arXivSub Start free trial

ICML 2024 Papers with Code β€” Page 4

International Conference on Machine Learning Β· 550 papers

LLM Maybe LongLM: SelfExtend LLM Context Window Without Tuning

Hongye Jin (Texas A&M University), Xia Hu (Rice University)

CodeTransformerLarge Language ModelText

🎯 What it does: The SelfExtend method is proposed, which expands the context window of large language models without fine-tuning during the inference phase by mapping unseen relative positional information and combining hierarchical attention (grouped attention and adjacent normal attention).

LLM-Empowered State Representation for Reinforcement Learning

Boyuan Wang (Tsinghua University), Xiangyang Ji (Tsinghua University)

CodeLarge Language ModelReinforcement LearningTabularBenchmark

🎯 What it does: Utilizing LLM to automatically generate task-related state representations and intrinsic reward functions, improving the quality of state representation in RL and accelerating learning.

Local Causal Structure Learning in the Presence of Latent Variables

Feng Xie (Beijing Technology and Business University), Zhi Geng (Beijing Technology and Business University)

CodeGraphTabular

🎯 What it does: An algorithm is proposed to accurately discover the direct causal relationships of a given target variable using local structure learning (MMB-by-MMB) in the presence of latent variables.

Logistic Variational Bayes Revisited

Michael Komodromos (Imperial College London), Sarah Lucie Filippi

CodeClassificationOptimizationReinforcement LearningTabular

🎯 What it does: This paper proposes a new upper bound for the expected softplus function and applies it to variational logistic regression and Gaussian process classification, introducing the VI-PER method.

Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts

Jiang-Xin Shi (Nanjing University), Yu-Feng Li (Nanjing University)

CodeClassificationData-Centric LearningTransformerSupervised Fine-TuningContrastive LearningImage

🎯 What it does: This paper demonstrates that full fine-tuning leads to a decline in tail class performance in long-tail learning tasks by comparing full fine-tuning and lightweight fine-tuning, and proposes a lightweight fine-tuning framework called LIFT, which can achieve high accuracy with very few learnable parameters in a short time.

Longitudinal Targeted Minimum Loss-based Estimation with Temporal-Difference Heterogeneous Transformer

Toru Shirakawa (Osaka University), Mark J. van der Laan

CodeTransformerTime SeriesSequential

🎯 What it does: This paper proposes a deep longitudinal TMLE method based on Transformer (Deep LTMLE) for estimating causal average outcomes under dynamic interventions.

LoRA Training in the NTK Regime has No Spurious Local Minima

Uijeong Jang (Seoul National University), Ernest K. Ryu (University of California)

CodeOptimizationTransformerSupervised Fine-TuningImageTextAudio

🎯 What it does: The theoretical analysis of LoRA (Low-Rank Adaptation) fine-tuning under the NTK (Neural Tangent Kernel) framework proves the existence of a global optimal solution with a rank of √N, and when the rank r ≳ √N, the optimization landscape has no spurious local minima, allowing gradient descent to converge to a low-rank global optimum, which also exhibits good generalization performance.

LQER: Low-Rank Quantization Error Reconstruction for LLMs

Cheng Zhang (Imperial College London), Yiren Zhao (Imperial College London)

CodeCompressionOptimizationComputational EfficiencyTransformerLarge Language ModelText

🎯 What it does: A new post-training quantization framework LQER is proposed, which combines quantization and low-rank approximation to reconstruct the quantization error of weights, thereby restoring the performance of large language models (LLMs) without additional training or iterative optimization.

LSEnet: Lorentz Structural Entropy Neural Network for Deep Graph Clustering

Li Sun (North China Electric Power University), Philip S. Yu (University of Illinois at Chicago)

CodeOptimizationGraph Neural NetworkGraph

🎯 What it does: A graph clustering method called LSEnet is proposed, which does not require a predefined number of clusters. It utilizes differentiable structural information (DSI) to learn a hierarchical partition tree in the hyperbolic space of the Lorentz model and complete clustering.

Maestro: Uncovering Low-Rank Structures via Trainable Decomposition

Samuel HorvΓ‘th (Mohamed bin Zayed University of Artificial Intelligence), Hongyi Wang (Carnegie Mellon University)

CodeCompressionOptimizationConvolutional Neural NetworkTransformerSupervised Fine-TuningImageText

🎯 What it does: The MAESTRO framework is proposed, which dynamically learns the optimal rank of each layer during training through Low-Rank Ordered Decomposition (LOD), achieving low-rank compression of the model.

MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models

Justin Chen, Mohit Bansal (University of North Carolina Chapel Hill)

CodeKnowledge DistillationGraph Neural NetworkLarge Language ModelContrastive LearningTextGraph

🎯 What it does: Construct a Multi-Agent Generated Graph (MAG) and distill its structure into a small language model to enhance reasoning capabilities.

MAGNOLIA: Matching Algorithms via GNNs for Online Value-to-go Approximation

Alexandre Hayderi (Stanford University), Anders Wikum (Stanford University)

CodeOptimizationGraph Neural NetworkGraph

🎯 What it does: This paper proposes an online Bayesian bipartite matching algorithm called MAGNOLIA based on graph neural networks (GNN), which learns to estimate value-to-go (VTG) using GNN to make approximately optimal matching decisions upon the arrival of each online node.

Mapping the Multiverse of Latent Representations

Jeremy Wayland (Helmholtz Munich), Bastian Rieck (Helmholtz Munich)

CodeGenerationData SynthesisRepresentation LearningTransformerAuto EncoderImageText

🎯 What it does: The PRESTO framework is proposed to map and compare the latent space structures of different machine learning models (especially those using latent representations) in a multiverse.

Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs

Ling Yang (Peking University), Bin CUI

CodeGenerationData SynthesisTransformerLarge Language ModelDiffusion modelImageText

🎯 What it does: A training-free framework called RPG (Recaption, Plan, Generate) is proposed, utilizing multimodal large language models (MLLM) for text re-labeling, planning regions, and achieving region-level generation and editing within diffusion models.

Mastering Zero-Shot Interactions in Cooperative and Competitive Simultaneous Games

Yannik Mahlau (Leibniz University Hannover), Bodo Rosenhahn (Leibniz University Hannover)

CodeRobotic IntelligenceReinforcement LearningAgentic AITabularBenchmark

🎯 What it does: In a simultaneous cooperation and competition game, the Albatross method is proposed, which can adaptively make decisions based on the opponent's bounded rationality under zero-shot interaction.

MD tree: a model-diagnostic tree grown on loss landscape

Yefan Zhou (Dartmouth College), Yaoqing Yang (Zhejiang University)

CodeOptimizationExplainability and InterpretabilityConvolutional Neural NetworkImage

🎯 What it does: This paper proposes a model diagnostic tree (MD tree) based on loss landscape metrics, which can diagnose the sources of failure in pre-trained neural networks (such as optimizer hyperparameters, model size, or insufficient data) without retraining and without accessing the original training configuration.

Mean-field Underdamped Langevin Dynamics and its Spacetime Discretization

Qiang Fu (Yale University), Ashia Camage Wilson

CodeOptimizationStochastic Differential Equation

🎯 What it does: A N-particle algorithm (N-ULA) based on average field undamped Langevin dynamics is proposed for high-dimensional entropy-regularized mean field optimization problems.

Measures of diversity and space-filling designs for categorical data

Cedric Malherbe (AstraZeneca), Tom Diethe

CodeOptimizationHyperparameter SearchGraph Neural NetworkReinforcement LearningAgentic AIGraphTabular

🎯 What it does: This paper focuses on constructing space-filling designs for discrete (categorical) data spaces and proposes a subset selection method based on combinatorial optimization.

Mechanistic Neural Networks for Scientific Machine Learning

Adeel Pervez (University of Amsterdam), Stratis Gavves

CodeTime SeriesPhysics RelatedOrdinary Differential Equation

🎯 What it does: This paper proposes Mechanistic Neural Networks (MNN), which can explicitly learn and solve differential equations by embedding Mechanistic Blocks in neural networks, thereby discovering and simulating dynamic systems directly from data.

Memory Efficient Neural Processes via Constant Memory Attention Block

Leo Feng (Mila - UniversitΓ© de MontrΓ©al), Mohamed Osama Ahmed (Borealis AI)

CodeGenerationData SynthesisComputational EfficiencyMeta LearningImageTime Series

🎯 What it does: This study proposes a Constant Memory Attention Block (CMAB) and integrates it into Neural Processes (NP), forming Constant Memory Attentive Neural Processes (CMANP), achieving an NP model that uses constant memory and constant computation during the conditioning, querying, and updating phases.

Meta-Reinforcement Learning Robust to Distributional Shift Via Performing Lifelong In-Context Learning

Tengye Xu (Zhejiang University), Qinyuan Ren (Zhejiang University)

CodeMeta LearningTransformerReinforcement LearningTabularSequential

🎯 What it does: A Meta-RL method named PSBL is proposed, which achieves robustness to task distribution drift by utilizing a pre-trained transformer (LILTrans) for gradient-free online inference during the testing phase.

MF-CLR: Multi-Frequency Contrastive Learning Representation for Time Series

Jufang Duan (Lenovo Research), Hongsheng Qi (Lenovo Research)

CodeClassificationAnomaly DetectionRepresentation LearningRecurrent Neural NetworkContrastive LearningTime SeriesFinance Related

🎯 What it does: Designed and implemented MF-CLR, a self-supervised contrastive learning framework for learning universal representations of multi-frequency time series.

MGit: A Model Versioning and Management System

Wei Hao (Columbia University), Junfeng Yang (Columbia University)

CodeCompressionFederated LearningTransformerSupervised Fine-TuningGraph

🎯 What it does: A model versioning and management system named MGit has been designed and implemented, which records model evolution traces and provides storage optimization, testing, updating, and collaboration features.

Mimicking Better by Matching the Approximate Action Distribution

Joao Candido Ramos, Alexandros Kalousis (University of Applied Sciences and Arts Western)

CodeRobotic IntelligenceReinforcement LearningSequential

🎯 What it does: A new observation-based imitation learning algorithm called MAAD is proposed, which infers missing expert actions using an inverse dynamics model and guides policy learning through behavior cloning regularization.

Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss

Zhenlong Liu (Southern University of Science and Technology), Hongxin Wei (Southern University of Science and Technology)

CodeOptimizationSafty and PrivacyConvolutional Neural NetworkImage

🎯 What it does: The Convex-Concave Loss (CCL) is proposed by incorporating a concave function into the cross-entropy loss, significantly improving the variance of training sample loss, thereby reducing the advantage of membership inference attacks (MIA) while maintaining model performance.

