arXivSub Start free trial

NeurIPS 2024 Papers with Code β€” Page 14

Conference on Neural Information Processing Systems Β· 1874 papers

Provable Benefits of Complex Parameterizations for Structured State Space Models

Yuval Ran-Milo (Tel Aviv University), Nadav Cohen (Google)

CodeImage

🎯 What it does: This paper discusses the theoretical and practical advantages of using complex parameterization in Structured State Space Models (SSM), demonstrating that complex SSMs outperform real-valued SSMs in expressiveness and learnability.

Provably and Practically Efficient Adversarial Imitation Learning with General Function Approximation

Tian Xu (Nanjing University), Yang Yu (Nanjing University)

CodeRobotic IntelligenceReinforcement Learning from Human FeedbackReinforcement LearningSequentialBenchmark

🎯 What it does: An online adversarial imitation learning framework OPT‑AIL is designed, utilizing online no-regret reward optimization and optimistic Bellman error minimization to learn rewards and Q-values, thereby achieving theoretically provable efficient imitation learning under general function approximation.

Provably Safe Neural Network Controllers via Differential Dynamic Logic

Samuel Teuber (Karlsruhe Institute of Technology), Andre Platzer (Carnegie Mellon University)

CodeAutonomous DrivingSafty and PrivacyTabularOrdinary Differential Equation

🎯 What it does: A method called VerSAILLE, which combines differential dynamic logic (dL) with neural network verification (NNV), is proposed to provide safety proofs for neural network-based control systems (NNCS) over an infinite time horizon. Additionally, a Mosaic framework is introduced, extending the linear constraint NNV tools to polynomial nonlinear and non-standard queries while maintaining completeness.

Proving Theorems Recursively

Haiming Wang (Sun Yat-sen University), Xiaodan Liang (Pengcheng Laboratory)

CodeLarge Language ModelSupervised Fine-TuningText

🎯 What it does: By recursively constructing verifiable proof sketches in a hierarchical manner and using sorry placeholders, POETRY advances layer by layer and ultimately achieves a complete proof.

ProvNeRF: Modeling per Point Provenance in NeRFs as a Stochastic Field

Kiyohiro Nakayama (Stanford University), Leonidas Guibas

CodeGenerationData SynthesisNeural Radiance FieldPoint Cloud

🎯 What it does: Introduce the observable position (provenance) distribution of each 3D point in NeRF training, forming a random field;

Proximal Causal Inference With Text Data

Jacob M. Chen (Johns Hopkins University), Katherine A. Keith (Williams College)

CodeTransformerLarge Language ModelTextBiomedical DataElectronic Health RecordsElectrocardiogram

🎯 What it does: This paper proposes a novel method that utilizes a zero-shot model for inferring two proxy variables from preprocessed text and applies it to proximal causal inference (proximal g-formula) to estimate causal effects in the absence of completely unobserved key confounding variables.

Prune and Repaint: Content-Aware Image Retargeting for any Ratio

Feihong Shen (Southeast University), Hao Chen (Southeast University)

CodeImage TranslationGenerationDiffusion modelImage

🎯 What it does: A content-aware image relocalization method named PruneRepaint is proposed, which combines hierarchical semantic-guided seam carving and an adaptive repainting module to achieve image retargeting at arbitrary ratios.

Pruning neural network models for gene regulatory dynamics using data and domain knowledge

Intekhab Hossain (Harvard T.H. Chan School of Public Health), John Quackenbush (Harvard T.H. Chan School of Public Health)

CodeOptimizationExplainability and InterpretabilityBiomedical DataOrdinary Differential Equation

🎯 What it does: A domain knowledge-based network pruning framework called DASH is proposed for inferring sparse neural network models of gene regulatory networks.

Pseudo-Private Data Guided Model Inversion Attacks

Xiong Peng (Hong Kong Baptist University), Mingyuan Zhou (University of Texas at Austin)

CodeGenerationAdversarial AttackConvolutional Neural NetworkGenerative Adversarial NetworkImage

🎯 What it does: The research proposes a model inversion attack guided by pseudo-private data (PPDG-MI), which enhances the attack effectiveness by dynamically fine-tuning the generator's prior distribution.

PSL: Rethinking and Improving Softmax Loss from Pairwise Perspective for Recommendation

Weiqin Yang (Zhejiang University), Can Wang (Zhejiang University)

CodeRecommendation SystemTabular

🎯 What it does: Proposed Pairwise Softmax Loss (PSL) to improve traditional Softmax Loss and achieve a more compact DCG approximation in recommendation systems.

PTQ4DiT: Post-training Quantization for Diffusion Transformers

Junyi Wu (University of Illinois Chicago), Yan Yan (University of Illinois Chicago)

CodeGenerationCompressionTransformerDiffusion modelImage

🎯 What it does: A post-training quantization (PTQ) method called PTQ4DiT is proposed for Diffusion Transformers (DiTs), which can compress the model to 8-bit weights/activations while maintaining generation quality, and further supports 4-bit weight quantization.

PuLID: Pure and Lightning ID Customization via Contrastive Alignment

Zinan Guo (ByteDance Inc), Qian HE

CodeRecognitionGenerationData SynthesisDiffusion modelContrastive LearningImageText

🎯 What it does: This paper proposes PuLID, a tuning-free method for identity (ID) customization in text-to-image (T2I) diffusion models.

Pure Message Passing Can Estimate Common Neighbor for Link Prediction

Kaiwen Dong (University of Notre Dame), Nitesh V Chawla

CodeGraph Neural NetworkGraph

🎯 What it does: This study investigates whether Message Passing Neural Networks (MPNN) can capture link structural features, and based on this, proposes the MPLP (Message Passing Link Predictor) model to estimate and predict potential edges in a graph.

