arXivSub Start free trial

NeurIPS 2023 Papers with Code β€” Page 14

Conference on Neural Information Processing Systems Β· 1376 papers

Understanding and Improving Feature Learning for Out-of-Distribution Generalization

Yongqiang Chen (Chinese University of Hong Kong), James Cheng (Chinese University of Hong Kong)

CodeDomain AdaptationRepresentation LearningConvolutional Neural NetworkImage

🎯 What it does: This paper explores the behavior of ERM and OOD objectives in feature learning through theoretical analysis and experiments, and proposes the Feature Augmented Training (FeAT) iterative method to obtain richer features and enhance OOD generalization performance.

Understanding and Mitigating Copying in Diffusion Models

Gowthami Somepalli (University of Maryland), Tom Goldstein (University of Maryland)

CodeGenerationDiffusion modelImageText

🎯 What it does: Analyzes the replication behavior of diffusion models under text conditions and proposes various de-duplication strategies during training and inference.

Understanding Contrastive Learning via Distributionally Robust Optimization

Junkang Wu (University of Science and Technology of China), Xiangnan He (University of Science and Technology of China)

CodeOptimizationRepresentation LearningContrastive LearningImageText

🎯 What it does: By viewing contrastive learning as distributionally robust optimization, this paper provides a theoretical analysis that explains the tolerance of contrastive learning to negative sample sampling bias and proposes a new weighted InfoNCE lossβ€”ADNCEβ€”to alleviate issues of excessive conservativeness and sensitivity to outliers.

Understanding Deep Gradient Leakage via Inversion Influence Functions

Haobo Zhang (Michigan State University), Jiayu Zhou (Michigan State University)

CodeSafty and PrivacyAdversarial AttackConvolutional Neural NetworkTransformerImageText

🎯 What it does: The problem of Deep Gradient Leakage (DGL) is analyzed by proposing and validating the Inverse Influence Function (I2F), providing both empirical and theoretical results.

Understanding Few-Shot Learning: Measuring Task Relatedness and Adaptation Difficulty via Attributes

Minyang Hu (Institute of Computing Technology, Chinese Academy of Sciences), Xilin CHEN

CodeMeta LearningImage

🎯 What it does: Proposed and validated the Task Attribute Distance (TAD) metric to measure the correlation between training tasks and new tasks, as well as the adaptation difficulty of new tasks;

Understanding the Latent Space of Diffusion Models through the Lens of Riemannian Geometry

Yong-Hyun Park (Seoul National University), Youngjung Uh (Seoul National University)

CodeGenerationDiffusion modelImageText

🎯 What it does: This paper analyzes the latent space of diffusion models through pullback metrics, extracts local latent bases, and utilizes them to achieve image editing in the latent space at a single moment. It further studies the evolution of the latent structure with diffusion steps and the impact of text prompts.

Undirected Probabilistic Model for Tensor Decomposition

Zerui Tao (Tokyo University of Agriculture and Technology), Qibin Zhao (RIKEN AIP)

CodeContrastive LearningMultimodalityTime Series

🎯 What it does: A framework for undirected tensor decomposition is constructed through deep energy-based models (EBM) to jointly learn tensor observations and latent factors, thereby achieving probabilistic modeling of non-Gaussian, multimodal data.

Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models

Shihao Zhao (University of Hong Kong), Kwan-Yee K. Wong (University of Hong Kong)

CodeGenerationData SynthesisDiffusion modelImageText

🎯 What it does: This paper proposes Uni-ControlNet, a unified framework that can simultaneously utilize various local (such as edges, depth, segmentation, etc.) and global (such as CLIP image embeddings) control signals within a single model, enabling composable text-to-image diffusion model control.

Uni3DETR: Unified 3D Detection Transformer

Zhenyu Wang (Tsinghua University), Shengjin Wang (Tsinghua University)

CodeObject DetectionAutonomous DrivingTransformerPoint Cloud

🎯 What it does: This paper proposes Uni3DETR, a unified 3D object detection framework capable of handling both indoor and outdoor point clouds.

UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild

Can Qin (Northeastern University), Ran Xu (Salesforce AI Research)

CodeSegmentationGenerationData SynthesisMixture of ExpertsDiffusion modelImageText

🎯 What it does: We propose and train UniControl, a unified diffusion model capable of handling multiple visual conditions (edges, segmentation, depth, skeletons, etc.) and text prompts to achieve controllable image generation.

Unified 3D Segmenter As Prototypical Classifiers

Zheyun Qin (Shandong University), Xiankai Lu (Shandong University)

CodeSegmentationTransformerPoint Cloud

🎯 What it does: A prototype-based unified framework called PROTOSEG is proposed, which unifies semantic, instance, and panoptic segmentation tasks into classification problems of different granularities, using Transformers to extract point embeddings and achieve classification through dynamic prototype association and updating.

Unified Embedding: Battle-Tested Feature Representations for Web-Scale ML Systems

Benjamin Coleman (Google DeepMind), Derek Zhiyuan Cheng (Google DeepMind)

CodeRecommendation SystemOptimizationTabularBenchmark

🎯 What it does: Proposes a Feature Multiplexing framework that allows multiple classification features to share the same embedding space, and based on this, designs a Unified Embedding that significantly reduces model parameters and latency.

Unified Off-Policy Learning to Rank: a Reinforcement Learning Perspective

Zeyu Zhang (University of Science and Technology of China), Mengdi Wang (Princeton University)

CodeRecommendation SystemOptimizationTransformerReinforcement LearningTabular

🎯 What it does: Unified the problem of Off-Policy Learning to Rank as a Markov Decision Process (MDP) and directly learned the optimal ranking policy through offline reinforcement learning (RL).

Unified Segment-to-Segment Framework for Simultaneous Sequence Generation

Shaolei Zhang (Chinese Academy of Sciences), Yang Feng (Chinese Academy of Sciences)

CodeRecognitionGenerationTransformerTextAudio

🎯 What it does: A unified paragraph-to-paragraph framework (Seg2Seg) is proposed, which introduces latent paragraphs as a bridge to learn source-target adaptive mapping in real-time sequence generation (such as streaming ASR, synchronous MT, and synchronous ST) and achieves multi-task learning.

UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models

Wenliang Zhao (Tsinghua University), Jiwen Lu (Tsinghua University)

CodeGenerationComputational EfficiencyDiffusion modelImageOrdinary Differential Equation

🎯 What it does: A unified prediction-correction framework called UniPC is proposed to accelerate the sampling of diffusion probabilistic models.

UniTSFace: Unified Threshold Integrated Sample-to-Sample Loss for Face Recognition

Qiufu Li (Shenzhen University), Jinming Duan (University of Birmingham)

CodeRecognitionConvolutional Neural NetworkContrastive LearningImage

🎯 What it does: A unified threshold integrated sample-to-sample loss (USS loss) is proposed, which learns a unified threshold to distinguish between positive and negative face pairs;

Universal Prompt Tuning for Graph Neural Networks

Taoran Fang (Zhejiang University), Lei CHEN

CodeGraph Neural NetworkPrompt EngineeringGraphBiomedical Data

🎯 What it does: A general prompt tuning method for pre-trained graph neural networks (Graph Prompt Feature, GPF and its variant GPF-plus) is proposed, which adapts to downstream tasks by adding learnable prompt vectors in the graph node feature space without modifying the model itself.

Unleash the Potential of Image Branch for Cross-modal 3D Object Detection

Yifan Zhang (City University of Hong Kong), Guoliang Xing (Chinese University of Hong Kong)

CodeObject DetectionAutonomous DrivingConvolutional Neural NetworkImagePoint Cloud

🎯 What it does: A cross-modal 3D object detection framework UPIDet is proposed, which utilizes image information to enhance point cloud detection performance.

Unleashing the Full Potential of Product Quantization for Large-Scale Image Retrieval

Yu Liang (Hunan University), Xiaoyu Wang (Hong Kong University of Science and Technology)

CodeRetrievalConvolutional Neural NetworkImage

🎯 What it does: A product quantization framework FPPQ based on deep learning is proposed, which utilizes a softmax differentiable PQ branch to learn category-level PQ codes, aiming to enhance the performance of large-scale image retrieval.

