arXivSub Start free trial

NeurIPS 2025 Papers with Code β€” Page 6

Conference on Neural Information Processing Systems Β· 2283 papers

DISCO: Disentangled Communication Steering for Large Language Models

Max Torop (Northeastern University), Jennifer Dy (Northeastern University)

CodeTransformerLarge Language ModelText

🎯 What it does: This paper proposes a new vector injection methodβ€”DISCO Steering, which directly injects the average difference vector into the query and value representation space of the Transformer attention heads to regulate the output of large language models. It also provides theoretical analysis, linear separability assessment, and various benchmark comparison experiments.

DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization

Gang Li (Texas A&M University), Tianbao Yang (Texas A&M University)

CodeOptimizationReinforcement LearningText

🎯 What it does: A reinforcement learning framework called DisCO based on discriminative constraint optimization is proposed to enhance the mathematical reasoning performance of large-scale inference models.

DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning

Leander Diaz-Bone (ETH Zurich), Andreas Krause (ETH Zurich)

CodeReinforcement Learning

🎯 What it does: This paper proposes an automatic course learning method based on goal selection called DISCOVER, aimed at addressing the sparse reward long-term reinforcement learning problem.

Discovering Data Structures: Nearest Neighbor Search and Beyond

Omar Salemohamed (University of Montreal), Gregory Valiant (Stanford University)

CodeTransformerImageTabular

🎯 What it does: This paper proposes an end-to-end learning framework that allows neural networks to learn to construct and query data structures from scratch, focusing on nearest neighbor search and extending it to problems like frequency estimation.

Discovering Opinion Intervals from Conflicts in Signed Graphs

Peter Blohm (Aalto University), Stefan Neumann (TU Wien)

CodeGraph Neural NetworkGraph

🎯 What it does: The BEST INTERVAL APPROXIMATION problem is proposed, aiming to assign overlapping opinion intervals to nodes in a signed graph to explain the conflicts and cooperation of positive and negative edges.

Discovering Symbolic Partial Differential Equation by Abductive Learning

En-Hao Gao (Nanjing University), Zhi-Hua Zhou (Nanjing University)

CodeTabularPhysics Related

🎯 What it does: Based on the abductive learning framework and FOL knowledge base, the ABL-PDE method is proposed to discover symbolic partial differential equations from data and estimate their coefficients.

Discrete Spatial Diffusion: Intensity-Preserving Diffusion Modeling

Javier E. Santos (Los Alamos National Laboratory), Yen Ting Lin (Los Alamos National Laboratory)

CodeRestorationGenerationData SynthesisDiffusion modelImage

🎯 What it does: A Discrete Spatial Diffusion (DSD) model is proposed, achieving a complete diffusion generation process in discrete pixel and particle counting space while strictly maintaining the total particle count, supporting conditional generation and image inpainting.

Disentangled Concepts Speak Louder Than Words: Explainable Video Action Recognition

Jongseo Lee (Kyung Hee University), Jinwoo Choi (Kyung Hee University)

CodeRecognitionExplainability and InterpretabilityTransformerLarge Language ModelVideo

🎯 What it does: This paper proposes a concept-based explainable video action recognition framework called DANCE, which generates structured explanations by breaking down action predictions into three types of interpretable concepts: motion dynamics, objects, and scenes.

Disentangled Representation Learning via Modular Compositional Bias

Whie Jung (Korea Advanced Institute of Science and Technology), Seunghoon Hong (Korea Advanced Institute of Science and Technology)

CodeGenerationRepresentation LearningDiffusion modelAuto EncoderImage

🎯 What it does: A general framework is proposed that can achieve attribute, object, and their joint disentanglement by adjusting the mixing strategy;

Disentangling Hyperedges through the Lens of Category Theory

Yoonho Lee (Korea Advanced Institute of Science and Technology), Chanyoung Park (Korea Advanced Institute of Science and Technology)

CodeClassificationGraph Neural NetworkGraphBiomedical Data

🎯 What it does: This paper decouples hyperedges in hypergraph structures, proposes a naturality condition criterion based on category theory, constructs the Natural-HNN model, and verifies its effectiveness in classifying cancer subtypes based on gene pathways.

Disentangling Latent Shifts of In-Context Learning with Weak Supervision

Josip Jukić (University of Zagreb), Jan Šnajder (University of Zagreb)

CodeTransformerLarge Language ModelPrompt EngineeringText

🎯 What it does: This paper proposes a method that views in-context learning (ICL) as weak supervision, encoding implicit shifts generated by demonstrations into lightweight adapters through a teacher-student framework, enabling promptless query reasoning and supporting large-scale demonstration combinations.

Disentangling misreporting from genuine adaptation in strategic settings: a causal approach

Dylan Zapzalka (University of Michigan), Maggie Makar (University of Michigan)

CodeTabularFinance Related

🎯 What it does: This paper proposes a method based on causal inference to distinguish between agents' misreporting (upcoding) and true adaptation in strategic decision-making scenarios, and to identify and estimate the misreporting rate when only misreported features are observed.

DIsoN: Decentralized Isolation Networks for Out-of-Distribution Detection in Medical Imaging

Felix Wagner (University of Oxford), Konstantinos Kamnitsas (University of Oxford)

CodeAnomaly DetectionFederated LearningConvolutional Neural NetworkImageBiomedical DataUltrasound

🎯 What it does: A decentralized isolation network (DIsoN) and its class-conditional variant CC-DIsoN are proposed for detecting outlier samples in medical images through model parameter exchange without sharing training data.

