both client resource constraints and communication costs pose major problems for training large models. In the centralized setting, sparse training addresses resource constraints, while in the distributed setting, local training addresses communication costs. Recent work has shown that local training provably improves communication complexity through acceleration. In th… ▽ More In Federated Learning (FL), both client resource constraints and communication costs pose major problems for training large models. In the centralized setting, sparse training addresses resource constraints, while in the distributed setting, local training addresses communication costs. Recent work has shown that local training provably improves communication complexity through acceleration. In this work we show that in FL, naive integration of sparse training and acceleration fails, and we provide theoretical and empirical explanations of this phenomenon. We introduce Sparse-ProxSkip, addressing the issue and implementing the efficient technique of Straight-Through Estimator pruning into sparse training. We demonstrate the performance of Sparse-ProxSkip in extensive experiments. △ Less

Submitted 28 February, 2025; v1 submitted 31 May, 2024; originally announced May 2024.

One QuantLLM for ALL: Fine-tuning Quantized LLMs Once for Efficient Deployments

Authors: Ke Yi, Yuhui Xu, Heng Chang, Chen Tang, Yuan Meng, Tong Zhang, Jia Li

Abstract: Large Language Models (LLMs) have advanced rapidly but face significant memory demands. While quantization has shown promise for LLMs, current methods typically require lengthy training to alleviate the performance degradation from quantization loss. However, deploying LLMs across diverse scenarios with different resource constraints, e.g., servers and personal computers, requires repeated trainin… ▽ More Large Language Models (LLMs) have advanced rapidly but face significant memory demands. While quantization has shown promise for LLMs, current methods typically require lengthy training to alleviate the performance degradation from quantization loss. However, deploying LLMs across diverse scenarios with different resource constraints, e.g., servers and personal computers, requires repeated training per application, which amplifies the lengthy training problem. Given that, it is advantageous to train a once-for-all (OFA) supernet capable of yielding diverse optimal subnets for downstream applications through one-shot training. Nonetheless, the scale of current language models impedes efficiency and amplifies interference from weight sharing between subnets. We make an initial attempt to extend the once-for-all framework to large language models. Specifically, we decouple shared weights to eliminate the interference and incorporate Low-Rank adapters for training efficiency. Furthermore, we observe the imbalance allocation of training resources from the traditional uniform sampling. A non-parametric scheduler is introduced to adjust the sampling rate for each quantization configuration, achieving a more balanced allocation among subnets with varying demands. We validate the approach on LLaMA2 families, and downstream evaluation confirms our ability to maintain high performance while significantly reducing deployment time faced with multiple scenarios. △ Less

Submitted 30 May, 2024; originally announced May 2024.

PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression

Authors: Vladimir Malinovskii, Denis Mazur, Ivan Ilin, Denis Kuznedelev, Konstantin Burlachenko, Kai Yi, Dan Alistarh, Peter Richtarik

Abstract: There has been significant interest in "extreme" compression of large language models (LLMs), i.e., to 1-2 bits per parameter, which allows such models to be executed efficiently on resource-constrained devices. Existing work focused on improved one-shot quantization techniques and weight representations; yet, purely post-training approaches are reaching diminishing returns in terms of the accurac… ▽ More There has been significant interest in "extreme" compression of large language models (LLMs), i.e., to 1-2 bits per parameter, which allows such models to be executed efficiently on resource-constrained devices. Existing work focused on improved one-shot quantization techniques and weight representations; yet, purely post-training approaches are reaching diminishing returns in terms of the accuracy-vs-bit-width trade-off. State-of-the-art quantization methods such as QuIP# and AQLM include fine-tuning (part of) the compressed parameters over a limited amount of calibration data; however, such fine-tuning techniques over compressed weights often make exclusive use of straight-through estimators (STE), whose performance is not well-understood in this setting. In this work, we question the use of STE for extreme LLM compression, showing that it can be sub-optimal, and perform a systematic study of quantization-aware fine-tuning strategies for LLMs. We propose PV-Tuning - a representation-agnostic framework that generalizes and improves upon existing fine-tuning strategies, and provides convergence guarantees in restricted cases. On the practical side, when used for 1-2 bit vector quantization, PV-Tuning outperforms prior techniques for highly-performant models such as Llama and Mistral. Using PV-Tuning, we achieve the first Pareto-optimal quantization for Llama 2 family models at 2 bits per parameter. △ Less

Submitted 30 May, 2024; v1 submitted 23 May, 2024; originally announced May 2024.

Comments: Preprint

Smooth Sensitivity for Geo-Privacy

Authors: Yuting Liang, Ke Yi

Abstract: Suppose each user $i$ holds a private value $x_i$ in some metric space $(U, \mathrm{dist})$, and an untrusted data analyst wishes to compute $\sum_i f(x_i)$ for some function $f : U \rightarrow \mathbb{R}$ by asking each user to send in a privatized $f(x_i)$. This is a fundamental problem in privacy-preserving population analytics, and the local model of differential privacy (LDP) is the predomina… ▽ More Suppose each user $i$ holds a private value $x_i$ in some metric space $(U, \mathrm{dist})$, and an untrusted data analyst wishes to compute $\sum_i f(x_i)$ for some function $f : U \rightarrow \mathbb{R}$ by asking each user to send in a privatized $f(x_i)$. This is a fundamental problem in privacy-preserving population analytics, and the local model of differential privacy (LDP) is the predominant model under which the problem has been studied. However, LDP requires any two different $x_i, x'_i$ to be $\varepsilon$-distinguishable, which can be overly strong for geometric/numerical data. On the other hand, Geo-Privacy (GP) stipulates that the level of distinguishability be proportional to $\mathrm{dist}(x_i, x_i')$, providing an attractive alternative notion of personal data privacy in a metric space. However, existing GP mechanisms for this problem, which add a uniform noise to either $x_i$ or $f(x_i)$, are not satisfactory. In this paper, we generalize the smooth sensitivity framework from Differential Privacy to Geo-Privacy, which allows us to add noise tailored to the hardness of the given instance. We provide definitions, mechanisms, and a generic procedure for computing the smooth sensitivity under GP equipped with a general metric. Then we present three applications: one-way and two-way threshold functions, and Gaussian kernel density estimation, to demonstrate the applicability and utility of our smooth sensitivity framework. △ Less

Submitted 10 May, 2024; originally announced May 2024.