Unleashing the Power of Graph Data Augmentation on Covariate Distribution Shift

Yongduo Sui (University of Science and Technology of China), Xiangnan He (Ant Group)

CodeClassificationDomain AdaptationGraph Neural NetworkGenerative Adversarial NetworkGraph

🎯 What it does: A framework named Adversarial Invariant Augmentation (AIA) is proposed for graph data augmentation to address the covariate shift problem in graph classification tasks; it enhances environmental features differentially while keeping stable features unchanged, improving the model's generalization performance in unseen environments.

Unleashing the Power of Randomization in Auditing Differentially Private ML

Krishna Pillutla (Google Research), Sewoong Oh (University of Washington)

CodeSafty and PrivacyGaussian SplattingTabular

🎯 What it does: Audit differential privacy machine learning algorithms and propose adding multiple random 'canaries' to the dataset for multiple statistical tests.

Unlimiformer: Long-Range Transformers with Unlimited Length Input

Amanda Bertsch (Carnegie Mellon University), Matthew R. Gormley (Carnegie Mellon University)

CodeTransformerTextRetrieval-Augmented Generation

🎯 What it does: The existing pre-trained encoder-decoder Transformer is modified to use k-NN retrieval to focus only on the top k most relevant keys in the cross-attention, enabling the processing of inputs of infinite length.

Unlocking Deterministic Robustness Certification on ImageNet

Kai Hu (Carnegie Mellon University), Matt Fredrikson (Carnegie Mellon University)

CodeClassificationOptimizationAdversarial AttackConvolutional Neural NetworkDiffusion modelImage

🎯 What it does: Design and train the LiResNet architecture and EMMA loss to achieve provably robust deep networks.

Unlocking Feature Visualization for Deep Network with MAgnitude Constrained Optimization

Thomas FEL, Thomas Serre (Brown University)

CodeGenerationOptimizationExplainability and InterpretabilityConvolutional Neural NetworkTransformerImage

🎯 What it does: A new feature visualization method called MACO is proposed, which utilizes amplitude constraints of the Fourier spectrum and phase optimization to generate natural image explanations.

UNSSOR: Unsupervised Neural Speech Separation by Leveraging Over-determined Training Mixtures

Zhong-Qiu Wang (Carnegie Mellon University), Shinji Watanabe (Carnegie Mellon University)

CodeRecognitionRestorationConvolutional Neural NetworkAudio

🎯 What it does: This paper proposes the UNSSOR method, which utilizes overdetermined mixed signals (more microphones than speakers) to train a neural network under unsupervised conditions by constructing a mixed constraint loss, achieving speech separation; after training, it can be used for single-microphone (underdetermined) separation.

Unsupervised Anomaly Detection with Rejection

Lorenzo Perini (KU Leuven), Jesse Davis (KU Leuven)

CodeAnomaly DetectionImageTabularTime SeriesBiomedical DataFinance RelatedAudio

🎯 What it does: This paper proposes an unsupervised learning to reject framework REJEX, which sets a constant threshold in anomaly detection using the EXCEED stability measure, thereby enabling the rejection of predictions for highly uncertain samples.

Unsupervised Optical Flow Estimation with Dynamic Timing Representation for Spike Camera

Lujie Xia (Peking University), Ruiqin Xiong (Peking University)

CodeAutonomous DrivingConvolutional Neural NetworkSpiking Neural NetworkOptical FlowImageVideo

🎯 What it does: A novel unsupervised optical flow estimation method for event cameras, USFlow, is proposed, which utilizes multi-layer dilated convolutions to achieve dynamic temporal representation, extracts features from multi-scale temporal windows, and constructs a self-supervised loss through optical flow-guided light intensity fusion.

Unsupervised Polychromatic Neural Representation for CT Metal Artifact Reduction

Qing Wu (ShanghaiTech University), Yuyao Zhang (ShanghaiTech University)

CodeRestorationImageComputed Tomography

🎯 What it does: Proposes an unsupervised multi-energy neural representation (Polyner) that directly recovers metal artifact-free images from CT projections affected by metal;

Unsupervised Video Domain Adaptation for Action Recognition: A Disentanglement Perspective

Pengfei Wei (ByteDance), Xiang Yin (ByteDance)

CodeRecognitionDomain AdaptationAuto EncoderContrastive LearningVideoMultimodality

🎯 What it does: This paper proposes an unsupervised video domain adaptation framework based on a separable variational autoencoder (TranSVAE), specifically for action recognition tasks.