Mobile Attention: Mobile-Friendly Linear-Attention for Vision Transformers

Zhiyu Yao (Baidu), Mingsheng Long (Tsinghua University)

CodeObject DetectionSegmentationComputational EfficiencyTransformerImage

🎯 What it does: A Mobile-Attention mechanism is proposed to replace the standard attention in ViT with a more efficient linear attention;

Modular Learning of Deep Causal Generative Models for High-dimensional Causal Inference

Md Musfiqur Rahman (Purdue University), Murat Kocaoglu (Purdue University)

CodeGenerationData SynthesisDiffusion modelGenerative Adversarial NetworkImage

🎯 What it does: A modular adversarial training algorithm, Modular-DCM, is proposed for constructing deep causal generative models (DCM), enabling accurate estimation of identifiable causal effects and causal sampling in high-dimensional data (such as images) with potential confounding factors.

MOKD: Cross-domain Finetuning for Few-shot Classification via Maximizing Optimized Kernel Dependence

Hongduan Tian (Hong Kong Baptist University), Bo Han (Hong Kong Baptist University)

CodeClassificationDomain AdaptationMeta LearningConvolutional Neural NetworkContrastive LearningImage

🎯 What it does: This paper proposes a two-layer framework MOKD based on optimized kernel dependency for cross-domain few-shot classification fine-tuning.

Mol-AE: Auto-Encoder Based Molecular Representation Learning With 3D Cloze Test Objective

Junwei Yang (Peking University), Hao Zhou (Tsinghua University)

CodeRepresentation LearningDrug DiscoveryTransformerAuto EncoderGraph

🎯 What it does: This paper proposes a 3D molecular representation learning framework called MOL-AE based on autoencoders, and designs a new 3D Cloze Test training objective to address the inconsistency between pre-training and downstream tasks in traditional coordinate denoising frameworks, as well as the twisted optimization problem caused by coordinate denoising.

MolCRAFT: Structure-Based Drug Design in Continuous Parameter Space

Yanru Qu (Tsinghua University), Wei-Ying Ma (Tsinghua University)

CodeDrug DiscoveryGraph Neural NetworkFlow-based ModelBiomedical Data

🎯 What it does: A generative model called MolCRAFT is proposed for structure-based drug design in continuous parameter space, addressing the issues of mode collapse and discrete-continuous space mismatch in traditional autoregressive and diffusion models for 3D conformation generation.

Momentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning

Long Qian (Zhejiang University), Siliang Tang (National University of Singapore)

CodeRecognitionRetrievalTransformerLarge Language ModelSupervised Fine-TuningVision Language ModelVideoTextMultimodality

🎯 What it does: Momentor has been developed, a video large language model with fine-grained temporal reasoning capabilities, trained on the automatically generated Moment-10M dataset;

Momentum Particle Maximum Likelihood

Jen Ning Lim (University of Warwick), Adam Michael Johansen

CodeOptimizationImageStochastic Differential Equation

🎯 What it does: A Momentum Particle Descent (MPD) algorithm is designed, introducing a momentum mechanism into particle gradient descent for maximum likelihood estimation of latent variable models.

Monotone, Bi-Lipschitz, and Polyak-Łojasiewicz Networks

Ruigang Wang (University of Sydney), Ian Manchester

CodeOptimizationImage

🎯 What it does: This paper proposes BiLipNet (reversible bi-Lipschitz network) and PLNet (scalar output network satisfying the Polyak-Łojasiewicz condition), and presents a method to construct reversible residual layers while ensuring strong monotonicity and Lipschitz continuity.

Multi-layer Rehearsal Feature Augmentation for Class-Incremental Learning

Bowen Zheng (Nanjing University), De-Chuan Zhan (Nanjing University)

CodeClassificationKnowledge DistillationContrastive LearningImage

🎯 What it does: This paper studies the overfitting problem of replay samples in continual learning and proposes a Multi-layer Replay Feature Augmentation (MRFA) method, which enhances the features of replay samples through gradient ascent at each layer to increase the inter-layer margin, thereby alleviating catastrophic forgetting.

Multi-Patch Prediction: Adapting Language Models for Time Series Representation Learning

Yuxuan Bian (Chinese University of Hong Kong), Qiang Xu (Chinese University of Hong Kong)

CodeAnomaly DetectionRepresentation LearningTransformerLarge Language ModelSupervised Fine-TuningTime Series

🎯 What it does: Transforming time series forecasting into a self-supervised multi-patch prediction task, utilizing causal Transformer (GPT2) to learn time series representations under a two-stage pre-training + fine-tuning framework.

MusicFlow: Cascaded Flow Matching for Text Guided Music Generation

K R Prajwal (VGG University of Oxford), Wei-Ning Hsu (Meta)

CodeGenerationData SynthesisTransformerFlow-based ModelTextOrdinary Differential EquationAudio

🎯 What it does: This paper presents MusicFlow, a cascaded text-to-music generation model based on flow matching, capable of generating music from natural language descriptions and supporting tasks such as continuation and filling in the blanks.

MVMoE: Multi-Task Vehicle Routing Solver with Mixture-of-Experts

Jianan Zhou (Nanyang Technological University), Xu Chi

CodeOptimizationTransformerReinforcement LearningMixture of Experts

🎯 What it does: A multi-task vehicle routing problem solver MVMoE has been developed, utilizing a mixture of experts (MoE) to achieve unified learning and solving for various VRP variants.

Navigating Complexity: Toward Lossless Graph Condensation via Expanding Window Matching

Yuchen Zhang (National University of Singapore), Yang You (National University of Singapore)

CodeCompressionKnowledge DistillationGraph Neural NetworkGraph

🎯 What it does: The GEOM method is proposed to achieve lossless graph condensation, first using curriculum learning to generate diverse supervisory signals, and then effectively transferring this information to small synthetic graphs through extended window matching, supplemented by a knowledge embedding extractor to further enhance performance.