Distance-informed Neural Processes

Aishwarya Venkataramanan (Friedrich Schiller University Jena), Joachim Denzler (Friedrich Schiller University Jena)

CodeClassificationAnomaly DetectionTabularTime Series

🎯 What it does: This paper proposes a Distance-Aware Neural Process (DNP) that improves uncertainty estimation and generalization by incorporating a double Lipschitz constraint into both global and local latent variables.

Distil-E2D: Distilling Image-to-Depth Priors for Event-Based Monocular Depth Estimation

Jie Long Lee (National University of Singapore), Gim Hee Lee (National University of Singapore)

CodeDepth EstimationAutonomous DrivingKnowledge DistillationTransformerImageMultimodality

🎯 What it does: A framework named Distil-E2D has been developed, which distills dense depth prior knowledge from image-based foundational depth models into the event domain. It achieves monocular depth estimation on event cameras by utilizing synthetic pseudo-labels, confidence-guided calibration loss, context transformers, and dual-decoder training.

Distilling LLM Agent into Small Models with Retrieval and Code Tools

Minki Kang (KAIST), Sung Ju Hwang (KAIST)

CodeRetrievalKnowledge DistillationTransformerLarge Language ModelTextRetrieval-Augmented GenerationChain-of-Thought

🎯 What it does: A framework called Agent Distillation is proposed by transferring the interactive reasoning and tool usage behavior of large language models to smaller models;

Distilling LLM Prior to Flow Model for Generalizable Agent’s Imagination in Object Goal Navigation

Badi Li (The University of Hong Kong), Wei-Shi Zheng (Sun Yat-sen University)

CodeKnowledge DistillationRobotic IntelligenceTransformerLarge Language ModelPrompt EngineeringFlow-based ModelPoint Cloud

🎯 What it does: A flow matching-based generative model called GOAL is proposed to perform semantic reasoning in unobserved areas for object goal navigation (ObjectNav), assisting agents in planning paths.

Distributed Multi-Agent Bandits Over ErdΕ‘s-RΓ©nyi Random Networks

Jingyuan Liu (Nanjing University), Mengfan Xu (University of Massachusetts Amherst)

CodeRecommendation SystemOptimizationFederated LearningGraph Neural NetworkReinforcement LearningTabular

🎯 What it does: This paper studies the multi-agent multi-armed bandit (MA-MAB) problem under a random ErdΕ‘s–RΓ©nyi communication network generated by a fixed base graph, and proposes a successful elimination (GSE) algorithm combined with gossip communication.

Ditch the Denoiser: Emergence of Noise Robustness in Self-Supervised Learning from Data Curriculum

Wenquan Lu (Brown University), Randall Balestriero (Brown University)

CodeRetrievalRepresentation LearningContrastive LearningImage

🎯 What it does: A completely self-supervised framework is proposed, capable of learning noise-robust visual representations without using a denoiser during the inference phase.

Diverse Influence Component Analysis: A Geometric Approach to Nonlinear Mixture Identifiability

Hoang-Son Nguyen (Oregon State University), Xiao Fu (Oregon State University)

CodeOptimizationRepresentation LearningAuto EncoderTabularBiomedical Data

🎯 What it does: By utilizing the convex geometric properties of the Jacobian matrix in nonlinear mixture models, the J-VolMax criterion is proposed to implement the DICA method, thereby achieving identifiable learning of latent variables.

Diversity as a Reward: Fine-Tuning LLMs on a Mixture of Domain-Undetermined Data

Zhenqing Ling (Sun Yat-sen University), Ying Shen (Alibaba Group)

CodeTransformerLarge Language ModelSupervised Fine-TuningText

🎯 What it does: This paper proposes a self-supervised data selection framework DAAR based on diversity rewards, which can perform high-quality fine-tuning of large language models in the absence of domain labels.

Diversity-Aware Policy Optimization for Large Language Model Reasoning

Jian Yao (Hong Kong Polytechnic University), KC Tan

CodeOptimizationTransformerLarge Language ModelReinforcement LearningText

🎯 What it does: This paper studies the role of diversity in the reinforcement learning (RL) training process for large language model (LLM) inference tasks and proposes a diversity-aware strategy optimization method that applies token-level diversity regularization on positive samples.

DKDR: Dynamic Knowledge Distillation for Reliability in Federated Learning

Yueyang Yuan (Wuhan University), Mang Ye (Wuhan University)

CodeFederated LearningKnowledge DistillationImage

🎯 What it does: This paper proposes the DKDR framework to address the reliability issues of knowledge distillation caused by heterogeneous multi-domain data in federated learning.

dKV-Cache: The Cache for Diffusion Language Models

Xinyin Ma (National University of Singapore), Xinchao Wang (National University of Singapore)

CodeOptimizationComputational EfficiencyTransformerLarge Language ModelDiffusion modelText

🎯 What it does: A KV-Cache mechanism for diffusion language models (DLM), called dKV-Cache, is proposed to accelerate inference.

DLoFT: Gradient-Decoupled Fine-Tuning for Generalizable Long Chain-of-Thought Reasoning

Sitong Wu (Chinese University of Hong Kong), Jiaya Jia (Chinese University of Hong Kong)

CodeTransformerLarge Language ModelSupervised Fine-TuningReinforcement LearningTextChain-of-Thought

🎯 What it does: This paper proposes a gradient decoupling fine-tuning method called DLoFT, which allows large language models to learn only the general LongChain-of-Thought reasoning paradigm during training, avoiding overfitting to problem-specific content.

DMol: A Highly Efficient and Chemical Motif-Preserving Molecule Generation Platform

Peizhi Niu (University of Illinois Urbana-Champaign), Olgica Milenkovic (University of Illinois Urbana-Champaign)

CodeGenerationDrug DiscoveryGraph Neural NetworkDiffusion modelGraph

🎯 What it does: A novel graph diffusion model DMol is proposed for efficiently generating drug molecules that retain key molecular substructures.