PURE: Prompt Evolution with Graph ODE for Out-of-distribution Fluid Dynamics Modeling

Hao Wu (University of Science and Technology of China), Xiao Luo (University of California)

CodeDomain AdaptationOptimizationGraph Neural NetworkTransformerPrompt EngineeringTime SeriesPhysics RelatedOrdinary Differential Equation

🎯 What it does: This study investigates the out-of-distribution fluid dynamics modeling problem and proposes a framework called PURE (Prompt Evolution with Graph ODE) to enhance the model's predictive performance under parameter and temporal distribution shifts.

PureGen: Universal Data Purification for Train-Time Poison Defense via Generative Model Dynamics

Omead Pooladzandi (California Institute of Technology), Gregory Pottie (University of California)

CodeAdversarial AttackData-Centric LearningDiffusion modelImage

🎯 What it does: This paper proposes PUREGEN, a dynamic random preprocessing method that utilizes Energy-Based Models (EBM) and Diffusion Models (DDPM) for unsupervised purification of data during the training phase, thereby defending against backdoor and triggerless training-time data poisoning attacks.

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

Vladimir Malinovskii (Yandex), Peter RichtΓ‘rik

CodeCompressionOptimizationTransformerLarge Language ModelSupervised Fine-TuningText

🎯 What it does: This paper proposes PV-Tuning, a fine-tuning framework for large language models with extremely low bit quantization (1-2 bits), which can simultaneously update continuous parameters (such as scaling factors and codebooks) and discrete parameters (weight quantization codes), significantly improving the accuracy of the quantized model.

Q-Distribution guided Q-learning for offline reinforcement learning: Uncertainty penalized Q-value via consistency model

Jing Zhang (Hong Kong University of Science and Technology), Bingyi Jing

CodeReinforcement LearningTabularBenchmark

🎯 What it does: This paper proposes an offline reinforcement learning method called Q-Distribution Guided Q-Learning (QDQ), which estimates the uncertainty of the Q value distribution using a consistency model and applies a lazy penalty to out-of-distribution (OOD) actions to balance excessive pessimism and exploration.

Q-VLM: Post-training Quantization for Large Vision-Language Models

Changyuan Wang (Tsinghua University), Jiwen Lu (Tsinghua University)

CodeCompressionComputational EfficiencyTransformerMixture of ExpertsVision Language ModelMultimodality

🎯 What it does: A post-training quantization framework Q-VLM is proposed for efficient multimodal inference of large visual language models, reducing model size and inference speed.

QGFN: Controllable Greediness with Action Values

Elaine Lau (McGill University), Emmanuel Bengio (Mila - Quebec AI Institute)

CodeGenerationDrug DiscoveryReinforcement LearningSequential

🎯 What it does: This paper proposes a QGFN method that combines GFlowNet with the action value function Q, achieving a controllable greedy strategy during sampling through an adjustable mixing parameter p, thereby improving the generation rate of high-reward samples while maintaining diversity.

QKFormer: Hierarchical Spiking Transformer using Q-K Attention

Chenlin Zhou (Pengcheng Laboratory), Yonghong Tian (Pengcheng Laboratory)

CodeClassificationSpiking Neural NetworkTransformerImage

🎯 What it does: A directly trained hierarchical spiking Transformer called QKFormer is designed, and a linear complexity Q-K attention mechanism along with a cross-scale SPEDS embedding module is proposed, aiming to enhance the performance and energy efficiency of Spiking Neural Networks (SNNs);

QuadMamba: Learning Quadtree-based Selective Scan for Visual State Space Model

Fei Xie (Shanghai Jiao Tong University), Chao Ma (Shanghai Jiao Tong University)

CodeClassificationObject DetectionSegmentationTransformerImage

🎯 What it does: A visual Mamba model called QuadMamba based on a learnable quadtree scanning mechanism has been designed for visual tasks such as image classification, object detection, instance segmentation, and semantic segmentation.

QuanTA: Efficient High-Rank Fine-Tuning of LLMs with Quantum-Informed Tensor Adaptation

Zhuo Chen (Massachusetts Institute of Technology), Marin Soljacic (Massachusetts Institute of Technology)

CodeTransformerLarge Language ModelSupervised Fine-TuningText

🎯 What it does: Proposes QuanTA, a tensor adaptive method inspired by quantum circuits for high-rank, efficient LLM fine-tuning.

Quantifying Aleatoric Uncertainty of the Treatment Effect: A Novel Orthogonal Learner

Valentyn Melnychuk (Ludwig Maximilian University of Munich), Mihaela van der Schaar (University of Cambridge)

CodeFlow-based ModelTabular

🎯 What it does: A novel orthogonal learner (AU-learner) is proposed to estimate the Markov boundary of the conditional treatment effect distribution (CDTE), thereby quantifying the Alitayi uncertainty of treatment effects.

Quantifying and Optimizing Global Faithfulness in Persona-driven Role-playing

Letian Peng (University of California, San Diego), Jingbo Shang (University of California, San Diego)

CodeOptimizationTransformerLarge Language ModelReinforcement LearningText

🎯 What it does: Quantitatively assess the global fidelity in persona-driven role-playing (PRP) and propose an Active-Passive Constraint (APC) scoring and an APC-based Direct Preference Optimization (DPO) scheme.