Nearest Neighbour Score Estimators for Diffusion Generative Models

Matthew Niedoba (University of British Columbia), Frank Wood (University of British Columbia)

CodeGenerationData SynthesisComputational EfficiencyDiffusion modelScore-based ModelImageOrdinary Differential Equation

🎯 What it does: A score estimator based on nearest neighbors is proposed, which uses multiple training samples for self-normalized importance sampling to reduce the variance of score estimation and decrease bias.

Neighboring Perturbations of Knowledge Editing on Large Language Models

Jun-Yu Ma (University of Science and Technology of China), Jia-Chen Gu (University of California)

CodeTransformerLarge Language ModelSupervised Fine-TuningTextBenchmark

🎯 What it does: This paper studies the perturbation of neighboring knowledge when adding new knowledge to large language models and proposes an additive metric for measuring such perturbations, along with the evaluation benchmark PEAK, and a pluggable editing framework APP, which aims to reduce the forgetting of existing answer lists and the introduction of noise while adding knowledge.

Nesting Particle Filters for Experimental Design in Dynamical Systems

Sahel Iqbal (Aalto University), Hany Abdulsamad (Aalto University)

CodeOptimizationReinforcement LearningTime Series

🎯 What it does: A nested particle filtering method (Inside‑Out SMC 2) is proposed for Bayesian experimental design with non-exchangeable data, and gradient optimization is performed within the particle MCMC framework.

Neural Jump-Diffusion Temporal Point Processes

Shuai Zhang (Academy of Mathematics and Systems Science, Chinese Academy of Sciences), Zhi-Ming Ma (Academy of Mathematics and Systems Science, Chinese Academy of Sciences)

CodeTime SeriesSequentialBiomedical DataStochastic Differential Equation

🎯 What it does: A new framework is proposed that views intensity processes as solutions to Neural Jump Diffusion Stochastic Differential Equations (NJDSDE), addressing the limitation of traditional Temporal Point Processes (TPP) that require a predefined intensity form.

Neural SPH: Improved Neural Modeling of Lagrangian Fluid Dynamics

Artur Toshev, Johannes Brandstetter (Johannes Kepler University)

CodeGraph Neural NetworkGraphPhysics Related

🎯 What it does: This paper proposes the Neural SPH framework, which enhances the physical consistency and long-term stability of the GNN simulator in Lagrangian fluid dynamics by incorporating external force handling and SPH relaxation steps during the training and inference phases.

NeWRF: A Deep Learning Framework for Wireless Radiation Field Reconstruction and Channel Prediction

Haofan Lu (University of California Los Angeles), Omid Abari (University of California Los Angeles)

CodeNeural Radiance FieldPoint Cloud

🎯 What it does: Proposes the NeWRF framework, which learns indoor wireless channel fields using sparse measurement points and accurately predicts channels at unmeasured points.

No Double Descent in Principal Component Regression: A High-Dimensional Analysis

Daniel Gedon (Uppsala University), Thomas B. SchΓΆn (Uppsala University)

CodeTabularAgriculture Related

🎯 What it does: The theoretical analysis of the generalization risk of principal component regression (PCR) in high-dimensional data under the spiked covariance model is conducted, proving that there is no double descent phenomenon.

Noise-Adaptive Confidence Sets for Linear Bandits and Application to Bayesian Optimization

Kwang-Sung Jun (University of Arizona), Jungtaek Kim (University of Pittsburgh)

CodeOptimizationTabular

🎯 What it does: A new noise-adaptive confidence set is proposed for linear bandit problems and applied to Bayesian optimization.

Nonsmooth Implicit Differentiation: Deterministic and Stochastic Convergence Rates

Riccardo Grazzi (Istituto Italiano di Tecnologia), Saverio Salzo (UniversitΓ  La Sapienza)

CodeOptimizationHyperparameter SearchTabular

🎯 What it does: This paper studies the fixed point differentiation problem for non-differentiable contraction mappings, providing deterministic convergence rates for ITD (Iterative Differentiation) and AID (Approximate Implicit Differentiation), and proposes the first provably convergent stochastic method, NSID; experiments are then conducted to validate these results in bilevel optimization (hyperparameter optimization and data poisoning).

Novel Spectral Algorithms for the Partial Credit Model

Duc Nguyen (University of Pennsylvania), Anderson Ye Zhang (University of Pennsylvania)

CodeRecommendation SystemTabularFinance Related

🎯 What it does: A spectral algorithm for Partial Credit Models (PCM) is proposed to estimate project parameters;

ODIM: Outlier Detection via Likelihood of Under-Fitted Generative Models

Dongha Kim (Sungshin Women's University), Yongdai Kim (Seoul National University)

CodeAnomaly DetectionAuto EncoderImageTextTabular

🎯 What it does: An unsupervised anomaly detection method ODIM based on low-fit generative model likelihood is proposed.

Off-policy Evaluation Beyond Overlap: Sharp Partial Identification Under Smoothness

Samir Khan (Stanford University), Johan Ugander (Stanford University)

CodeTabular

🎯 What it does: Under the condition of no overlap, a precise partial identification framework for offline policy evaluation (OPE) is proposed using the smoothness (Lipschitz) assumption, along with a closed-form linear programming solution method; asymptotically optimal estimators and convergence rate analysis are also provided.

