arXivSub Start free trial

ICLR 2026 Papers with Code β€” Page 12

International Conference on Learning Representations Β· 2207 papers

Long-Document QA with Chain-of-Structured-Thought and Fine-Tuned SLMs

Zhuowen Liang (Hong Kong University of Science and Technology), Nan Tang (Hong Kong University of Science and Technology)

CodeTransformerLarge Language ModelSupervised Fine-TuningReinforcement LearningTextChain-of-Thought

🎯 What it does: Propose a framework that converts long document question answering into structured output, combining structured ideas generated by LLMs with reinforcement learning training on small models.

Long-range Modeling and Processing of Multimodal Event Sequences

Jichu Li (Renmin University of China), Quyu Kong

CodeComputational EfficiencyRepresentation LearningTransformerLarge Language ModelSupervised Fine-TuningVision Language ModelMultimodalityTime Series

🎯 What it does: Propose the MM-TPP framework, integrating visual, textual, temporal, and event type information into multi-modal event sequence modeling, and enhancing long-sequence processing capability through adaptive time similarity compression.

Long-tailed Test-Time Adaptation for Vision-Language Models

Xucong Wang (University Of Science And Technology Of China), Yang Wang (Suzhou Institute For Advanced Research)

CodeDomain AdaptationVision Language ModelMultimodality

🎯 What it does: This paper proposes L-TTA, a test-time adaptation (TTA) framework for vision-language models (VLMs) on long-tail test sets, achieving dynamic performance improvement of models on unlabeled, sequentially arriving data streams.

LongLive: Real-time Interactive Long Video Generation

Shuai Yang (NVIDIA), Yukang Chen (NVIDIA)

CodeGenerationComputational EfficiencyTransformerPrompt EngineeringVideo

🎯 What it does: Propose LONGLIVE, a real-time interactive long video generation framework that supports continuous user input during the generation process, capable of producing high-quality videos up to 240 seconds in length.

LongRLVR: Long-Context Reinforcement Learning Requires Verifiable Context Rewards

Guanzheng Chen (National University Of Singapore), Lidong Bing (MiroMind Ai)

CodeData SynthesisTransformerSupervised Fine-TuningReinforcement LearningTextRetrieval-Augmented Generation

🎯 What it does: In long-text reasoning tasks, LongRLVR is proposed, adding a verifiable context reward to RLVR to explicitly encourage the model to first retrieve relevant evidence before providing answers.

Look Back to Reason Forward: Revisitable Memory for Long-Context LLM Agents

Yaorui Shi (University of Science and Technology of China), An Zhang (University of Science and Technology of China)

CodeReinforcement Learning from Human FeedbackTransformerLarge Language ModelReinforcement LearningAgentic AITextRetrieval-Augmented GenerationChain-of-Thought

🎯 What it does: Propose ReMemR1, an LLM memory agent that integrates historical callback queries into the 'reading while memorizing' framework, achieving nonlinear reasoning and significantly improving long-text question answering performance.

Lookahead Tree-Based Rollouts for Enhanced Trajectory-Level Exploration in Reinforcement Learning with Verifiable Rewards

Shangyu Xing (Nanjing University), Xiang Ren (University of Southern California)

CodeReinforcement LearningText

🎯 What it does: Propose a tree-search-based rolling strategy called LATR to enhance trajectory-level diversity in RLVR, and integrate it into GRPO and DAPO algorithms;

Lookup multivariate Kolmogorov-Arnold Networks

Sergey Pozdnyakov (Γ‰cole Polytechnique FΓ©dΓ©rale de Lausanne), Philippe Schwaller (Γ‰cole Polytechnique FΓ©dΓ©rale de Lausanne)

CodeClassificationComputational EfficiencyImageTabular

🎯 What it does: In deep learning models, traditional high-dimensional linear layers are replaced with lookup multivariate Kolmogorov-Arnold networks (lmKANs), achieving a large number of trainable parameters while inference FLOPs are only twice that of linear layers; simultaneously, custom CUDA kernels are provided to accelerate inference.