DMWM: Dual-Mind World Model with Long-Term Imagination

Lingyi Wang (Virginia Tech), Naren Ramakrishnan (Virginia Tech)

CodeRobotic IntelligenceReinforcement Learning from Human FeedbackRecurrent Neural NetworkReinforcement LearningWorld ModelSequential

🎯 What it does: A dual-process-based world model (DMWM) is proposed, which combines the fast intuitive RSSM (System 1) with a logical reasoning neural network (System 2) and achieves long-term, logically consistent imagination and planning through bidirectional feedback.

DNA-DetectLLM: Unveiling AI-Generated Text via a DNA-Inspired Mutation-Repair Paradigm

Xiaowei Zhu (Institute of Information Engineering Chinese Academy of Sciences), Yanan Cao (Institute of Information Engineering Chinese Academy of Sciences)

CodeClassificationAnomaly DetectionTransformerLarge Language ModelText

🎯 What it does: A zero-shot AI-generated text detection method based on the DNA mutation-repair paradigm, DNA-DetectLLM, is proposed, which utilizes an ideal AI sequence for stepwise repair and quantifies the difficulty of repair as a detection signal.

Do Language Models Use Their Depth Efficiently?

RΓ³bert CsordΓ‘s (Stanford University), Christopher Potts (Stanford University)

CodeTransformerLarge Language ModelText

🎯 What it does: This paper explores whether the depth of large pre-trained language models is effectively utilized through causal interventions, cosine similarity, Logitlens, integrated gradients, and other analyses of residual flow, inter-layer interactions, and layer contributions.

Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awareness

Rongzhe Wei (Georgia Institute of Technology), Pan Li (Georgia Institute of Technology)

CodeTransformerLarge Language ModelReinforcement LearningGraph

🎯 What it does: A machine learning model (LLM) forgetfulness evaluation framework based on knowledge graphs and confidence is proposed, and reasoning evaluation is conducted through a powerful LLM discriminator.

Do-PFN: In-Context Learning for Causal Effect Estimation

Jake Robertson (Prior Labs), Bernhard SchΓΆlkopf (Max Planck Institute for Intelligent Systems)

CodeMeta LearningTransformerTabular

🎯 What it does: This paper proposes Do-PFN, a pre-trained transformer that predicts causal effects from observational data through context learning.

Doctor Approved: Generating Medically Accurate Skin Disease Images through AI-Expert Feedback

Janet Wang (Tulane University), Jihun Hamm (Tulane University)

CodeGenerationData SynthesisLarge Language ModelReinforcement LearningDiffusion modelImage

🎯 What it does: This paper proposes a framework called MAGIC based on AI-expert collaboration, which utilizes large language models to evaluate medical checklists to guide diffusion models in generating skin disease images with high clinical accuracy, and uses these synthetic images for data augmentation.

DoDo-Code: an Efficient Levenshtein Distance Embedding-based Code for 4-ary IDS Channel

Alan J.X. Guo (Tianjin University), Xin Chen (Tianjin University)

CodeConvolutional Neural NetworkSequential

🎯 What it does: A high-rate single IDS error-correcting 4-ary code called DoDo-Code is designed.

Does Object Binding Naturally Emerge in Large Pretrained Vision Transformers?

Yihao Li (University of Pennsylvania), Konrad Kording

CodeSegmentationRepresentation LearningTransformerContrastive LearningImage

🎯 What it does: This study investigates whether object binding capabilities naturally emerge in large pre-trained Vision Transformers (ViT), defines the 'IsSameObject' metric, and validates its decodability through linear/quadratic detectors; further analyzes the low-dimensional subspace of binding information in the feature space and examines its impact on attention allocation and downstream segmentation tasks.

Domain-RAG: Retrieval-Guided Compositional Image Generation for Cross-Domain Few-Shot Object Detection

Yu Li (Fudan University), Yu-Gang Jiang (Fudan University)

CodeObject DetectionGenerationData SynthesisDiffusion modelImageRetrieval-Augmented Generation

🎯 What it does: A training-free, retrieval-guided combined image generation framework called Domain-RAG is proposed to generate synthetic images that conform to domain distribution while preserving the original foreground in cross-domain few-shot object detection.

Domain-Specific Pruning of Large Mixture-of-Experts Models with Few-shot Demonstrations

zican Dong, Zhifeng Wang (EBTech Co. Ltd)

CodeCompressionDomain AdaptationComputational EfficiencyMixture of ExpertsTabular

🎯 What it does: This paper proposes a domain-specific pruning method called EASY-EP, which performs high compression rate expert pruning on large mixture of experts (MoE) models, addressing the memory bottleneck issue of large-scale MoE models.

Don't be lazy: CompleteP enables compute-efficient deep transformers

Nolan Simran Dey (Cerebras Systems), Joel Hestness (Cerebras Systems)

CodeOptimizationComputational EfficiencyTransformerLarge Language ModelText

🎯 What it does: The study investigates the parameterization strategy when simultaneously expanding depth and width in Transformers, proposing and validating that CompleteP (α=1) can achieve deep transferability of hyperparameters (learning rate, initialization standard deviation, etc.).

Don't Just Chase β€œHighlighted Tokens” in MLLMs: Revisiting Visual Holistic Context Retention

Xin Zou (Hong Kong University of Science and Technology), Xuming Hu (Shanghai Jiao Tong University)

CodeRecognitionOptimizationComputational EfficiencyTransformerLarge Language ModelVision Language ModelImageMultimodality

🎯 What it does: Developed HoloV, a global context-preserving visual token cropping framework for multimodal large language models.