Quantifying the Gain in Weak-to-Strong Generalization

Moses Charikar (Stanford University), Kirankumar Shiragur (Microsoft Research)

CodeOptimizationRepresentation LearningTransformerLarge Language ModelText

🎯 What it does: Proposes and theorizes the mechanism of weak-to-strong generalization, proving that the error of a strong model using labels generated by a weak model is at least one 'misfit' order of magnitude lower than that of the weak model;

Quantitative Convergences of Lie Group Momentum Optimizers

Lingkai Kong (Georgia Institute of Technology), Molei Tao (Georgia Institute of Technology)

CodeOptimizationTransformerImage

🎯 What it does: This paper proposes two momentum-based Lie group optimizers: Lie Heavy-Ball and Lie NAG-SC, and provides quantitative convergence rates under L-smooth and local strong convexity conditions, verifying the acceleration effect of Lie NAG-SC, while applying it to the optimization of visual Transformers with orthogonal constraints.

Quantum algorithm for large-scale market equilibrium computation

Po-Wei Huang (National University of Singapore), Patrick Rebentrost (National University of Singapore)

CodeOptimizationComputational EfficiencyTabularFinance Related

🎯 What it does: The first quantum equilibrium computation algorithm for the Fisher market is proposed, and iterative updates are achieved through error-proportional response dynamics.

Quantum Deep Equilibrium Models

Philipp Schleich (University of Toronto), Alan Aspuru-Guzik

CodeOptimizationImage

🎯 What it does: A Quantum Deep Equilibrium Model (QDEQ) is proposed, achieving parameter optimization through the use of deep equilibrium techniques on quantum models;

Quasi-Bayes meets Vines

David Huk (University of Warwick), Mark Steel (University of Warwick)

CodeHyperparameter SearchTabular

🎯 What it does: A high-dimensional joint density estimation method combining Bayesian prediction and Vine copula is proposedβ€”Quasi-Bayesian Vine (QB-Vine).

Query-Efficient Correlation Clustering with Noisy Oracle

Yuko Kuroki (CENTAI Institute), Wei Chen (Microsoft Research)

CodeOptimizationGraph

🎯 What it does: A method for achieving query-efficient relevant clustering under unknown and noisy similarity is proposed, along with two pure exploration (fixed confidence / fixed budget) online learning frameworks, corresponding to the KC-FC and KC-FB algorithms.

QUEST: Quadruple Multimodal Contrastive Learning with Constraints and Self-Penalization

Qi Song (Beihang University), Jianxin Li (Beihang University)

CodeRetrievalContrastive LearningMultimodalityAudio

🎯 What it does: The QUEST framework is proposed, which implements quaternion constraints and self-punishment for multimodal contrastive learning through a shared and unique information decoder.

QWO: Speeding Up Permutation-Based Causal Discovery in LiGAMs

Mohammad Shahverdikondori (Γ‰cole Polytechnique FΓ©dΓ©rale de Lausanne), Negar Kiyavash (Γ‰cole Polytechnique FΓ©dΓ©rale de Lausanne)

CodeOptimizationComputational EfficiencyGraph

🎯 What it does: An efficient QWO module is proposed for quickly calculating the causal graph GΟ€ under a given permutation in linear Gaussian acyclic models (LiGAM), significantly accelerating the permutation search process.

R$^2$-Gaussian: Rectifying Radiative Gaussian Splatting for Tomographic Reconstruction

Ruyi Zha (Australian National University), Hongdong Li (Australian National University)

CodeGaussian SplattingImageComputed Tomography

🎯 What it does: The paper proposes a sparse-view CT reconstruction framework based on 3D Gaussian splatting, called R-Gaussian.

RA-PbRL: Provably Efficient Risk-Aware Preference-Based Reinforcement Learning

Yujie Zhao (University of California), Huazheng Wang (Oregon State University)

CodeReinforcement LearningTabularSequential

🎯 What it does: This paper proposes a risk-aware preference reinforcement learning algorithm named RA-PbRL, aimed at addressing the PbRL problem where only complete trajectory preference feedback is available. It demonstrates the theoretical feasibility and lower bounds for achieving nested and static quantile risk objectives.

Rad-NeRF: Ray-decoupled Training of Neural Radiance Field

Lidong Guo (Tsinghua University), Yu Wang (Tsinghua University)

CodeGenerationData SynthesisNeural Radiance FieldGaussian SplattingImage

🎯 What it does: We propose a ray-decoupled training framework called Rad-NeRF, which utilizes sub-NeRF integration and a soft gating module to allocate different sub-models along the ray dimension, achieving better lighting and geometric consistency through deep mutual learning.

RAGraph: A General Retrieval-Augmented Graph Learning Framework

Xinke Jiang (Peking University), Yasha Wang (Peking University)

CodeRetrievalGraph Neural NetworkGraphRetrieval-Augmented Generation

🎯 What it does: A general retrieval-enhanced graph learning framework RAGRAPH is proposed, which improves the generalization ability of pre-trained graph neural networks on unseen graph data by utilizing external graph data through retrieval and information injection.

RAMP: Boosting Adversarial Robustness Against Multiple $l_p$ Perturbations for Universal Robustness

Enyi Jiang (University of Illinois), Gagandeep Singh (University of Illinois)

CodeAdversarial AttackConvolutional Neural NetworkImage

🎯 What it does: Proposes the RAMP framework to enhance joint robustness against various l_p transformations.

RandNet-Parareal: a time-parallel PDE solver using Random Neural Networks

Guglielmo Gattiglio (University of Warwick), Massimiliano Tamborrino (University of Warwick)

CodeTime SeriesPhysics RelatedStochastic Differential EquationOrdinary Differential Equation

🎯 What it does: A novel parallel time solver RandNet-Parareal is proposed, which learns the error between coarse and fine solvers through a random neural network, thereby achieving rapid correction in the Parareal iteration.