Loopholing Discrete Diffusion: Deterministic Bypass of the Sampling Wall

Mingyu Jo (KAIST), Sungjin Ahn (KAIST)

CodeGenerationTransformerDiffusion modelText

🎯 What it does: Propose the Loopholing mechanism and Loopholing Discrete Diffusion Models (LDDMs), which introduce a deterministic hidden layer path into discrete diffusion models to avoid distribution information collapse caused by the sampling wall;

LoRA meets Riemannion: Muon Optimizer for Parametrization-independent Low-Rank Adapters

Vladimir Bogachev (HSE University), Maxim Rakhuba (HSE University)

CodeOptimizationImageText

🎯 What it does: Propose a fully Riemannian LoRA framework that directly optimizes low-rank adapters on a fixed-rank matrix manifold to resolve parameterization ambiguity;

LoRA-Mixer: Coordinate Modular LoRA Experts Through Serial Attention Routing

Wenbing Li (Huazhong University of Science and Technology), Wei Yang (Huazhong University of Science and Technology)

CodeComputational EfficiencyAI Code AssistantTransformerMixture of ExpertsTextBenchmark

🎯 What it does: Developed a hybrid expert framework called LoRA-Mixer, which routes LoRA experts to the attention projection layer, achieving efficient multi-task adaptation.

LoRA-S: An Efficient Low Rank Adaptation scheme via Sylvester equation

Jinyang ZHENG, Tong Wu (Hong Kong University of Science and Technology)

CodeOptimizationComputational EfficiencySupervised Fine-TuningImageText

🎯 What it does: Propose the LoRA-S framework, which couples LoRA with pre-trained optimizers via horizontal enhancement theory to achieve efficient low-rank adaptation without weight decay.

Lost in the Non-convex Loss Landscape: How to Fine-tune the Large Time Series Model?

Xu Zhang (Fudan University), Wei Wang (Fudan University)

CodeAnomaly DetectionOptimizationRecurrent Neural NetworkSupervised Fine-TuningTime SeriesBenchmark

🎯 What it does: Proposes the Smoothed Full Fine-tuning (SFF) technique, which smooths the loss landscape and enhances downstream fine-tuning performance by performing linear interpolation between pre-trained LTSM and randomly initialized models.

Low Rank Transformer for Multivariate Time Series Anomaly Detection and Localization

Charalampos Shimillas (University of Cyprus), Marios Polycarpou (University of Cyprus)

CodeAnomaly DetectionExplainability and InterpretabilityTransformerTime Series

🎯 What it does: Study the learning process of Transformer in multivariate time series anomaly detection, propose Low-Rank Transformer (ALoRa-T) for anomaly detection, and design ALoRa-Loc to achieve anomaly localization and interpretability.

Low-Latency Neural LiDAR Compression with 2D Context Models

Rui Song (Hong Kong University of Science and Technology), Jun Zhang (Hong Kong University of Science and Technology)

CodeCompressionAuto EncoderOptical FlowMultimodalityPoint Cloud

🎯 What it does: Designed a fully 2D context model called RangeCM, achieving low-latency LiDAR point cloud geometry and intensity compression.

Low-Pass Filtering Improves Behavioral Alignment of Vision Models

Max Wolff (Max Planck Institute for Intelligent Systems), Wieland Brendel (Max Planck Institute for Intelligent Systems)

CodeExplainability and InterpretabilityConvolutional Neural NetworkTransformerImageBenchmark

🎯 What it does: Significantly improve the behavioral consistency of visual models with humans (error consistency and shape preference) by applying low-pass filtering (blurring or downsampling) to the input during testing

LRIM: a Physics-Based Benchmark for Provably Evaluating Long-Range Capabilities in Graph Learning

JoΓ«l Mathys, Francesco Alesiani (NEC Laboratories Europe)

CodeGraph Neural NetworkTransformerGraphBenchmarkPhysics Related

🎯 What it does: Propose a physics-based provable long-range graph learning benchmark (LRIM) based on the Ising model, generating datasets of varying scales and long-range difficulty through controllable parameters, and converting the energy change prediction task into a node regression problem;

LSA: Layer-wise Sparsity Allocation for Large Language Model Pruning Based on Minimal Linear Reconstruction Error

Zhiguo Yang (University of Electronic Science and Technology of China), Jian Cheng (University of Electronic Science and Technology of China)

CodeComputational EfficiencyKnowledge DistillationTransformerLarge Language ModelTextBenchmark

🎯 What it does: Propose a hierarchical sparse allocation method LSA based on minimum linear reconstruction error for unsupervised sparse pruning of large language models while maintaining high performance.