DON’T NEED RETRAINING: A Mixture of DETR and Vision Foundation Models for Cross-Domain Few-Shot Object Detection

Chang-Han Liu, Yang Gao (Nanjing University)

CodeObject DetectionDomain AdaptationTransformerMixture of ExpertsImage

🎯 What it does: A cross-domain few-shot object detection method based on the Mixture-of-Experts (MoE) architecture is proposed, which integrates visual foundation models (VFM) as expert features into the pre-trained DETR detector, achieving cross-domain inference without re-training on base classes.

Doodle to Detect: A Goofy but Powerful Approach to Skeleton-based Hand Gesture Recognition

Sang Hoon Han (Sogang University), Sung In Cho (Sogang University)

CodeRecognitionPose EstimationTransformerImageVideo

🎯 What it does: Proposes the SKETCH framework, which transforms the original four-dimensional skeleton sequences into images and uses a visual Transformer for online gesture recognition.

DOTA: Distributional Test-time Adaptation of Vision-Language Models

Zongbo Han (Beijing University of Posts and Telecommunications), Changqing Zhang (Tianjin University)

CodeClassificationDomain AdaptationTransformerVision Language ModelImageBiomedical DataMagnetic Resonance Imaging

🎯 What it does: A distributed testing adaptive method named Dota is proposed, which achieves dynamic adaptation of visual-language models by continuously estimating the Gaussian distribution of test data and using Bayesian inference without performing gradient backpropagation.

Doubly Robust Alignment for Large Language Models

Erhan Xu (London School of Economics), Chengchun Shi (London School of Economics)

CodeOptimizationReinforcement Learning from Human FeedbackTransformerLarge Language ModelReinforcement LearningText

🎯 What it does: This paper proposes a double-robust preference optimization method (DRPO) for fine-tuning large language models within the RLHF framework, achieving a more robust alignment with human preferences.

DOVE: Efficient One-Step Diffusion Model for Real-World Video Super-Resolution

Zheng Chen (Shanghai Jiao Tong University), Yulun Zhang (Shanghai Jiao Tong University)

CodeRestorationSuper ResolutionTransformerDiffusion modelVideo

🎯 What it does: DOVE is proposed, a single-step diffusion model for real-world video super-resolution;

DOVTrack: Data-Efficient Open-Vocabulary Tracking

Zekun Qian (Tianjin University), Wei Feng (Tianjin University)

CodeObject DetectionObject TrackingConvolutional Neural NetworkDiffusion modelContrastive LearningVideo

🎯 What it does: A data-efficient open vocabulary multi-object tracking method is proposed on sparsely annotated video data, utilizing diffusion feature generation, dynamic group contrastive learning, and adaptive localization loss, significantly improving association, classification, and localization performance.

DP-LLM: Runtime Model Adaptation with Dynamic Layer-wise Precision Assignment

Sangwoo Kwon (Seoul National University), Yeonhong Park (Seoul National University)

CodeTransformerLarge Language ModelText

🎯 What it does: Proposes DP-LLM, a mechanism that dynamically allocates quantization precision layer by layer on the device according to runtime requirements;

DPΒ²O-SR: Direct Perceptual Preference Optimization for Real-World Image Super-Resolution

Rongyuan Wu (Hong Kong Polytechnic University), Lei Zhang (Hong Kong Polytechnic University)

CodeSuper ResolutionOptimizationDiffusion modelImage

🎯 What it does: Utilizing the randomness of pre-trained text-to-image diffusion models, we directly optimize the perceptual quality of real-world image super-resolution models by constructing perceptual rewards and preference comparisons.

DPA: A one-stop metric to measure bias amplification in classification datasets

Bhanu Tokas (Arizona State University), Hannah Kerner (Arizona State University)

CodeClassificationConvolutional Neural NetworkImageMultimodalityTabular

🎯 What it does: Proposes and implements Directional Predictability Amplification (DPA), a metric that quantifies the amplification of bias in classification datasets and distinguishes between positive and negative amplification directions.

DreamPRM: Domain-reweighted Process Reward Model for Multimodal Reasoning

Qi Cao (University of California San Diego), Pengtao Xie (University of California San Diego)

CodeOptimizationData-Centric LearningReinforcement LearningMultimodalityChain-of-Thought

🎯 What it does: This paper proposes DreamPRM, a dual-layer optimization-based multimodal process reward model training framework that can adaptively reweight different multimodal reasoning datasets to enhance the model's generalization ability.

DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents

Hao Li (Washington University in St. Louis), Chaowei Xiao (Johns Hopkins University)

CodeSafty and PrivacyAdversarial AttackTransformerLarge Language ModelPrompt EngineeringText

🎯 What it does: A dynamic rule isolation framework called DRIFT is proposed to defend against prompt injection attacks in LLM agent systems.

DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving

Hao LU, Ying-Cong Chen

CodeAutonomous DrivingGaussian SplattingOptical FlowImagePoint Cloud

🎯 What it does: A driving scene reconstruction model called DrivingRecon based on a 4D Gaussian distribution is proposed, which can quickly generate high-quality dynamic four-dimensional scenes in a single forward inference.

DSAS: A Universal Plug-and-Play Framework for Attention Optimization in Multi-Document Question Answering

Jiakai Li (University of Electronic Science and Technology of China), Ke Qin (University of Electronic Science and Technology of China)

CodeOptimizationTransformerLarge Language ModelText

🎯 What it does: This paper proposes Dual-Stage Adaptive Sharpening (DSAS), a training-free plugin that optimizes the attention of Transformers in multi-document question answering tasks, addressing long-distance dependencies and the 'intermediate defocus' problem.