OLLIE: Imitation Learning from Offline Pretraining to Online Finetuning

Sheng Yue (Tsinghua University), Yaoxue Zhang (Tsinghua University)

CodeRobotic IntelligenceReinforcement Learning from Human FeedbackReinforcement LearningGenerative Adversarial NetworkImage

🎯 What it does: A framework for imitation learning from offline pre-training to online fine-tuning, called OLLIE, is proposed. It learns an approximate expert policy from offline data and synchronously obtains an aligned discriminator, supporting rapid online fine-tuning for high-dimensional tasks.

On Hypothesis Transfer Learning of Functional Linear Models

Haotian Lin (Pennsylvania State University), Matthew Reimherr (Pennsylvania State University)

CodeTabularTime SeriesFinance Related

🎯 What it does: This paper proposes and theoretically analyzes two algorithms, TL-FLR and ATL-FLR, based on Optimal Transfer Learning (OTL) within the frameworks of Functional Linear Regression (FLR) and Functional Generalized Linear Models (FGLM), aimed at enhancing the predictive performance of the target task when information from the source task is limited.

On Mechanistic Knowledge Localization in Text-to-Image Generative Models

Samyadeep Basu (University of Maryland), Soheil Feizi (University of Maryland)

CodeGenerationData SynthesisTransformerDiffusion modelImageText

🎯 What it does: Two methods, LOCOGEN and LOCOEDIT, are proposed for locating and editing the control layers of visual attributes in text-to-image generation models.

On PI Controllers for Updating Lagrange Multipliers in Constrained Optimization

Motahareh Sohrabi (Mila-Quebec AI Institute and Universite de Montreal), Jose Gallego-Posada (Mila-Quebec AI Institute and Universite de Montreal)

CodeOptimizationTabular

🎯 What it does: A νPI algorithm based on a PI controller is proposed for updating Lagrange multipliers in Lagrangian constraint optimization, along with theoretical analysis and experimental validation.

On Prompt-Driven Safeguarding for Large Language Models

Chujie Zheng (Tsinghua University), Nanyun Peng (University of California Los Angeles)

CodeOptimizationSafty and PrivacyTransformerLarge Language ModelPrompt EngineeringText

🎯 What it does: Study the working mechanism of safety prompts in large language models and propose a representation space-based safety prompt optimization method called DRO.

On the Convergence of Projected Bures-Wasserstein Gradient Descent under Euclidean Strong Convexity

Junyi FAN, Zhengyuan Zhou

CodeOptimization

🎯 What it does: The paper studies the global convergence theory of the Bures-Wasserstein gradient descent algorithm (including the projection version) for positive definite matrices under Euclidean strong convexity and smoothness conditions, and provides a closed-form projection formula for the BW ball constraint.

On the Diminishing Returns of Width for Continual Learning

Etash Kumar Guha, Vihan Lakshman (ThirdAI)

CodeConvolutional Neural NetworkTransformerImage

🎯 What it does: This study investigates the impact of width on catastrophic forgetting in continual learning, proposes a theoretical framework, and demonstrates that increasing width leads to diminishing returns, validating its performance on large-width FFN and WideResNet.

On the Expressive Power of Spectral Invariant Graph Neural Networks

Bohang Zhang (Peking University), Haggai Maron (NVIDIA Research)

CodeGraph Neural NetworkGraphBenchmark

🎯 What it does: This paper proposes and unifies the spectral invariant graph neural network framework, namely Eigenspace Projection GNN (EPNN), and conducts a theoretical analysis of its expressive power;

On the Feasibility of Single-Pass Full-Capacity Learning in Linear Threshold Neurons with Binary Input Vectors

Ruipeng Liu (Syracuse University), Garrett Ethan Katz (Syracuse University)

CodeSpiking Neural NetworkTabular

🎯 What it does: This study investigates the feasibility of single-pass and full-capacity linear threshold neuron learning rules, focusing on binary input vectors.

On the Hardness of Probabilistic Neurosymbolic Learning

Jaron Maene (KU Leuven), Luc De Raedt (Orebro University)

CodeTabular

🎯 What it does: This paper studies the complexity and feasibility of approximating the gradient of Weighted Model Counting (WMC) in probabilistic neural-symbolic learning.

On the Minimal Degree Bias in Generalization on the Unseen for non-Boolean Functions

Denys Pushkin (Γ‰cole Polytechnique FΓ©dΓ©rale de Lausanne), Emmanuel Abbe (Apple)

CodeTransformer

🎯 What it does: This study investigates the minimum order bias of random feature models (RF) and Transformers in the context of non-Boolean functions' GOTU (generalization to unseen domains), exploring two scenarios: small features and sparse targets. It proves that under the small feature paradigm, RF converges to the lowest order interpolator and discusses the peculiarities of square root unit embeddings.

On the Trajectory Regularity of ODE-based Diffusion Sampling

Defang Chen (Zhejiang University), Siwei Lyu (University at Buffalo)

CodeGenerationOptimizationDiffusion modelAuto EncoderImageOrdinary Differential Equation

🎯 What it does: This paper studies the geometric laws of ODE-based diffusion model sampling trajectories and proposes a time scheduling method based on these laws.

One Size Fits All for Semantic Shifts: Adaptive Prompt Tuning for Continual Learning

Doyoung Kim (KAIST), Jae-Gil Lee (KAIST)

CodeClassificationRepresentation LearningTransformerPrompt EngineeringImage

🎯 What it does: An adaptive prompt tuning framework called AdaPromptCL is proposed to handle varying degrees of semantic drift in continual learning.