LucidFlux: Caption-Free Universal Image Restoration via a Large-Scale Diffusion Transformer

Song Fei (Hong Kong University of Science and Technology), Lei Zhu (Hong Kong University of Science and Technology)

CodeRestorationTransformerVision Language ModelDiffusion modelImage

🎯 What it does: Developed a caption-free photorealistic image restoration framework called LucidFlux, leveraging the large-scale Diffusion Transformer Flux.1 to perform lossless restoration of real-world low-quality images.

LUMINA: Detecting Hallucinations in RAG System with Context–Knowledge Signals

Samuel Yeh (University of Wisconsin-Madison), Tanwi Mallick (Argonne National Laboratory)

CodeAnomaly DetectionTransformerTextRetrieval-Augmented Generation

🎯 What it does: Developed an unsupervised hallucination detection framework called LUMINA, which evaluates the credibility of answers generated by RAG systems using two signals: external context utilization rate and internal knowledge utilization rate.

Lumos-1: On Autoregressive Video Generation with Discrete Diffusion from a Unified Model Perspective

Hangjie Yuan (Tsinghua University), Yi Yang (Zhejiang University)

CodeGenerationTransformerLarge Language ModelSupervised Fine-TuningVision Language ModelDiffusion modelImageVideoTextMultimodality

🎯 What it does: Propose Lumos-1, an autoregressive video generation model based on LLM, which employs discrete diffusion for efficient generation;

MAC-AMP: A Closed-Loop Multi-Agent Collaboration System for Multi-Objective Antimicrobial Peptide Design

Gen Zhou (Western University), Pingzhao Hu (Western University)

CodeOptimizationExplainability and InterpretabilityDrug DiscoveryReinforcement Learning from Human FeedbackProtein Structure PredictionTransformerLarge Language ModelReinforcement LearningAgentic AIBiomedical Data

🎯 What it does: A closed-loop multi-agent collaboration system, MAC-AMP, was constructed to achieve multi-objective optimization in antimicrobial peptide (AMP) design.

MAGE: Multi-scale Autoregressive Generation for Offline Reinforcement Learning

Chenxing Lin (Xiamen University), Cheng Wang (Xiamen University)

CodeGenerationTransformerReinforcement LearningAuto EncoderBenchmark

🎯 What it does: Propose MAGEβ€”a multi-scale autoregressive generation method that utilizes a quantized autoencoder and multi-scale Transformer to progressively generate offline reinforcement learning trajectories from coarse to fine, addressing long-horizon sparse reward tasks;

Making Slow Thinking Faster: Compressing LLM Chain-of-Thought via Step Entropy

Zeju Li, Qiang Xu (Chinese University of Hong Kong)

CodeOptimizationComputational EfficiencyTransformerSupervised Fine-TuningReinforcement LearningTextBenchmarkChain-of-Thought

🎯 What it does: Propose a chain-of-thought compression method based on step entropy, trimming low-entropy steps to improve inference efficiency.

Mamba-3: Improved Sequence Modeling using State Space Principles

Aakash Lahoti (Carnegie Mellon University), Albert Gu (Carnegie Mellon University)

CodeComputational EfficiencyRepresentation LearningLarge Language ModelTextSequential

🎯 What it does: Propose Mamba-3, a linear sequence layer based on state space models (SSM), significantly improving language modeling, state tracking, and inference efficiency.

Many Eyes, One Mind: Temporal Multi-Perspective and Progressive Distillation for Spiking Neural Networks

Kai Sun, Levin Kuhlmann (Northeastern University)

CodeClassificationKnowledge DistillationSpiking Neural NetworkTransformerImage

🎯 What it does: Proposes a unified knowledge distillation framework, MEOM, combining multi-perspective temporal distillation and progressive consistency training to enhance the overall accuracy and time flexibility of spiking neural networks during truncated inference.