Randomized Exploration in Cooperative Multi-Agent Reinforcement Learning

Hao-Lun Hsu (Duke University), Pan Xu (Duke University)

CodeReinforcement Learning

🎯 What it does: A unified framework is proposed for implementing Thompson Sampling-based stochastic exploration algorithmsβ€”CoopTS-PHE and CoopTS-LMCβ€”in parallel MDP environments;

Randomized Sparse Matrix Compression for Large-Scale Constrained Optimization in Cancer Radiotherapy

Shima Adeli (Sharif University of Technology), Masoud Zarepisheh (Memorial Sloan Kettering Cancer Center)

CodeOptimizationBiomedical Data

🎯 What it does: A dose impact matrix compression method based on random sparsification is proposed, enabling the solution of large-scale constrained nonlinear optimization problems in cancer radiotherapy within clinical time windows.

RanDumb: Random Representations Outperform Online Continually Learned Representations

Ameya Prabhu (University of Oxford), Puneet K. Dokania (IIIT Hyderabad)

CodeClassificationRepresentation LearningImage

🎯 What it does: This paper presents RanDumbβ€”a baseline for online continual learning that uses only random Fourier feature projections and a nearest class mean (with Mahalanobis distance) classifier, aimed at evaluating the comparison between random representations and traditional online learning representations.

RankUp: Boosting Semi-Supervised Regression with an Auxiliary Ranking Classifier

Pin-Yen Huang (Academia Sinica), Yu Tsao (Academia Sinica)

CodeOptimizationContrastive LearningImageTextAudio

🎯 What it does: The RankUp framework is proposed, which transforms regression tasks into ranking problems, using an Auxiliary Ranking Classifier (ARC) trained together with semi-supervised classification methods like FixMatch, and introduces an optional Regression Distribution Alignment (RDA) to further improve the quality of pseudo-labels.

RashomonGB: Analyzing the Rashomon Effect and Mitigating Predictive Multiplicity in Gradient Boosting

Hsiang Hsu (JPMorganChase Global Technology Applied Research), Chun-Fu Chen (JPMorganChase AI Research)

CodeOptimizationExplainability and InterpretabilityTabular

🎯 What it does: Analyzes the Rashomon effect in gradient boosting and proposes the RashomonGB method, which efficiently constructs a model ensemble using the residual Rashomon set, further evaluating prediction diversity, interpretability, and fairness.

RaVL: Discovering and Mitigating Spurious Correlations in Fine-Tuned Vision-Language Models

Maya Varma (Stanford University), Curtis Langlotz (Stanford University)

CodeClassificationObject DetectionSegmentationData-Centric LearningTransformerSupervised Fine-TuningVision Language ModelContrastive LearningImageMultimodality

🎯 What it does: This paper proposes the RAVL method, which analyzes fine-grained image regions to automatically discover and eliminate the false correlations learned by visual-language models during fine-tuning, thereby enhancing the model's robustness in zero-shot tasks.

RCDN: Towards Robust Camera-Insensitivity Collaborative Perception via Dynamic Feature-based 3D Neural Modeling

Tianhang Wang (Tongji University), changjun jiang

CodeObject DetectionSegmentationAutonomous DrivingNeural Radiance FieldOptical FlowImageVideo

🎯 What it does: This paper proposes RCDN, an algorithm capable of recovering failed viewpoints and maintaining high accuracy in multi-vehicle collaborative perception scenarios where cameras fail or noise is severe, through collaborative neural rendering.

Real-Time Recurrent Learning using Trace Units in Reinforcement Learning

Esraa Elelimy (University of Alberta), Martha White (University of Alberta)

CodeRecurrent Neural NetworkTransformerReinforcement LearningSequential

🎯 What it does: A lightweight recurrent unit RTU is proposed and evaluated for real-time recursive learning (RTRL) in online reinforcement learning.

Real-Time Selection Under General Constraints via Predictive Inference

Yuyang Huo (Nankai University), Changliang Zou (Nankai University)

CodeOptimizationSupervised Fine-TuningTabular

🎯 What it does: A real-time online sample selection algorithm II-COS is proposed, which can select samples that meet the target response interval while satisfying individual cost constraints and interaction diversity constraints.

Real-time Stereo-based 3D Object Detection for Streaming Perception

Changcai Li (Sun Yat-sen University), Huihui Zhou (Pengcheng Laboratory)

CodeObject DetectionObject TrackingAutonomous DrivingOptical FlowImageVideo

🎯 What it does: A real-time 3D object detection framework called StreamDSGN based on stereo vision is proposed for streaming perception.

Real-world Image Dehazing with Coherence-based Pseudo Labeling and Cooperative Unfolding Network

Chengyu Fang (Shenzhen International Graduate School Tsinghua University), Xiu Li (Shenzhen International Graduate School Tsinghua University)

CodeRestorationKnowledge DistillationImage

🎯 What it does: This paper proposes the Collaborative Unfolding Network (CORUN) and the consistency pseudo-label-based Mean-Teacher framework (Colabator) for achieving high-quality image dehazing in real-world scenarios.

RealCompo: Balancing Realism and Compositionality Improves Text-to-Image Diffusion Models

Xinchen Zhang (Tsinghua University), Bin CUI

CodeGenerationData SynthesisTransformerLarge Language ModelDiffusion modelImageText

🎯 What it does: The RealCompo framework is proposed, which utilizes large language models to generate layouts and integrates pre-trained text-image diffusion models with spatially aware diffusion models (layouts, key points, segmentation, etc.) through a dynamic balancer without training, to achieve a balance between image realism and multi-object composability.