Online Learning and Information Exponents: The Importance of Batch size & Time/Complexity Tradeoffs

Luca Arnaboldi (Ecole Polytechnique Federale de Lausanne), Ludovic Stephan (Ecole Polytechnique Federale de Lausanne)

CodeOrdinary Differential Equation

🎯 What it does: This paper studies the impact of batch size on the iteration time and sample complexity when training a two-layer neural network with one-shot SGD, and proposes a method called 'correlated loss SGD' to overcome the time bottleneck caused by the self-interaction of traditional SGD in the case of large batches.

Open-Domain Text Evaluation via Contrastive Distribution Methods

Sidi Lu (University of California), Nanyun Peng (University of California)

CodeGenerationData SynthesisTransformerLarge Language ModelContrastive LearningText

🎯 What it does: A contrastive evaluation framework based on two language models of different scales is proposedβ€”Contrastive Distribution Methods (CDM), which includes generative and discriminative variants, to generate pseudo-negative samples or directly calculate contrastive momentum, thereby obtaining reference-free text quality scores.

Open-Vocabulary Calibration for Fine-tuned CLIP

Shuoyuan Wang (Southern University of Science and Technology), Hongxin Wei (Southern University of Science and Technology)

CodeClassificationRecognitionTransformerSupervised Fine-TuningPrompt EngineeringImage

🎯 What it does: A Distance-Aware Calibration (DAC) method is proposed to correct the confidence distortion of fine-tuned CLIP under open vocabulary.

Operator SVD with Neural Networks via Nested Low-Rank Approximation

Jongha Jon Ryu (Massachusetts Institute of Technology), Gregory W. Wornell (Massachusetts Institute of Technology)

CodeRetrievalOptimizationImagePhysics Related

🎯 What it does: A framework utilizing Nested Low-Rank Approximation (Nested LoRA) is proposed, which uses neural networks to directly learn the first L singular values and corresponding singular functions of linear operators (such as integral kernels or differential operators);

Optimal Batched Linear Bandits

Xuanfei Ren (University of Science and Technology of China), Pan Xu (Duke University)

CodeOptimizationReinforcement LearningTabular

🎯 What it does: This paper proposes a new batch linear Bandit algorithm E4, which adopts the Explore-Estimate-Eliminate-Exploit framework to address the optimal decision-making problem under limited time and asymptotic limits.

Optimal Eye Surgeon: Finding image priors through sparse generators at initialization

Avrajit Ghosh (Michigan State University), Rongrong Wang (Michigan State University)

CodeRestorationImageMagnetic Resonance Imaging

🎯 What it does: This paper proposes a framework for sparse pruning during the random initialization of networks, resulting in a sparse subnetwork (Sparse-DIP) that can serve as an image prior for image recovery with little or no training.

Optimally Improving Cooperative Learning in a Social Setting

Shahrzad Haddadan (Rutgers University), Jie Gao (Rutgers University)

CodeOptimizationGraph Neural NetworkGraph

🎯 What it does: The study investigates how to select k agents with their own classifiers in a social network to improve their original predictions, thereby maximizing the overall prediction accuracy of the network.

Optimistic Multi-Agent Policy Gradient

Wenshuai Zhao (Aalto University), Joni Pajarinen (Aalto University)

CodeReinforcement LearningBenchmark

🎯 What it does: A framework is proposed that incorporates optimistic updates into multi-agent policy gradient methods, primarily achieved by clipping negative values in the advantage function to 0 (or using Leaky ReLU);

OptiMUS: Scalable Optimization Modeling with (MI)LP Solvers and Large Language Models

Ali AhmadiTeshnizi (Stanford University), Madeleine Udell (Stanford University)

CodeOptimizationTransformerLarge Language ModelAgentic AIPrompt EngineeringText

🎯 What it does: A multi-agent system named OptiMUS based on large language models has been developed, capable of automatically decomposing optimization problems described in natural language into parameters, constraints, and objectives, generating executable solving code, and self-debugging, ultimately solving linear programming and mixed-integer programming problems.

OSN: Infinite Representations of Dynamic 3D Scenes from Monocular Videos

Ziyang Song (Hong Kong Polytechnic University), Bo Yang (Hong Kong Polytechnic University)

CodeSegmentationGenerationDepth EstimationNeural Radiance FieldVideo

🎯 What it does: This paper proposes an OSN framework that learns all feasible dynamic 3D scene representations from monocular RGB videos, capable of infinitely generating 3D scene configurations that satisfy the video.

OT-CLIP: Understanding and Generalizing CLIP via Optimal Transport

Liangliang Shi (Shanghai Jiao Tong University), Junchi Yan (Shanghai Jiao Tong University)

CodeClassificationOptimizationRepresentation LearningContrastive LearningImage

🎯 What it does: The contrastive learning and inference processes of CLIP are treated as inverse optimal transport (Inverse OT) bi-level optimization and graph matching problems, proposing the OT-CLIP loss family and OT prediction framework.

Out of the Ordinary: Spectrally Adapting Regression for Covariate Shift

Benjamin Eyre (Columbia University), Richard Zemel (University of Toronto)

CodeDomain AdaptationImageTabular

🎯 What it does: This paper proposes a post-processing method for spectral adaptation of regression models under covariate shift, called SpAR, which projects the weights of the last layer of a pre-trained regression model using unlabeled target data to reduce out-of-distribution (OOD) errors caused by spectral inflation.

Outlier-Efficient Hopfield Layers for Large Transformer-Based Models

Jerry Yao-Chieh Hu (Northwestern University), Han Liu (Northwestern University)

CodeAnomaly DetectionOptimizationTransformerLarge Language ModelImageTextTime Series

🎯 What it does: A model based on the modern Hopfield network called 'Outlier-Efficient' is proposed, which improves the Transformer attention mechanism to reduce output anomalies caused by low-information words (such as punctuation and separators).