UP-NeRF: Unconstrained Pose Prior-Free Neural Radiance Field

Injae Kim (Korea University), Hyunwoo J. Kim (Korea University)

CodeGenerationPose EstimationTransformerNeural Radiance FieldImage

🎯 What it does: A method called UP-NeRF is proposed, which jointly optimizes camera poses and neural radiance fields to achieve high-quality view synthesis without camera pose priors and in the presence of inconsistent lighting and transient occlusions.

Use perturbations when learning from explanations

Juyeon Heo (University of Cambridge), Adrian Weller (Alan Turing Institute)

CodeExplainability and InterpretabilityImage

🎯 What it does: This paper rephrases the framework of Model Explanation (MLX) as a robustness problem, utilizing human-provided explanation masks to define the perturbation space, thereby training models that are robust to irrelevant features without requiring strong parameter smoothing.

Utilitarian Algorithm Configuration

Devon R. Graham (University of British Columbia), Tim Roughgarden (Columbia University)

CodeOptimizationTabular

🎯 What it does: This paper proposes a utility function-based algorithm configuration method called Utilitarian Procrastination, addressing the shortcomings of traditional expected runtime minimization and providing theoretical guarantees.

VanillaNet: the Power of Minimalism in Deep Learning

Hanting Chen (Huawei Noah's Ark Lab), Dacheng Tao (University of Sydney)

CodeObject DetectionSegmentationConvolutional Neural NetworkImage

🎯 What it does: A minimalist convolutional network called VanillaNet is proposed, which removes depth, shortcut connections, and self-attention, using only a minimalist module of 1Γ—1 convolution + BN + activation. A deep training strategy and a series of activation functions are employed during training to enhance non-linearity.

Variance-Reduced Gradient Estimation via Noise-Reuse in Online Evolution Strategies

Oscar Li (Carnegie Mellon University), Luke Metz (OpenAI)

CodeOptimizationReinforcement LearningTime SeriesSequential

🎯 What it does: This paper proposes an online unbiased, low-variance evolutionary strategy gradient estimation method called NRES, which addresses the high variance and slow convergence issues of traditional online ES.

Variational Annealing on Graphs for Combinatorial Optimization

Sebastian Sanokowski (Johannes Kepler University Linz), Sebastian Lehner (Johannes Kepler University Linz)

CodeOptimizationGraph Neural NetworkReinforcement LearningGraph

🎯 What it does: The VAG-CO method is proposed, which solves combinatorial optimization problems using a self-regressive variational adaptive graph model.

Variational Inference with Gaussian Score Matching

Chirag Modi (Flatiron Institute), Lawrence K. Saul (Flatiron Institute)

CodeOptimizationScore-based ModelTabular

🎯 What it does: A variational inference method based on score matching (GSM-VI) is proposed, which achieves closed-form iterative updates of Gaussian family variational distributions by minimizing the KL distance at each step and enforcing the matching of the posterior and the gradient of the variational distribution.

Variational Weighting for Kernel Density Ratios

Sangwoong Yoon (Korea Institute for Advanced Study), Yung-Kyun Noh (Korea Institute for Advanced Study)

CodeObject DetectionAnomaly DetectionOptimizationGenerative Adversarial NetworkImageTabular

🎯 What it does: This paper proposes Variational Weighted Kernel Density Estimation (VWKDE), which reduces bias in density ratio estimation by applying position-dependent weight functions to the kernel, and applies this method to posterior probability and KL divergence interpolation estimation.

VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset

Sihan Chen (University of Chinese Academy of Sciences), Jing Liu (University of Chinese Academy of Sciences)

CodeGenerationRetrievalTransformerLarge Language ModelContrastive LearningVideoTextMultimodalityAudio

🎯 What it does: A multimodal video subtitle dataset VAST-27M with a scale of 27M has been constructed, and a foundational model VAST capable of perceiving visual, audio, subtitle, and text modalities has been trained.