Reasoning Multi-Agent Behavioral Topology for Interactive Autonomous Driving

Haochen Liu (Nanyang Technological University), Hongyang Li (Shanghai AI Lab)

CodeAutonomous DrivingOptimizationTransformerTabular

🎯 What it does: In autonomous driving, simultaneous multi-agent behavior prediction and planning are achieved by introducing a behavior topology (BeTop) based on winding theory to explicitly supervise the consistency of multi-agent future interactions. Furthermore, a collaborative prediction and planning Transformer network, BeTopNet, is designed to control uncertainty and conflicts.

Reasons and Solutions for the Decline in Model Performance after Editing

Xiusheng Huang (Chinese Academy of Sciences), Kang Liu (Chinese Academy of Sciences)

CodeTransformerLarge Language ModelSupervised Fine-TuningText

🎯 What it does: Through experiments from both data and model perspectives, the reasons for the performance decline after knowledge editing were systematically analyzed, and a new sequence editing method called D4S was proposed to mitigate performance loss.

REBEL: Reinforcement Learning via Regressing Relative Rewards

Zhaolin Gao (Cornell University), Wen Sun (Princeton University)

CodeReinforcement LearningText

🎯 What it does: This paper proposes a reinforcement learning algorithm named REBEL, which achieves policy optimization by regressing on 'relative rewards', simplifying the implementation difficulty of traditional RL schemes.

REBORN: Reinforcement-Learned Boundary Segmentation with Iterative Training for Unsupervised ASR

Liang-Hsuan Tseng (National Taiwan University), Shao-Hua Sun (National Taiwan University)

CodeRecognitionSegmentationConvolutional Neural NetworkReinforcement LearningGenerative Adversarial NetworkAudio

🎯 What it does: In unsupervised speech recognition, an iterative training framework called REBORN is proposed, which alternately trains a segmentation model and a phoneme prediction model.

Reciprocal Reward Influence Encourages Cooperation From Self-Interested Agents

John Luoyu Zhou, Jonathan Kao

CodeReinforcement Learning

🎯 What it does: This paper proposes a reinforcement learning agent named Reciprocator, which encourages self-interested agents to cooperate through intrinsic reciprocal rewards.

Reconstruction of Manipulated Garment with Guided Deformation Prior

Ren Li (Γ‰cole Polytechnique FΓ©dΓ©rale de Lausanne), Pascal Fua (Γ‰cole Polytechnique FΓ©dΓ©rale de Lausanne)

CodeRestorationGenerationTransformerDiffusion modelVideoPoint CloudMesh

🎯 What it does: An algorithm is proposed to recover complete 3D meshes from incomplete 3D point clouds of non-worn and manipulated garments using the ISP model, an extended diffusion deformation prior, and a UV mapping network.

RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance

Zhicheng Sun (Peking University), Yadong MU

CodeGenerationData SynthesisDiffusion modelFlow-based ModelRectified FlowImage

🎯 What it does: This paper proposes a personalized image generation method that requires no training, utilizing Anchored Classifier Guidance to guide Rectified Flow, which can maintain identity consistency based on reference images provided by users.

Recurrent Complex-Weighted Autoencoders for Unsupervised Object Discovery

Anand Gopalakrishnan (Swiss AI Lab), Michael Curtis Mozer (Google DeepMind)

CodeObject DetectionConvolutional Neural NetworkAuto EncoderImage

🎯 What it does: A fully convolutional autoencoder (SynCx) is proposed, utilizing complex weights and recursive phase updates to achieve unsupervised object detection.

Recursive PAC-Bayes: A Frequentist Approach to Sequential Prior Updates with No Information Loss

Yi-Shan Wu (University of South Denmark), Yevgeny Seldin (University of Copenhagen)

CodeClassificationOptimizationImage

🎯 What it does: A recursive PAC-Bayes framework is proposed, allowing for sequential prior updates without losing confidence information, and corresponding PAC-Bayes bounds are provided;

REDUCR: Robust Data Downsampling using Class Priority Reweighting

William Bankes (University College London), Zi Wang (Google DeepMind)

CodeOptimizationData-Centric LearningConvolutional Neural NetworkTransformerSupervised Fine-TuningImage

🎯 What it does: This paper proposes an online batch selection method called REDUCR, which implements robust data downsampling using class priority re-weighting, significantly improving the generalization performance of the worst class while reducing the amount of training data.

RefDrop: Controllable Consistency in Image or Video Generation via Reference Feature Guidance

Jiaojiao Fan (Georgia Institute of Technology), Yongxin Chen (Georgia Institute of Technology)

CodeGenerationData SynthesisDiffusion modelImageVideo

🎯 What it does: By incorporating reference feature guidance into the self-attention of the diffusion model UNet, controllable consistency generation that is independent of training has been achieved.

Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models

Shi Luohe (Wuhan University), hai zhao

CodeGenerationRetrievalTransformerLarge Language ModelTextRetrieval-Augmented Generation

🎯 What it does: A training-free, retrieval-based decoding method (Reference Trustable Decoding, RTD) is proposed, which constructs a reference dataset and adjusts the output distribution based on similarity during the decoding phase, allowing LLMs to quickly adapt to downstream tasks while keeping the original parameters unchanged.

Referring Human Pose and Mask Estimation In the Wild

Bo Miao (University of Western Australia), Ajmal Saeed Mian

CodeObject DetectionSegmentationPose EstimationTransformerVision Language ModelImageTextMultimodality

🎯 What it does: Proposed and implemented the 'R-HPM' (Referring Human Pose and Mask Estimation) task, which can accurately predict the joint location information and segmentation mask of a specified person through text or location prompts (scribble/point).