Overcoming Data and Model heterogeneities in Decentralized Federated Learning via Synthetic Anchors

Chun-Yin Huang (University of British Columbia), Xiaoxiao Li (University of British Columbia)

CodeDomain AdaptationFederated LearningKnowledge DistillationImage

🎯 What it does: In a serverless decentralized federated learning scenario, this paper proposes the use of synthetic anchor data through feature regularization and knowledge distillation methods to alleviate data and model heterogeneity, thereby improving the generalization performance of local models on cross-domain tasks.

Overcoming Saturation in Density Ratio Estimation by Iterated Regularization

Lukas Gruber (Johannes Kepler University Linz), Werner Zellinger (Austrian Academy of Sciences)

CodeDomain AdaptationOptimizationImageText

🎯 What it does: Proposes and implements an iterative regularization method (iterative Tikhonov regularization) for density ratio estimation, overcoming the saturation phenomenon of traditional kernel methods and achieving faster error convergence across various algorithms.

PairNet: Training with Observed Pairs to Estimate Individual Treatment Effect

Lokesh Nagalapatti (Indian Institute of Technology Bombay), Sunita Sarawagi (Indian Institute of Technology Bombay)

CodeTabularBiomedical Data

🎯 What it does: A new Individual Treatment Effect (ITE) estimation training strategy called PairNet is proposed, which minimizes loss using only observed instance pairs;

PAPM: A Physics-aware Proxy Model for Process Systems

Pengwei Liu (Zhejiang University), Dong Ni (Zhejiang University)

CodeOptimizationComputational EfficiencyTime SeriesBenchmarkPhysics RelatedOrdinary Differential Equation

🎯 What it does: For agent modeling of process systems, a physics-aware agent model (PAPM) is proposed that globally incorporates partial prior physical knowledge (general forms of various initial/boundary conditions and conservation relationships), along with a spatiotemporal stepping module (TSSM) designed to flexibly adapt to different process systems.

Parameter Efficient Quasi-Orthogonal Fine-Tuning via Givens Rotation

Xinyu Ma (Peking University), Junfeng Zhao (Peking University)

CodeOptimizationComputational EfficiencyTransformerSupervised Fine-TuningText

🎯 What it does: A parameter-efficient fine-tuning method based on Givens rotation (qGOFT) is proposed, which adapts large pre-trained models to downstream tasks through reparameterization while preserving the angular information of the pre-trained model.

Parameter Estimation in DAGs from Incomplete Data via Optimal Transport

Vy Vo (Monash University), Dinh Phung (VinAI Research)

CodeOptimizationImageGraphTime Series

🎯 What it does: In the context of missing data, this paper proposes a parameter learning framework based on optimal transport (OT) called OTP-DAG, aimed at estimating the parameters of probabilistic graphical models for arbitrary DAG structures.

PARDEN, Can You Repeat That? Defending against Jailbreaks via Repetition

Ziyang Zhang (University of Oxford), Jakob Nicolaus Foerster

CodeAdversarial AttackTransformerLarge Language ModelPrompt EngineeringText

🎯 What it does: The PARDEN method is proposed, which utilizes the LLM itself to first generate outputs, then has the LLM repeat those outputs, and uses BLEU similarity to determine if it is a jailbreak, thereby achieving defense.

Path-Guided Particle-based Sampling

Mingzhou Fan (Texas A&M University), Xiaoning Qian (Texas A&M University)

CodeOptimizationTabularStochastic Differential Equation

🎯 What it does: A particle sampling framework PGPS based on Log-weighted Shrinkage (LwS) density path guidance is proposed, which uses neural networks to learn vector fields, allowing particles to migrate along a predetermined path from the initial distribution to the target posterior distribution.

PcLast: Discovering Plannable Continuous Latent States

Anurag Koul (Microsoft Research), Alex Lamb (Microsoft Research)

CodeRobotic IntelligenceReinforcement LearningContrastive LearningSequential

🎯 What it does: For high-dimensional perceptual input, the PCLAST method is proposed to learn a plannable continuous latent state representation, and based on this, achieve multi-level planning.

PEARL: Zero-shot Cross-task Preference Alignment and Robust Reward Learning for Robotic Manipulation

Runze Liu (Tsinghua University), Xiu Li (Tsinghua University)

CodeRobotic IntelligenceTransformerReinforcement LearningSequential

🎯 What it does: This paper proposes a zero-shot cross-task preference alignment and robust reward learning framework (PEARL), which can utilize preference labels from the source task to generate pseudo-labels in the target task and learn policies.

PICLe: Eliciting Diverse Behaviors from Large Language Models with Persona In-Context Learning

Hyeong Kyu Choi (University of Wisconsin Madison), Yixuan Li (University of Wisconsin Madison)

CodeTransformerLarge Language ModelSupervised Fine-TuningText

🎯 What it does: A method called PICLe is proposed, which uses Bayesian inference and likelihood ratios to select examples in order to induce large language models to exhibit target personality traits through contextual learning.

PID: Prompt-Independent Data Protection Against Latent Diffusion Models

Ang Li (Peking University), Yisen Wang (Peking University)

CodeSafty and PrivacyAdversarial AttackDiffusion modelImage

🎯 What it does: This paper addresses the potential threats of privacy leakage and proposes a protection method for Latent Diffusion Models (PID) that does not rely on text prompts.