VCC: Scaling Transformers to 128K Tokens or More by Prioritizing Important Tokens

Zhanpeng Zeng (University of Wisconsin Madison), Shuai Zheng (AWS AI)

CodeCompressionComputational EfficiencyTransformerText

🎯 What it does: This paper proposes the VIP-Token Focused Compression (VCC) scheme, which compresses and decompresses long sequences between Transformer layers, significantly reducing the computational and memory requirements for sequence length.

VeriX: Towards Verified Explainability of Deep Neural Networks

Min Wu (Stanford University), Clark Barrett (Stanford University)

CodeAutonomous DrivingExplainability and InterpretabilityImage

🎯 What it does: This paper proposes VERIX, which generates optimal robust explanations and counterfactuals on decision boundaries based on constraint solving and feature sensitivity ranking.

ViCA-NeRF: View-Consistency-Aware 3D Editing of Neural Radiance Fields

Jiahua Dong (University of Illinois Urbana-Champaign), Yu-Xiong Wang (University of Illinois Urbana-Champaign)

CodeImage TranslationGenerationDiffusion modelNeural Radiance FieldImage

🎯 What it does: By combining text prompts with a two-dimensional diffusion model (Instruct-Pix2Pix) and utilizing NeRF depth information to edit key views, a 3D editing framework called ViCA-NeRF is proposed, which propagates edits to the panorama through projection and mixing methods while maintaining viewpoint consistency.

VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks

Wenhai Wang (Chinese University of Hong Kong), Jifeng Dai (Tsinghua University)

CodeObject DetectionSegmentationTransformerLarge Language ModelVision Language ModelImage

🎯 What it does: Proposes the VisionLLM framework, using LLM as an open decoder to accomplish vision-centric tasks.

Visual Explanations of Image-Text Representations via Multi-Modal Information Bottleneck Attribution

Ying Wang (New York University), Andrew Gordon Wilson (New York University)

CodeExplainability and InterpretabilityTransformerContrastive LearningImageTextMultimodality

🎯 What it does: Proposes an explainability method based on multimodal information bottleneck (M2IB) for generating attribution maps for image-text pairs;

Visual Instruction Tuning

Haotian Liu (University of Wisconsin Madison), Yong Jae Lee (Columbia University)

CodeRecognitionGenerationRetrievalTransformerLarge Language ModelSupervised Fine-TuningVision Language ModelImageTextMultimodalityBenchmark

🎯 What it does: This study proposes LLaVA (Large Language and Vision Assistant), a multimodal model capable of visual question answering and chatting, by connecting the CLIP visual encoder with the Vicuna LLM through linear projection and performing end-to-end instruction tuning on visual instruction-following data generated by GPT-4.

VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models

Ziyi Yin (Pennsylvania State University), Fenglong Ma (Pennsylvania State University)

CodeRecognitionAdversarial AttackTransformerVision Language ModelImageTextMultimodality

🎯 What it does: This paper studies adversarial attacks on downstream fine-tuning models using only publicly available pre-trained vision-language models under black-box conditions, and proposes the VLATTACK method.

Vocabulary-free Image Classification

Alessandro Conti (University of Trento), Elisa Ricci (Fondazione Bruno Kessler)

CodeClassificationRetrievalTransformerVision Language ModelImageMultimodality

🎯 What it does: Proposes the Vocabulary-free Image Classification (VIC) task and develops the CaSED method to achieve vocabulary-free image classification.

VoxDet: Voxel Learning for Novel Instance Detection

Bowen Li (Carnegie Mellon University), Sebastian Scherer (Carnegie Mellon University)

CodeObject DetectionPoint Cloud

🎯 What it does: This paper proposes a voxel learning-based 3D geometric perception framework called VoxDet, designed for detecting unseen instances under multi-view template conditions.

VPGTrans: Transfer Visual Prompt Generator across LLMs

Ao Zhang (National University of Singapore), Tat-Seng Chua (National University of Singapore)

CodeTransformerLarge Language ModelPrompt EngineeringVision Language ModelImageTextMultimodality

🎯 What it does: A two-stage visual prompt generator (VPG) transfer framework called VPGTrans is proposed, which can efficiently transfer VPG between different LLM sizes and types, significantly reducing training costs.