ReFIR: Grounding Large Restoration Models with Retrieval Augmentation

Hang Guo (Tsinghua University), Shu-Tao Xia (Tsinghua University)

CodeRestorationRetrievalDiffusion modelImage

🎯 What it does: A training-free retrieval-enhanced framework called ReFIR is proposed, which uses high-quality reference images obtained through retrieval to help large image restoration models avoid 'hallucinations' and generate more realistic details.

ReFT: Representation Finetuning for Language Models

Zhengxuan Wu (Stanford University), Christopher Potts (Stanford University)

CodeExplainability and InterpretabilityComputational EfficiencyRepresentation LearningTransformerLarge Language ModelSupervised Fine-TuningText

🎯 What it does: This paper proposes and evaluates a parameter-efficient fine-tuning method through low-rank linear subspace intervention (ReFT) on the hidden representations of pre-trained language models, focusing on LoReFT and its efficient variant DiReFT.

Refusal in Language Models Is Mediated by a Single Direction

Andy Arditi (Independent), Neel Nanda

CodeLarge Language ModelText

🎯 What it does: The rejection mechanism in large language models was studied and found to be driven by a single direction.

RegExplainer: Generating Explanations for Graph Neural Networks in Regression Tasks

Jiaxing Zhang (New Jersey Institute of Technology), Hua Wei (Arizona State University)

CodeExplainability and InterpretabilityGraph Neural NetworkContrastive LearningGraph

🎯 What it does: A post-hoc explanation method named RegExplainer is proposed for explaining graph neural networks in graph regression tasks.

Regression under demographic parity constraints via unlabeled post-processing

Gayane Taturyan (Universite Gustave Eiffel), Mohamed Hebiri (Universite Gustave Eiffel)

CodeOptimizationTabular

🎯 What it does: This paper proposes a post-processing algorithm for a regression model that does not require inferring sensitive attributes, ensuring fair predictions under demographic balance constraints.

Regularized Adaptive Momentum Dual Averaging with an Efficient Inexact Subproblem Solver for Training Structured Neural Network

Zih-Syuan Huang (National Taiwan University), Ching-pei Lee (Institute of Statistical Mathematics)

CodeOptimizationConvolutional Neural NetworkTransformerImageTextAudio

🎯 What it does: A new Regularized Adaptive Dual Equilibrium (RAMDA) algorithm is proposed for training deep neural networks with structures (such as sparsity), and an implementable subproblem approximation solver is designed for this algorithm.

Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs

Rui Yang (University of Illinois Urbana-Champaign), Tong Zhang (University of Illinois Urbana-Champaign)

CodeReinforcement Learning from Human FeedbackTransformerLarge Language ModelSupervised Fine-TuningReinforcement LearningText

🎯 What it does: This paper proposes enhancing the generalization of the reward model to unseen data by adding text generation regularization (GRM) in the hidden layers of the reward model, thereby alleviating the issue of reward over-optimization in RLHF.

Reinforced Cross-Domain Knowledge Distillation on Time Series Data

QING XU, Zhenghua Chen (Institute for Infocomm Research A*STAR)

CodeDomain AdaptationKnowledge DistillationReinforcement LearningTime Series

🎯 What it does: This paper proposes an end-to-end cross-domain knowledge distillation framework RCD-KD, which combines reinforcement learning to dynamically select target domain samples and an adversarial domain discriminator to achieve unsupervised domain adaptation for lightweight models in time series tasks.

Reinforcement Learning Gradients as Vitamin for Online Finetuning Decision Transformers

Kai Yan (University of Illinois Urbana-Champaign), Yu-Xiong Wang (University of Illinois Urbana-Champaign)

CodeTransformerReinforcement Learning

🎯 What it does: This paper studies the issue of online fine-tuning of the Decision Transformer after offline pre-training and proposes combining TD3 reinforcement learning gradients with the original self-supervised training to enhance the online fine-tuning effect.

Reinforcement Learning Policy as Macro Regulator Rather than Macro Placer

Ke Xue (Nanjing University), Chao Qian (Huawei Noah's Ark Lab)

CodeOptimizationReinforcement LearningTabularBenchmark

🎯 What it does: This paper proposes a macro regulator method called MaskRegulate based on reinforcement learning, which makes local adjustments on an existing macro layout instead of starting from scratch.

Reinforcement Learning with Adaptive Regularization for Safe Control of Critical Systems

Haozhe Tian (Imperial College London), Pietro Ferraro (Imperial College London)

CodeSafty and PrivacyReinforcement LearningSequential

🎯 What it does: The RL-AR algorithm is proposed, which achieves safe control of critical systems by introducing a safety regularizer (MPC) and an adaptive weight combination of the RL policy during the reinforcement learning process.

Reinforcement Learning with Euclidean Data Augmentation for State-Based Continuous Control

Jinzhu Luo (University of South Carolina), Qi Zhang (University of South Carolina)

CodeRobotic IntelligenceReinforcement Learning

🎯 What it does: A state space data augmentation method based on Euclidean symmetry is proposed, using body-based state representation instead;

Reinforcing LLM Agents via Policy Optimization with Action Decomposition

Muning Wen (Shanghai Jiao Tong University), Ying Wen (Shanghai Jiao Tong University)

CodeOptimizationReinforcement Learning from Human FeedbackTransformerLarge Language ModelSupervised Fine-TuningReinforcement LearningText

🎯 What it does: Proposes Bellman Backup with Action Decomposition (BAD) and combines it with PPO to form POAD, assigning rewards to each intra-action token of the language agent at a finer granularity;

Rejection via Learning Density Ratios

Alexander Soen (Amazon), Vu Nguyen (Amazon)

CodeClassificationAnomaly DetectionOptimizationImage

🎯 What it does: A post-hoc rejection framework based on the idealized distribution density ratio is proposed, which determines when to reject predictions by learning an idealized distribution regularized by α-divergence that is aligned with the original data distribution.