Piecewise Constant and Linear Regression Trees: An Optimal Dynamic Programming Approach

Mim van den Bos (Delft University of Technology), Emir Demirović (Delft University of Technology)

CodeOptimizationComputational EfficiencyTabular

🎯 What it does: Three optimal regression tree algorithms based on dynamic programming have been developed, namely piecewise constant regression trees, univariate linear regression trees, and multivariate linear regression trees, along with a dedicated acceleration algorithm for deep binary trees.

Planning, Fast and Slow: Online Reinforcement Learning with Action-Free Offline Data via Multiscale Planners

Chengjie Wu (Tsinghua University), Chongjie Zhang (Washington University in St. Louis)

CodeReinforcement LearningVideo

🎯 What it does: This paper investigates how to achieve efficient online reinforcement learning through a pre-trained value function and a two-level state-centered planner (with fast and slow scales) using passive dataset video data without action annotations.

Plug-and-Play image restoration with Stochastic deNOising REgularization

Marien Renaud (University of Bordeaux), Nicolas Papadakis (Telecom Paris)

CodeRestorationImageStochastic Differential Equation

🎯 What it does: The Stochastic deNOising REgularization (SNORE) framework is proposed, which modifies the PnP denoising step to denoise on noisy images and solves the inverse problem using stochastic gradient descent.

Position: A Call to Action for a Human-Centered AutoML Paradigm

Marius Lindauer (Leibniz University Hannover), Bernd Bischl (Ludwig Maximilians University Munich)

CodeLarge Language ModelReview/Survey Paper

🎯 What it does: This paper reviews the development and current status of Automated Machine Learning (AutoML), pointing out its shortcomings in transparency, customizability, interactivity, collaboration, and user empowerment, and calls for the establishment of a human-centered AutoML paradigm.

Position: Quo Vadis, Unsupervised Time Series Anomaly Detection?

M. Saquib Sarfraz (Mercedes-Benz Tech Innovation), Marios Koulakis (Karlsruhe Institute of Technology)

CodeAnomaly DetectionKnowledge DistillationGraph Neural NetworkTransformerTime SeriesReview/Survey PaperBenchmark

🎯 What it does: A critical analysis of the current state of research on time series anomaly detection is conducted, proposing and implementing various simple baselines (such as PCA reconstruction error, 1-NN distance, L2 norm, and a single layer MLP/MLPMixer/Transformer/GCN-LSTM), and comparing them with existing deep learning methods under standard and modified evaluation metrics.

Position: Reinforcement Learning in Dynamic Treatment Regimes Needs Critical Reexamination

Zhiyao Luo (University of Oxford), Tingting Zhu (University of Oxford)

CodeReinforcement LearningBiomedical DataElectronic Health Records

🎯 What it does: This paper systematically evaluates the performance of various offline reinforcement learning (RL) algorithms in dynamic treatment regimes (DTR) through 17,550 experiments on a sepsis dataset, focusing on the diversity of policy evaluation methods, reward design, and benchmark settings and their impact on the results.

Position: Standardization of Behavioral Use Clauses is Necessary for the Adoption of Responsible Licensing of AI

Daniel McDuff (University of Washington), Danish Contractor

Code

🎯 What it does: Analyze and quantify the adoption of AI licenses (including behavioral usage terms) in AI models and software repositories, assess the differences in their terms, and propose standardization and tooling suggestions.

Position: Towards Implicit Prompt For Text-To-Image Models

Yue Yang (Shanghai Jiao Tong University), Ping Luo (Hong Kong University)

CodeGenerationTransformerLarge Language ModelPrompt EngineeringDiffusion modelImageTextMultimodalityBenchmark

🎯 What it does: Proposes the concept of implicit prompts, constructs the ImplicitBench benchmark, and conducts a systematic evaluation on six mainstream text-to-image models.

PrE-Text: Training Language Models on Private Federated Data in the Age of LLMs

Charlie Hou (Carnegie Mellon University), Daniel Lazar (Meta)

CodeData SynthesisFederated LearningSafty and PrivacyComputational EfficiencyTransformerLarge Language ModelSupervised Fine-TuningText

🎯 What it does: The PrE-Text method is proposed, which generates synthetic text through differential privacy in a federated learning environment, serving as a replacement for traditional on-device training to train small and large models.

Prediction-powered Generalization of Causal Inferences

Ilker Demirel (Massachusetts Institute of Technology), David Sontag (Massachusetts Institute of Technology)

CodeMachine LearningTabular

🎯 What it does: This paper studies how to combine limited randomized controlled trials (RCTs) with large-scale observational data to enhance the external validity of causal inference for the target population.

Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss

Ruijie Zheng (University of Maryland), Furong Huang (Microsoft Research)

CodeRobotic IntelligenceConvolutional Neural NetworkReinforcement LearningContrastive LearningSequential

🎯 What it does: A multi-task offline pre-training framework named Premier-TACO is proposed, which learns general visual representations through time-action driven contrastive learning, thereby enhancing the efficiency of few-shot policy learning.

Preventing Model Collapse in Gaussian Process Latent Variable Models

Ying Li (University of Hong Kong), Michael Minyi Zhang (University of Hong Kong)

CodeOptimizationRepresentation LearningImageTabular

🎯 What it does: This paper proposes a novel Gaussian Process Latent Variable Model (GPLVM) - advised RFLVM, which prevents model collapse by learning projection noise and using a Spectral Mixture kernel combined with differentiable Random Fourier Features (RFF) to achieve fully differentiable variational inference.