VPP: Efficient Conditional 3D Generation via Voxel-Point Progressive Representation

Zekun Qi (Xi'an Jiaotong University), Kaisheng Ma (Tsinghua University)

CodeGenerationData SynthesisTransformerGenerative Adversarial NetworkPoint Cloud

🎯 What it does: A 3D generation method based on voxel-point progressive generation (VPP) is proposed, which can efficiently generate multi-category, high-resolution point clouds and supports downstream tasks such as editing and completion.

VRA: Variational Rectified Activation for Out-of-distribution Detection

Mingyu Xu (Chinese Academy of Sciences), Jianhua Tao (Tsinghua University)

CodeAnomaly DetectionConvolutional Neural NetworkTransformerImage

🎯 What it does: A post-hoc OOD detection method called VRA (Variational Rectified Activation) is proposed, which designs an activation function through variational methods to suppress abnormally low/high activations and amplify intermediate activations.

Vulnerabilities in Video Quality Assessment Models: The Challenge of Adversarial Attacks

Aoxiang Zhang, Yuan-Gen Wang (Guangzhou University)

CodeAdversarial AttackVideo

🎯 What it does: A robustness evaluation of no-reference video quality assessment (NR-VQA) models is conducted, systematically studying their vulnerability to adversarial attacks for the first time, and proposing a white-box attack method based on Score-Reversed Boundary Loss and a black-box attack method based on patch random search.

Wasserstein distributional robustness of neural networks

Xingjian Bai (University of Oxford), Jan Obloj

CodeOptimizationAdversarial AttackConvolutional Neural NetworkImage

🎯 What it does: This paper proposes a framework based on Wasserstein Distributionally Robust Optimization (W-DRO) to unify the study of adversarial attacks and robust training of neural networks, and extends it to distributed threat models.

Weakly Supervised 3D Open-vocabulary Segmentation

Kunhao Liu (Nanyang Technological University), Shijian Lu (Nanyang Technological University)

CodeSegmentationKnowledge DistillationNeural Radiance FieldContrastive LearningImage

🎯 What it does: Through weak supervision, knowledge distillation from CLIP and DINO to NeRF is achieved for open vocabulary segmentation of 3D scenes.

Weakly-Supervised Concealed Object Segmentation with SAM-based Pseudo Labeling and Multi-scale Feature Grouping

Chunming He (Shenzhen International Graduate School Tsinghua University), Xiu Li (Shenzhen International Graduate School Tsinghua University)

CodeObject DetectionSegmentationConvolutional Neural NetworkImage

🎯 What it does: Utilize SAM to generate pseudo-masks under sparse annotations (points/strokes) and train a weakly supervised hidden object segmentation model through multi-scale feature grouping (MFG).

What Can We Learn from Unlearnable Datasets?

Pedro Sandoval-Segura (University of Maryland), Tom Goldstein (University of Maryland)

CodeAdversarial AttackData-Centric LearningConvolutional Neural NetworkImage

🎯 What it does: This study evaluates the vulnerable 'non-learnable' datasets, revealing their impact on deep learning models and proposing new cracking methods.

What Do Deep Saliency Models Learn about Visual Attention?

Shi Chen (University of Minnesota), Qi Zhao (University of Minnesota)

CodeExplainability and InterpretabilityConvolutional Neural NetworkImage

🎯 What it does: An interpretable framework has been developed to decompose the implicit features of deep saliency models into trainable bases, and to quantitatively measure the positive and negative contributions of each semantic to saliency prediction through probability mapping and semantic alignment, thereby enabling a systematic analysis of model behavior.

What functions can Graph Neural Networks compute on random graphs? The role of Positional Encoding

Nicolas Keriven (Centre National de la Recherche Scientifique), Samuel Vaiter (Centre National de la Recherche Scientifique)

CodeGraph Neural NetworkGraph

🎯 What it does: This study investigates the expressible function space of graph neural networks (GNNs) on large random graphs for node tasks and analyzes the impact of positional encoding on expressiveness.

What Makes Good Examples for Visual In-Context Learning?