Relating Hopfield Networks to Episodic Control

Hugo Chateau-Laurent (Inria centre of the University of Bordeaux), Frederic Alexandre

CodeRetrievalReinforcement LearningImage

🎯 What it does: This paper proves that the Differentiable Neural Dictionary (DND) used in reinforcement learning is essentially an instance of the Universal Hopfield Network (UHN), and derives the energy function through continuous approximation; it then evaluates its performance in terms of capacity and retrieval on MNIST, CIFAR-10, and Tiny ImageNet.

ReLIZO: Sample Reusable Linear Interpolation-based Zeroth-order Optimization

Xiaoxing Wang (Shanghai Jiao Tong University), Junchi Yan (Shanghai Jiao Tong University)

CodeOptimizationAdversarial AttackNeural Architecture SearchImageText

🎯 What it does: A ReLIZO zero-order optimization method is proposed, which reduces the number of queries and computational complexity while maintaining a constant sample size by estimating gradients through linear interpolation and allowing the reuse of previous queries.

ReMoDetect: Reward Models Recognize Aligned LLM's Generations

Hyunseok Lee (Korea Advanced Institute of Science and Technology), Jinwoo Shin (Korea Advanced Institute of Science and Technology)

CodeRecognitionGenerationTransformerLarge Language ModelReinforcement LearningText

🎯 What it does: A reward model-based alignment framework for detecting LLM-generated text, ReMoDetect, is proposed to distinguish between LLM-generated text and human text.

Remove that Square Root: A New Efficient Scale-Invariant Version of AdaGrad

Sayantan Choudhury (Mohammed Bin Zayed University of Artificial Intelligence), Eduard Gorbunov (Mohammed Bin Zayed University of Artificial Intelligence)

CodeOptimizationImageTabular

🎯 What it does: KATE is proposedβ€”a variant of AdaGrad that removes the square root and achieves scale invariance, and it is proven to have a convergence rate comparable to AdaGrad/Adam on smooth non-convex problems.

ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization

Luca Eyring (Technical University of Munich), Zeynep Akata (Technical University of Munich)

CodeGenerationOptimizationReinforcement LearningImageText

🎯 What it does: A method is proposed to enhance the performance of single-step text-to-image models during the inference phase through Reward-guided Noise Optimization (ReNO).

Reparameterization invariance in approximate Bayesian inference

Hrittik Roy (Technical University of Denmark), SΓΈren Hauberg (Technical University of Denmark)

CodeClassificationAnomaly DetectionOptimizationConvolutional Neural NetworkImageStochastic Differential Equation

🎯 What it does: This paper studies the issue of the lack of reparameterization invariance in approximate posteriors of Bayesian neural networks, proposing the use of Laplace diffusion with pseudo-Riemannian metrics to explain the geometric reasons behind the success of linearized Laplace, and providing a feasible sampling algorithm.

Replay-and-Forget-Free Graph Class-Incremental Learning: A Task Profiling and Prompting Approach

Chaoxi Niu (University of Technology Sydney), Bing Liu (University of Illinois at Chicago)

CodeClassificationGraph Neural NetworkContrastive LearningGraph

🎯 What it does: This study investigates graph-class incremental learning (GCIL) without task IDs, achieving complete no-replay and no-forgetting node classification through task analysis and graph prompts.

Representation Noising: A Defence Mechanism Against Harmful Finetuning

Domenic Rosati (Dalhousie University), Frank Rudzicz (Dalhousie University)

CodeRepresentation LearningAdversarial AttackTransformerLarge Language ModelSupervised Fine-TuningText

🎯 What it does: A defense mechanism called Representation Noising (RepNoise) is proposed, aimed at resisting harmful fine-tuning attacks (HFA) by eliminating intermediate representation information of harmful inputs, making it difficult for attackers to recover harmful capabilities even after obtaining the model weights.

Reprogramming Pretrained Target-Specific Diffusion Models for Dual-Target Drug Design

Xiangxin Zhou (University of Chinese Academy of Sciences), Jianzhu Ma (Tsinghua University)

CodeDrug DiscoveryGraph Neural NetworkDiffusion modelGraphBiomedical Data

🎯 What it does: A generative model for dual-target drug design was developed, and a dual-target dataset based on synergistic drug combinations was constructed.

Repurposing Language Models into Embedding Models: Finding the Compute-Optimal Recipe

Albert Q. Jiang (University of Cambridge), Piotr MiΕ‚oΕ› (University of Warsaw)

CodeTransformerLarge Language ModelSupervised Fine-TuningContrastive LearningText

🎯 What it does: This study investigates the optimal configuration for fine-tuning a pre-trained decoder language model to produce high-quality text embeddings under computational constraints using contrastive loss.

Reranking Laws for Language Generation: A Communication-Theoretic Perspective

AntΓ³nio Farinhas (Instituto Superior TΓ©cnico, Universidade de Lisboa), Andre Martins

CodeGenerationAI Code AssistantTransformerLarge Language ModelText

🎯 What it does: This paper proposes viewing the generator-reorderer system as a communication system and proves that under multi-path redundancy generation and reordering, the probability of incorrect answers can decay exponentially/power-law with the number of candidates N, achieving asymptotically error-free generation.