DSRF: A Dynamic and Scalable Reasoning Framework for Solving RPMs

Chengtai Li (University of Nottingham Ningbo China), Xudong Jiang (Nanyang Technological University)

CodeImageVideo

🎯 What it does: A dynamic scalable reasoning framework (DSRF) is proposed to address the issues of rule scalability and adaptability in abstract visual reasoning tasks.

Dual Alignment Framework for Few-shot Learning with Inter-Set and Intra-Set Shifts

Siyang Jiang (Chinese University of Hong Kong), Ming-syan Chen

CodeClassificationMeta LearningGenerative Adversarial NetworkImage

🎯 What it does: To address the distribution shift issues between the support set and the query set, as well as within each of them in few-shot learning, this paper proposes the Dual Support-Query Shift challenge and presents the DUAL framework for robust feature extraction and dual regularization optimal transport alignment.

Dual Data Alignment Makes AI-Generated Image Detector Easier Generalizable

Ruoxin Chen (Tencent YouTu Lab), Shouhong Ding (Tencent YouTu Lab)

CodeObject DetectionData-Centric LearningAuto EncoderImageBenchmark

🎯 What it does: This study investigates a dual domain data alignment method (Dual Data Alignment, DDA) for detecting AI-generated images, synchronously aligning real images and synthetic images at both the pixel and frequency levels to reduce bias and enhance detection generalization capabilities.

Dual Prototype-Enhanced Contrastive Framework for Class-Imbalanced Graph Domain Adaptation

Xin Ma (Sichuan University), Jiancheng Lv

CodeDomain AdaptationGraph Neural NetworkContrastive LearningGraph

🎯 What it does: A dual-prototype enhanced contrastive framework (ImGDA) is proposed for unsupervised graph domain adaptation under severe label imbalance in the source domain.

Dual-Flow: Transferable Multi-Target, Instance-Agnostic Attacks via $\textit{In-the-wild}$ Cascading Flow Optimization

Yixiao Chen (Tsinghua University), Junliang Xing (Tsinghua University)

CodeAdversarial AttackDiffusion modelImageStochastic Differential EquationOrdinary Differential Equation

🎯 What it does: Proposes a Dual-Flow framework that generates initial perturbations using a pre-trained diffusion ODE flow and fine-tunes the reverse velocity function through LoRA, forming a multi-target instance-independent adversarial attack;

Dual-Stage Value-Guided Inference with Margin-Based Reward Adjustment for Fast and Faithful VLM Captioning

Ankan Deria (Mohamed bin Zayed University of AI), Imran Razzak

CodeGenerationComputational EfficiencyTransformerReinforcement LearningVision Language ModelImageText

🎯 What it does: A two-stage value-guided reasoning framework, ViMaR, is proposed, significantly enhancing the credibility and detail of image descriptions generated by VLM.

DUAL: Learning Diverse Kernels for Aggregated Two-sample and Independence Testing

Zhijian Zhou (University of Melbourne), Feng Liu (University of Melbourne)

CodeOptimizationImage

🎯 What it does: A method named DUAL is proposed, which improves kernel-based two-sample and independence tests using multi-kernel learning and diversity metrics, significantly enhancing test power while maintaining control over Type I error.

DualEqui: A Dual-Space Hierarchical Equivariant Network for Large Biomolecules

Junjie Xu (Pennsylvania State University), Suhang Wang (Pennsylvania State University)

CodeProtein Structure PredictionGraph Neural NetworkBiomedical DataBenchmark

🎯 What it does: This paper proposes DualEquiNet, a dual-space hierarchical equivariant network for the property prediction of large-scale biomolecules (RNA, proteins) in three-dimensional structures.

DualMPNN: Harnessing Structural Alignments for High-Recovery Inverse Protein Folding

Xuhui Liao (Harbin Institute of Technology), Junjie Chen (Harbin Institute of Technology)

CodeProtein Structure PredictionGraph Neural NetworkGraph

🎯 What it does: A dual-stream information transmission neural network, DualMPNN, is designed to guide protein reverse folding using structural alignment templates.

DualOptim: Enhancing Efficacy and Stability in Machine Unlearning with Dual Optimizers

Xuyang Zhong (City University of Hong Kong), Chen Liu (City University of Hong Kong)

CodeGenerationOptimizationLarge Language ModelSupervised Fine-TuningDiffusion modelImageText

🎯 What it does: A Dual Optimizer (DualOptim) is proposed and validated, which uses an adaptive learning rate optimizer (such as Adam) for the forgetting target and the original optimizer (such as SGD) for the retaining target, decoupling momentum between the two to enhance the effectiveness and stability of machine unlearning (MU).

DUET: Dual-Perspective Pseudo Labeling and Uncertainty-aware Exploration & Exploitation Training for Source-Free Domain Adaptation

Jae Yun Lee (Sogang University), Sung In Cho (Sogang University)

CodeDomain AdaptationKnowledge DistillationRepresentation LearningContrastive LearningImage

🎯 What it does: In the source-free domain adaptation (SFDA) task, a dual-view pseudo-label generation and uncertainty-aware visual optimization framework is proposed, utilizing the collaborative predictions of the target model and CLIP to produce more reliable pseudo-labels, while dynamically balancing exploration and exploitation during training.

DuetGraph: Coarse-to-Fine Knowledge Graph Reasoning with Dual-Pathway Global-Local Fusion

Jin Li (University of Science and Technology of China), Xike Xie (University of Science and Technology of China)

CodeGraph Neural NetworkGraph

🎯 What it does: This paper proposes DuetGraph, which constructs a dual-channel global-local fusion and coarse-fine decomposition reasoning framework to alleviate the over-smoothing problem in knowledge graph reasoning.