Yuanhan Zhang (Nanyang Technological University), Ziwei Liu (Nanyang Technological University)

CodeObject DetectionSegmentationContrastive LearningImage

🎯 What it does: This study investigates how to enhance context learning effects in visual large models by automatically retrieving good examples, proposing both unsupervised and supervised retrieval frameworks.

When Demonstrations meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning

Siliang Zeng (University of Minnesota), Mingyi Hong (University of Minnesota)

CodeRobotic IntelligenceReinforcement LearningWorld ModelSequential

🎯 What it does: This paper proposes an offline inverse reinforcement learning framework based on maximum likelihood estimation, which jointly learns the reward function and optimal policy using a world model and a conservative policy.

When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment

Tianwei Ni (Mila UniversitΓ© de MontrΓ©al), Pierre-Luc Bacon (Mila UniversitΓ© de MontrΓ©al)

CodeRecurrent Neural NetworkTransformerReinforcement LearningSequential

🎯 What it does: This paper systematically analyzes the memory and credit assignment capabilities of Transformers in reinforcement learning, proposes formal definitions for memory length and credit assignment length, and designs configurable toy tasks (such as Passive/Active T-Maze) to decouple these two capabilities. It then evaluates Transformer-based and LSTM-based RL algorithms in various POMDP environments (including custom T-Maze, Passive/Active Visual Match, Key-to-Door, PyBullet Benchmarks, etc.) to explore their performance under different memory/credit assignment lengths.

When Visual Prompt Tuning Meets Source-Free Domain Adaptive Semantic Segmentation

Xinhong Ma (Huawei Noah's Ark Lab), Yunhe Wang (Huawei Noah's Ark Lab)

CodeSegmentationDomain AdaptationTransformerPrompt EngineeringImage

🎯 What it does: A visual prompt tuning framework for source-free domain adaptive semantic segmentation, Uni-UVPT, is proposed, which adapts a frozen Transformer model using only a small number of learnable parameters.

Where Did I Come From? Origin Attribution of AI-Generated Images

Zhenting Wang (Rutgers University), Shiqing Ma (Sony AI)

CodeGenerationData SynthesisOptimizationImage

🎯 What it does: A model-agnostic AI image source attribution method has been developed without modifications, utilizing reverse engineering to reconstruct inputs and distinguishing whether an image was generated by a specific model through reconstruction loss;

Which Models have Perceptually-Aligned Gradients? An Explanation via Off-Manifold Robustness

Suraj Srinivas (Harvard University), Himabindu Lakkaraju (Harvard University)

CodeClassificationRecognitionDiffusion modelImage

🎯 What it does: This study investigates the phenomenon of perceptual alignment of robust model gradients, proposing discrete manifold robustness to explain why gradients lie on the signal manifold, and introduces signal-interference decomposition.

Why think step by step? Reasoning emerges from the locality of experience

Ben Prystawski (Stanford University), Noah Goodman

CodeTransformerLarge Language ModelChain-of-Thought

🎯 What it does: The effectiveness of chain reasoning in language models was studied, and it was demonstrated that the local structure of training data allows intermediate reasoning steps to reduce bias.

Window-Based Distribution Shift Detection for Deep Neural Networks

Guy Bar-Shalom (Technion Israel Institute of Technology), Ran El-Yaniv (Technion Israel Institute of Technology)

CodeClassificationDomain AdaptationAnomaly DetectionConvolutional Neural NetworkTransformerImage

🎯 What it does: A coverage-based window distribution shift detection method (Coverage-Based Detection, CBD) is proposed, which monitors whether the input stream undergoes distribution changes by calculating the lower bound of coverage based on the confidence (such as entropy) of the pre-trained model.

Winner Takes It All: Training Performant RL Populations for Combinatorial Optimization

Nathan Grinsztajn (InstaDeep), Thomas D Barrett

CodeOptimizationTransformerReinforcement LearningTabular

🎯 What it does: A population-based reinforcement learning method called Poppy is proposed to solve NP-hard combinatorial optimization problems by training a set of complementary strategies to improve the quality of solutions during inference.

Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model

Zirui Liu (Rice University), Xia Hu (Rice University)

CodeTransformerLarge Language ModelSupervised Fine-TuningText

🎯 What it does: A new unbiased sampling matrix multiplication estimation method WTA-CRS is proposed to significantly reduce activation storage during Transformer training while maintaining gradient unbiasedness.

WITRAN: Water-wave Information Transmission and Recurrent Acceleration Network for Long-range Time Series Forecasting

Yuxin Jia (Beijing Jiaotong University), Huaiyu Wan (Beijing Jiaotong University)

CodeRecurrent Neural NetworkTransformerTime Series

🎯 What it does: A new time series long-short term information transmission framework called WIT (Water-wave Information Transmission) is proposed, and based on this, a Recursive Accelerated Network (RAN) is constructed to efficiently capture global/local associations and long/short cycle repetitive semantics for long/ultra-long sequence prediction.

Would I have gotten that reward? Long-term credit assignment by counterfactual contribution analysis

Alexander Meulemans (ETH ZΓΌrich), Greg Wayne

CodeReinforcement LearningContrastive Learning

🎯 What it does: This paper proposes a model-based long-term credit allocation method called COCOA (Counterfactual Contribution Analysis), which achieves more accurate policy gradient estimation by inferring the contribution of actions to future rewards.

You Only Condense Once: Two Rules for Pruning Condensed Datasets

Yang He (Agency for Science Technology and Research), Joey Tianyi Zhou (Agency for Science Technology and Research)

CodeData SynthesisCompressionConvolutional Neural NetworkRecurrent Neural NetworkImage

🎯 What it does: The YOCO (You Only Condense Once) method is proposed, which allows for flexible scaling (trimming) of the synthesized dataset based on different computational resource requirements after a single dataset compression, without the need for an additional compression process.

Zero-One Laws of Graph Neural Networks

Sam Adam-Day (University of Oxford), Ismail Ilkan Ceylan (University of Oxford)

CodeGraph Neural NetworkGraph

🎯 What it does: This study proves that graph neural networks (GNNs) follow the zero-one law on large-scale ErdΕ‘s–RΓ©nyi graphs, revealing the limits of their expressiveness and extrapolation capabilities.

Zero-Shot Anomaly Detection via Batch Normalization

Aodong Li (University of California Irvine), Stephan Mandt (University of California Irvine)

CodeAnomaly DetectionMeta LearningContrastive LearningImageTabular

🎯 What it does: A zero-shot anomaly detection method based on batch normalization and meta-training, ACR, is proposed, which can complete anomaly detection under new distributions without retraining.

Zero-shot causal learning

Hamed Nilforoshan (Stanford University), Jure Leskovec (Stanford University)

CodeMeta LearningDrug DiscoveryTabularBiomedical DataElectronic Health Records

🎯 What it does: A zero-shot causal learning framework, CaML, is proposed, which can predict the causal effects of individuals on new interventions without any historical intervention data.

Zero-shot Visual Relation Detection via Composite Visual Cues from Large Language Models

Lin Li (Zhejiang University), Long Chen (The Hong Kong University of Science and Technology)

CodeRecognitionObject DetectionComputational EfficiencyTransformerLarge Language ModelVision Language ModelImageChain-of-Thought

🎯 What it does: Proposes the RECODE method, which utilizes large language models to generate composite descriptive prompts (subject, object, space) to improve zero-shot visual relationship detection in CLIP;

ZipLM: Inference-Aware Structured Pruning of Language Models

Eldar Kurtic (IST Austria), Dan Alistarh (Neural Magic)

CodeCompressionComputational EfficiencyKnowledge DistillationTransformerLarge Language ModelSupervised Fine-TuningText

🎯 What it does: This paper proposes ZipLMβ€”a reasoning-aware structured pruning method that can batch-generate various compressed BERT/GPT models under given reasoning environments and speed-up targets.

ZoomTrack: Target-aware Non-uniform Resizing for Efficient Visual Tracking

Yutong Kou (Chinese Academy of Sciences), Liang Li (Beijing Institute of Basic Medical Sciences)

CodeObject TrackingOptimizationComputational EfficiencyTransformerVideo

🎯 What it does: This paper proposes a visual tracking method called ZoomTrack based on non-uniform scaling, which enhances tracking accuracy while maintaining a small input size and high speed.