Towards Consistent Object Detection via LiDAR-Camera Synergy

Authors: Kai Luo, Hao Wu, Kefu Yi, Kailun Yang, Wei Hao, Rongdong Hu

Abstract: As human-machine interaction continues to evolve, the capacity for environmental perception is becoming increasingly crucial. Integrating the two most common types of sensory data, images, and point clouds, can enhance detection accuracy. Currently, there is no existing model capable of detecting an object's position in both point clouds and images while also determining their corresponding relati… ▽ More As human-machine interaction continues to evolve, the capacity for environmental perception is becoming increasingly crucial. Integrating the two most common types of sensory data, images, and point clouds, can enhance detection accuracy. Currently, there is no existing model capable of detecting an object's position in both point clouds and images while also determining their corresponding relationship. This information is invaluable for human-machine interactions, offering new possibilities for their enhancement. In light of this, this paper introduces an end-to-end Consistency Object Detection (COD) algorithm framework that requires only a single forward inference to simultaneously obtain an object's position in both point clouds and images and establish their correlation. Furthermore, to assess the accuracy of the object correlation between point clouds and images, this paper proposes a new evaluation metric, Consistency Precision (CP). To verify the effectiveness of the proposed framework, an extensive set of experiments has been conducted on the KITTI and DAIR-V2X datasets. The study also explored how the proposed consistency detection method performs on images when the calibration parameters between images and point clouds are disturbed, compared to existing post-processing methods. The experimental results demonstrate that the proposed method exhibits excellent detection performance and robustness, achieving end-to-end consistency detection. The source code will be made publicly available at https://github.com/xifen523/COD. △ Less

Submitted 9 August, 2024; v1 submitted 2 May, 2024; originally announced May 2024.

Comments: Accepted to IEEE SMC 2024. The source code will be made publicly available at https://github.com/xifen523/COD

SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation

Authors: Yuying Ge, Sijie Zhao, Jinguo Zhu, Yixiao Ge, Kun Yi, Lin Song, Chen Li, Xiaohan Ding, Ying Shan

Abstract: The rapid evolution of multimodal foundation model has demonstrated significant progresses in vision-language understanding and generation, e.g., our previous work SEED-LLaMA. However, there remains a gap between its capability and the real-world applicability, primarily due to the model's limited capacity to effectively respond to various user instructions and interact with diverse visual data. I… ▽ More The rapid evolution of multimodal foundation model has demonstrated significant progresses in vision-language understanding and generation, e.g., our previous work SEED-LLaMA. However, there remains a gap between its capability and the real-world applicability, primarily due to the model's limited capacity to effectively respond to various user instructions and interact with diverse visual data. In this work, we focus on bridging this gap through integrating two enhanced features: (1) comprehending images of arbitrary sizes and ratios, and (2) enabling multi-granularity image generation. We present a unified and versatile foundation model, namely, SEED-X, which is able to model multi-granularity visual semantics for comprehension and generation tasks. Besides the competitive results on public benchmarks, SEED-X demonstrates its effectiveness in handling real-world applications across various domains after instruction tuning. We hope that our work will inspire future research into what can be achieved by versatile multimodal foundation models in real-world applications. The models, codes, and datasets are released in https://github.com/AILab-CVC/SEED-X. △ Less

Submitted 2 March, 2025; v1 submitted 22 April, 2024; originally announced April 2024.

Comments: We added benchmark results (without updating models) and ablation study in this version. Project released at: https://github.com/AILab-CVC/SEED-X

Wills Aligner: Multi-Subject Collaborative Brain Visual Decoding

Authors: Guangyin Bao, Qi Zhang, Zixuan Gong, Jialei Zhou, Wei Fan, Kun Yi, Usman Naseem, Liang Hu, Duoqian Miao

Abstract: Decoding visual information from human brain activity has seen remarkable advancements in recent research. However, the diversity in cortical parcellation and fMRI patterns across individuals has prompted the development of deep learning models tailored to each subject. The personalization limits the broader applicability of brain visual decoding in real-world scenarios. To address this issue, we… ▽ More Decoding visual information from human brain activity has seen remarkable advancements in recent research. However, the diversity in cortical parcellation and fMRI patterns across individuals has prompted the development of deep learning models tailored to each subject. The personalization limits the broader applicability of brain visual decoding in real-world scenarios. To address this issue, we introduce Wills Aligner, a novel approach designed to achieve multi-subject collaborative brain visual decoding. Wills Aligner begins by aligning the fMRI data from different subjects at the anatomical level. It then employs delicate mixture-of-brain-expert adapters and a meta-learning strategy to account for individual fMRI pattern differences. Additionally, Wills Aligner leverages the semantic relation of visual stimuli to guide the learning of inter-subject commonality, enabling visual decoding for each subject to draw insights from other subjects' data. We rigorously evaluate our Wills Aligner across various visual decoding tasks, including classification, cross-modal retrieval, and image reconstruction. The experimental results demonstrate that Wills Aligner achieves promising performance. △ Less

Submitted 16 December, 2024; v1 submitted 20 April, 2024; originally announced April 2024.

Comments: AAAI 2025, 16 pages