DyFlow: Dynamic Workflow Framework for Agentic Reasoning

Yanbo Wang (Mohamed bin Zayed University of Artificial Intelligence), Xiuying Chen (Mohamed bin Zayed University of Artificial Intelligence)

CodeLarge Language ModelSupervised Fine-TuningAgentic AITextBiomedical Data

🎯 What it does: We propose DyFlow, a dynamic workflow framework that utilizes LLM designers and executors to adaptively generate and adjust reasoning sub-goals based on real-time feedback during execution.

DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs

Dongyuan Li (University of Tokyo), Renhe Jiang (University of Tokyo)

CodeRecommendation SystemRecurrent Neural NetworkGraph Neural NetworkGraphTime SeriesSequentialStochastic Differential Equation

🎯 What it does: A dynamic graph modeling framework DyG-Mamba based on continuous state space models is proposed, which can capture long-term temporal dependencies and enhance robustness.

DyMoDreamer: World Modeling with Dynamic Modulation

Boxuan Zhang (Beijing Institute of Technology), Gang Wang (Beijing Institute of Technology)

CodeReinforcement LearningWorld ModelVideo

🎯 What it does: A new world model-based reinforcement learning algorithm DyMoDreamer has been developed, which enhances the extraction of dynamic features and temporal information through a dynamic modulation mechanism, achieving higher sample efficiency.

Dyn-O: Building Structured World Models with Object-Centric Representations

Zizhao Wang (University of Texas at Austin), Jiang Bian (Microsoft Research Asia)

CodeRepresentation LearningReinforcement LearningContrastive LearningWorld ModelImageVideo

🎯 What it does: Developed Dyn-O, a world model based on object-centered representation, which learns object-level features and models dynamics in this space while achieving static-dynamic feature decoupling.

DynaAct: Large Language Model Reasoning with Dynamic Action Spaces

Xueliang Zhao (University of Hong Kong), Lingpeng Kong (University of Hong Kong)

CodeOptimizationTransformerLarge Language ModelReinforcement LearningAgentic AITextBenchmark

🎯 What it does: Dynamically constructing a compressed action space through submodular functions enhances the performance of large language models in complex problem reasoning processes.

Dynam3D: Dynamic Layered 3D Tokens Empower VLM for Vision-and-Language Navigation

Zihan Wang (National University of Singapore), Gim Hee Lee (National University of Singapore)

CodeRobotic IntelligenceTransformerVision Language ModelContrastive LearningSimultaneous Localization and MappingMultimodalityPoint Cloud

🎯 What it does: A dynamic hierarchical 3D representation framework, Dynam3D, has been developed for monocular vision-language navigation, combining a 3D patch-instance-zone vision-language model to achieve real-time environmental perception and navigation action prediction.

Dynamic Bundling with Large Language Models for Zero-Shot Inference on Text-Attributed Graphs

Yusheng Zhao (Peking University), Ming Zhang (University of Illinois Chicago)

CodeClassificationGraph Neural NetworkLarge Language ModelTextGraph

🎯 What it does: The DENSE method is proposed, which packages the texts of nearby nodes into bundles and queries a large language model (LLM) to obtain bundle-level labels. These labels are then used as supervisory signals to train a graph neural network (GNN) for zero-shot node classification.

Dynamic Configuration for Cutting Plane Separators via Reinforcement Learning on Incremental Graph

Mingxuan Ye (University of Science and Technology of China), Feng Wu (University of Science and Technology of China)

CodeOptimizationGraph Neural NetworkTransformerReinforcement LearningGraph

🎯 What it does: A method called DynSep is proposed, which uses reinforcement learning to dynamically decide when to stop pruning plane separators and which separators should be activated on incremental graphs, in order to improve the solving efficiency of Mixed Integer Linear Programming (MILP).

Dynamic Diffusion SchrΓΆdinger Bridge in Astrophysical Observational Inversions

Ye Zhu (Γ‰cole Polytechnique), Olga Russakovsky (Princeton University)

CodeGenerationData SynthesisComputational EfficiencyDiffusion modelScore-based ModelTime SeriesPhysics Related

🎯 What it does: The study utilizes a dynamic Schrâdinger bridge model for observational inverse prediction of star-forming giant molecular clouds, proposing the Astro-DSB framework.

Dynamic Gaussian Splatting from Defocused and Motion-blurred Monocular Videos

Xuankai Zhang (Sun Yat-sen University), Qing Zhang (Sun Yat-sen University)

CodeRestorationData SynthesisConvolutional Neural NetworkGaussian SplattingVideo

🎯 What it does: A unified framework is proposed to synthesize high-quality new views from monocular videos containing defocus and motion blur using dynamic Gaussian scattering technology.

Dynamic Semantic-Aware Correlation Modeling for UAV Tracking

Xinyu Zhou (Fudan University), Wenqiang Zhang (Fudan University)

CodeObject TrackingTransformerVideo

🎯 What it does: A dynamic semantic-aware association modeling framework for drone tracking, DSATrack, is proposed to enhance the semantic matching and localization accuracy between the template and the search area.

Dynamic Siamese Expansion Framework for Improving Robustness in Online Continual Learning

Fei Ye (University of Electronic Science and Technology of China), shijie zhou

CodeClassificationAdversarial AttackTransformerContrastive LearningImage

🎯 What it does: This paper proposes the Dynamic Siamese Expansion Framework (DSEF), which dynamically generates lightweight experts through a static + dynamic Siamese backbone network in online continual learning, while maintaining the robustness of historical knowledge when learning new tasks.

Dynamical Low-Rank Compression of Neural Networks with Robustness under Adversarial Attacks

Steffen SchotthΓΆfer (Oak Ridge National Laboratory), Stefan Schnake (Oak Ridge National Laboratory)

CodeCompressionOptimizationAdversarial AttackConvolutional Neural NetworkSupervised Fine-TuningImage

🎯 What it does: A robust low-rank compression method based on dynamic low-rank training and spectral regularization is proposed, which can achieve up to 94% parameter compression while maintaining or improving adversarial robustness.