ResAD: A Simple Framework for Class Generalizable Anomaly Detection

Xincheng Yao (Shanghai Jiao Tong University), Chongyang Zhang (Shanghai Jiao Tong University)

CodeAnomaly DetectionConvolutional Neural NetworkImageVideoBenchmark

🎯 What it does: Proposes the ResAD framework, which utilizes residual features to achieve class-generalizable anomaly detection.

Resfusion: Denoising Diffusion Probabilistic Models for Image Restoration Based on Prior Residual Noise

Zhenning Shi (Nankai University), Huazhu Fu (Institute of High Performance Computing)

CodeRestorationConvolutional Neural NetworkDiffusion modelImage

🎯 What it does: A general framework named Resfusion is proposed, which introduces residual terms into the diffusion forward process and directly starts from the noisy degraded image to complete the reverse recovery.

ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search

Dan Zhang (Tsinghua University), Jie Tang (Tsinghua University)

CodeReinforcement Learning from Human FeedbackTransformerLarge Language ModelSupervised Fine-TuningReinforcement LearningTextBenchmark

🎯 What it does: Proposes ReST-MCTS, which utilizes tree search MCTS* and an automatically generated process reward model to perform dual training of the strategy and reward model for LLM in a self-supervised manner, generating high-quality reasoning trajectories.

Rethinking Decoders for Transformer-based Semantic Segmentation: A Compression Perspective

Qishuai Wen (Beijing University of Posts and Telecommunications), Chun-Guang Li (Beijing University of Posts and Telecommunications)

CodeSegmentationCompressionTransformerImage

🎯 What it does: A Transformer decoder based on compression theory (DEPICT) is proposed, which completes semantic segmentation through PCA and a gradient-free expansion of coding rate, designing fully attention-based self-attention and cross-attention modules.

Rethinking Fourier Transform from A Basis Functions Perspective for Long-term Time Series Forecasting

Runze Yang (Shanghai Jiao Tong University), li jianxun

CodeTransformerTime Series

🎯 What it does: This paper proposes and implements Fourier Basis Mapping (FBM), treating the discrete Fourier transform as an expansion of sine and cosine basis functions, generating features that incorporate both time and frequency information. It achieves long-term time series prediction through three mapping networks: linear, MLP, and Transformer, while addressing the issues of inconsistent starting periods and sequence lengths present in existing Fourier-based methods.

Rethinking Human Evaluation Protocol for Text-to-Video Models: Enhancing Reliability, Reproducibility, and Practicality

Tianle Zhang (Shanghai AI Laboratory), Kaipeng Zhang (Shanghai AI Laboratory)

CodeGenerationData SynthesisPrompt EngineeringVideoText

🎯 What it does: A standardized human evaluation protocol for text-to-video generation models, T2VHE, is proposed to address the issues of repeatability, reliability, and practicality in existing evaluations.

Rethinking Imbalance in Image Super-Resolution for Efficient Inference

Wei Yu (Harbin Institute of Technology), Xiangyang Ji (Tsinghua University)

CodeRestorationSuper ResolutionImage

🎯 What it does: This study investigates the imbalance problem of data distribution and model optimization in image super-resolution, proposing a weight balancing framework WBSR, which includes Hierarchical Equitable Sampling (HES) and Balanced Diversity Loss (BDLoss), and presents a gradient projection dynamic inference strategy.

Rethinking Inverse Reinforcement Learning: from Data Alignment to Task Alignment

Weichao Zhou (Boston University), Wenchao Li (Boston University)

CodeRobotic IntelligenceReinforcement Learning from Human FeedbackReinforcement LearningGenerative Adversarial Network

🎯 What it does: A new Inverse Reinforcement Learning (IRL) framework is proposed, prioritizing task alignment over traditional data alignment, utilizing expert demonstrations as weak supervision signals, and deriving a set of candidate reward functions to better reflect task objectives.

Rethinking Out-of-Distribution Detection on Imbalanced Data Distribution

Kai Liu (Zhejiang University), Jieping Ye (Alibaba Cloud)

CodeAnomaly DetectionConvolutional Neural NetworkImage

🎯 What it does: A framework for OOD detection called ImOOD is proposed, which can correct the bias caused by class imbalance through regularization during the training phase, improving the accuracy of OOD detection under long-tail data distribution.

Rethinking the Diffusion Models for Missing Data Imputation: A Gradient Flow Perspective

Zhichao Chen (Zhejiang University), Hao Wang (Zhejiang University)

CodeDiffusion modelScore-based ModelTabularOrdinary Differential Equation

🎯 What it does: Proposes NewImp, a framework for missing data imputation based on Wasserstein Gradient Flow in diffusion models.

Rethinking the Membrane Dynamics and Optimization Objectives of Spiking Neural Networks

Hangchi Shen (Southwest University), Gang Pan (Zhejiang University)

CodeClassificationOptimizationSpiking Neural NetworkSupervised Fine-TuningImage

🎯 What it does: A learnable initial membrane potential (IMP) is proposed to enhance the expressive capability of spiking neural networks, combined with LTS processing and label smoothing TET loss to improve performance on static and event data.

Rethinking the Power of Timestamps for Robust Time Series Forecasting: A Global-Local Fusion Perspective

Chengsen Wang (Beijing University of Posts and Telecommunications), Jianxin Liao (Beijing University of Posts and Telecommunications)

CodeTransformerTime Series

🎯 What it does: A general plugin framework GLAFF is proposed, which utilizes global information from timestamps to enhance the robustness of mainstream time series forecasting models.