Dynamics of Spontaneous Topic Changes in Next Token Prediction with Self-Attention

Mumin Jia (York University), Jairo Diaz-Rodriguez (York University)

CodeTransformerLarge Language ModelTextRetrieval-Augmented Generation

🎯 What it does: This study investigates the spontaneous topic change mechanism of self-attention models in next-word prediction and validates it through single-layer self-attention theory and modern LLM experiments.

Dynamics-Aligned Latent Imagination in Contextual World Models for Zero-Shot Generalization

Frank RΓΆder (Institute for Data Science Foundations), Pradeep Kr. Banerjee (Institute for Data Science Foundations)

CodeRobotic IntelligenceRecurrent Neural NetworkTransformerReinforcement LearningWorld ModelSequential

🎯 What it does: In the DreamerV3 framework, a self-supervised context encoder is added, which can infer implicit environmental context from the agent-environment interaction history, thus achieving zero-shot generalization.

DynaPipe: Dynamic Layer Redistribution for Efficient Serving of LLMs with Pipeline Parallelism

HongXin Xu, Xianwei Zhang (Sun Yat-Sen University)

CodeOptimizationComputational EfficiencyTransformerLarge Language ModelText

🎯 What it does: A technique for dynamically reallocating pipeline layers during LLM inference is proposed to address the issue of pipeline idleness caused by tail sampling;

E-BATS: Efficient Backpropagation-Free Test-Time Adaptation for Speech Foundation Models

Jiaheng Dong (University of Melbourne), Ting Dang (University of Melbourne)

CodeDomain AdaptationOptimizationComputational EfficiencyConvolutional Neural NetworkPrompt EngineeringAudio

🎯 What it does: This paper proposes E-BATS, a gradient-free adaptive method for speech foundation models that can adapt in real-time to changes in different acoustic domains without using source data or labels.

E2Former: An Efficient and Equivariant Transformer with Linear-Scaling Tensor Products

Yunyang Li (Yale University), Jia Zhang (Ubiquant)

CodeComputational EfficiencyDrug DiscoveryProtein Structure PredictionTransformerGraphBiomedical Data

🎯 What it does: The E2Former architecture is proposed, utilizing Wigner 6j convolutions to transfer edge-level tensor multiplication to node-level, achieving an efficient SO(3) equivariant Transformer for molecular modeling.

EA3D: Online Open-World 3D Object Extraction from Streaming Videos

Xiaoyu Zhou (Peking University), Ming-Hsuan Yang (Google DeepMind)

CodeObject DetectionSegmentationVision Language ModelGaussian SplattingSimultaneous Localization and MappingVideo

🎯 What it does: An online, open-world 3D object extraction framework EA3D is proposed, capable of real-time 3D reconstruction and semantic understanding without prior geometric or pose information.

Each Complexity Deserves a Pruning Policy

Hanshi Wang (Chinese Academy of Sciences), Zhipeng Zhang

CodeAutonomous DrivingComputational EfficiencyTransformerVision Language ModelMultimodality

🎯 What it does: This paper proposes an adaptive pruning framework for untrained visual-language models, AutoPrune, which generates personalized token retention strategies for each input while adhering to a fixed computational budget.

EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test

Yuhui Li (Peking University), Hongyang Zhang (University of Waterloo)

CodeOptimizationComputational EfficiencyTransformerLarge Language ModelText

🎯 What it does: Proposes EAGLE-3, a lossless acceleration method that utilizes training-time tests during the inference phase and integrates multi-layer features;

EAReranker: Efficient Embedding Adequacy Assessment for Retrieval Augmented Generation

Dongyang Zeng (Guangzhou University), Binxing Fang (Guangzhou University)

CodeGenerationRetrievalExplainability and InterpretabilityComputational EfficiencyTransformerTextRetrieval-Augmented Generation

🎯 What it does: Proposes EAReranker, a RAG pre-ranking model that evaluates the sufficiency of retrieval results using only embedding vectors.

EasySpec: Layer-Parallel Speculative Decoding for Efficient Multi-GPU Utilization

Yize Wu (Intelligent Software Research Center, Institute of Software, Chinese Academy of Sciences), Yanjun Wu (Intelligent Software Research Center, Institute of Software, Chinese Academy of Sciences)

CodeOptimizationComputational EfficiencyTransformerLarge Language ModelTextBenchmark

🎯 What it does: This paper presents EasySpec, a layer-parallel speculation strategy for the Drafting phase of Speculative Decoding in multi-GPU environments, significantly improving inference throughput.

EDELINE: Enhancing Memory in Diffusion-based World Models via Linear-Time Sequence Modeling

Jia-Hua Lee (National Tsing Hua University), Chun-Yi Lee (National Taiwan University)

CodeGenerationReinforcement LearningDiffusion modelWorld ModelSequential

🎯 What it does: A unified world model architecture EDELINE is proposed, which combines state space models and diffusion models to enhance the memory and generation quality of diffusion-based world models.

Edit Less, Achieve More: Dynamic Sparse Neuron Masking for Lifelong Knowledge Editing in LLMs

Jinzhe Liu (University of Chinese Academy of Sciences), Shuhui Wang (University of Chinese Academy of Sciences)

CodeTransformerLarge Language ModelText

🎯 What it does: Proposed Neuron-Specific Masked Knowledge Editing (NMKE), which achieves lifelong knowledge editing of LLMs through neuron-level attribution and dynamic sparse masking;

EditInfinity: Image Editing with Binary-Quantized Generative Models

Jiahuan Wang (Harbin Institute of Technology), Wenjie Pei (Harbin Institute of Technology)

CodeImage TranslationGenerationPrompt EngineeringDiffusion modelImageBenchmark

🎯 What it does: This paper proposes EditInfinity, which utilizes the binary characteristics of the VQ quantization model Infinity to achieve text-driven high-fidelity image editing.

Effects of Dropout on Performance in Long-range Graph Learning Tasks

Jasraj Singh (Nanyang Technological University), Laura Toni (University College London)

CodeClassificationGraph Neural NetworkGraph

🎯 What it does: This study investigates the impact of dropout-style algorithms such as DropEdge, DropNode, DropAgg, DropGNN, and DropMessage in long-distance graph learning tasks, and proposes a new method called DropSens.

Efficient Adaptive Experimentation with Noncompliance

Miruna Oprescu (Cornell University), Nathan Kallus (Cornell University)

CodeTabular

🎯 What it does: In an adaptive experimental environment where only binary instrumental variables can be randomly assigned and treatment cannot be directly enforced, estimate the Average Treatment Effect (ATE).

Efficient Algorithms for Robust and Partial Semi-Discrete Optimal Transport

Pankaj K Agarwal, Keegan Yao (Duke University)

CodeOptimizationTabular

🎯 What it does: This paper studies the theoretical properties and algorithms of semi-discrete robust and partially optimal transport (α‑OPT and λ‑ROT), showing that their optimal solutions can be represented by constrained Laguerre diagrams.

Efficient Allocation of Working Memory Resource for Utility Maximization in Humans and Recurrent Neural Networks

Qingqing Yang (Ohio State University), Hsin-Hung Li (Ohio State University)

CodeOptimizationReinforcement Learning from Human FeedbackRecurrent Neural NetworkReinforcement LearningSequential

🎯 What it does: This study investigates how humans allocate memory resources in working memory tasks based on learned rewards and natural statistical distributions, and validates the resource allocation mechanism under utility maximization through experiments, theoretical extensions, and recurrent neural network models.

Efficient Fairness-Performance Pareto Front Computation

Mark Kozdoba (Technion Israel Institute of Technology), Shie Mannor (NVIDIA)

CodeOptimizationComputational EfficiencyTabularBiomedical Data

🎯 What it does: A new method is proposed to compute the optimal Pareto front between fairness and performance, which does not require training complex fairness representation models.

Efficient Large Language Model Inference with Neural Block Linearization

Mete Erdogan (Γ‰cole Polytechnique FΓ©dΓ©rale de Lausanne), Volkan Cevher (Γ‰cole Polytechnique FΓ©dΓ©rale de Lausanne)

CodeCompressionComputational EfficiencyTransformerLarge Language ModelText

🎯 What it does: A method called Neural Block Linearization (NBL) is proposed, which compresses large-scale language models by replacing the self-attention layers of Transformers with linear layers derived from linear minimum mean square error (LMMSE), achieving inference acceleration.

Efficient Last-Iterate Convergence in Solving Extensive-Form Games

Linjian Meng (Nanjing University), Yang Gao (Nanjing University)

CodeOptimizationReinforcement Learning from Human FeedbackReinforcement LearningTabular

🎯 What it does: The paper proposes an algorithm called Reward Transformation CFR+ (RTCFR+), which utilizes the parameter-independent RM+ (CFR+) to solve the perturbed regularization game at each iteration and achieves the last iteration convergence of the original game through the reward transformation framework.

Efficient Multi-modal Large Language Models via Progressive Consistency Distillation

Zichen Wen (Shanghai Jiao Tong University), Linfeng Zhang (Shanghai Jiao Tong University)

CodeCompressionComputational EfficiencyKnowledge DistillationTransformerLarge Language ModelVision Language ModelImageMultimodality

🎯 What it does: A training framework for multimodal large model visual token compression is proposed through Enhanced Progressive Consistency Distillation (EPIC), which is compatible with various compression methods without altering the model structure.

Efficient Multimodal Dataset Distillation via Generative Models

Zhenghao Zhao (University of Illinois Chicago), Yan Yan (University of Illinois Chicago)

CodeRetrievalKnowledge DistillationDiffusion modelContrastive LearningImageTextMultimodality

🎯 What it does: The EDGE method is proposed and implemented, utilizing a generative diffusion model for efficient distillation of image-text datasets, generating a small number of high-quality image-text pairs, and further enhancing retrieval performance through post-caption synthesis.

Efficient Policy Optimization in Robust Constrained MDPs with Iteration Complexity Guarantees

Sourav Ganguly (New Jersey Institute of Technology), Adam Wierman (California Institute of Technology)

CodeOptimizationReinforcement LearningTabular

🎯 What it does: A natural policy gradient algorithm for robust constrained Markov decision processes (RCMDP) is proposed, which can satisfy constraints and obtain an approximately optimal policy simultaneously without the need for binary search.

Efficient Preference-Based Reinforcement Learning: Randomized Exploration meets Experimental Design

Andreas Schlaginhaufen (Ecole Polytechnique Federale de Lausanne), Maryam Kamgarpour (Ecole Polytechnique Federale de Lausanne)

CodeOptimizationReinforcement Learning from Human FeedbackReinforcement LearningTabular

🎯 What it does: This paper proposes a series of meta-algorithms based on RLoracle, which learn the reward function from trajectory-level preference feedback in Markov decision processes using random exploration and maximum likelihood estimation. Two versions are provided: one for minimizing online cumulative returns (Algorithm 1) and another for preference-independent exploration and single batch estimation (Algorithm 2), along with an improved version that combines lazy random exploration with optimal design (Algorithm 3).