Many-for-Many: Unify the Training of Multiple Video and Image Generation and Manipulation Tasks

Ruibin Li (ByteDance), Lei Zhang (Hong Kong Polytechnic University)

CodeGenerationData SynthesisTransformerDiffusion modelFlow-based ModelImageVideoTextMultimodality

🎯 What it does: Proposes the Many-for-Many (MfM) framework, training a single model to perform various video and image generation and editing tasks.

Mapping Semantic & Syntactic Relationships with Geometric Rotation

Michael Freenor (TELUS Digital), Lauren Alvarez (TELUS Digital)

CodeDomain AdaptationRepresentation LearningText

🎯 What it does: Developed the RISE method based on rotational alignment, modeling sentence-level semantic-syntactic variations (negation, conditional clauses, politeness) as consistent rotations on a hypersphere, supporting cross-lingual and cross-model inference.

MAPSS: Manifold-based Assessment of Perceptual Source Separation

Amir Ivry (Technion Israel Institute of Technology), Shinji Watanabe (Carnegie Mellon University)

CodeTransformerDiffusion modelContrastive LearningBenchmarkAudio

🎯 What it does: Proposed two novel evaluation metrics for audio source separationβ€”Perceptual Separation (PS) and Perceptual Matching (PM)β€”by constructing a diffusion graph on self-supervised audio embeddings to separate and quantify two distortion patterns: leakage and self-distortion.

Market Games for Generative Models: Equilibria, Welfare, and Strategic Entry

Xiukun Wei (Ohio State University), Xueru Zhang (Ohio State University)

CodeGenerationOptimizationConvolutional Neural NetworkSupervised Fine-TuningImage

🎯 What it does: This paper models the generative model market as a three-layer model-platform-user game, analyzing pure Nash equilibrium, user welfare, and diversity, and proposes entry strategies from the perspective of model providers.

MarS-FM: Generative Modeling of Molecular Dynamics via Markov State Models

Kacper KapuΕ›niak (University of Oxford), Francesco Di Giovanni (Valence Labs)

CodeDrug DiscoveryFlow-based ModelBiomedical DataPhysics Related

🎯 What it does: Proposed the MSM Emulators class of models, learning cross-state transitions through Markov state models and implementing the MARS-FM framework to generate molecular dynamics trajectories.

MARS-Sep: Multimodal-Aligned Reinforced Sound Separation

Zihan Zhang (Zhejiang University), Tao Jin (Zhejiang University)

CodeRestorationReinforcement LearningVision-Language-Action ModelContrastive LearningMultimodality

🎯 What it does: Propose the MARS-Sep model by improving multimodal alignment audio separation through a reinforcement learning framework;

MAS$^2$: Self-Generative, Self-Configuring, Self-Rectifying Multi-Agent Systems

Kun Wang (Nanyang Technological University), Yufei Guo (Peking University)

CodeOptimizationLarge Language ModelReinforcement LearningAgentic AITextBenchmark

🎯 What it does: Propose MAS 2, which utilizes multi-agent generation, implementation, and correction of meta-agents for recursive self-construction of multi-agent systems;

MaskCO: Masked Generation Drives Effective Representation Learning and Exploiting for Combinatorial Optimization

Lvda Chen (Shanghai Jiao Tong University), Junchi Yan (Shanghai Jiao Tong University)

CodeOptimizationRepresentation LearningTransformerSupervised Fine-TuningReinforcement LearningGraphBenchmark

🎯 What it does: Proposes MaskCO, a self-supervised learning framework based on mask generation for neural combinatorial optimization;

Masked Generative Policy for Robotic Control

Lipeng Zhuang (University of Glasgow), Paul Henderson (University of Glasgow)

CodeRobotic IntelligenceTransformerAuto EncoderSequential

🎯 What it does: Propose the Masked Generative Policy (MGP) framework, which uses a parallel masked generation Transformer to generate and dynamically refine action sequences, achieving low-latency vision-motor imitation learning.

MaskPro: Linear-Space Probabilistic Learning for Strict (N:M)-Sparsity on LLMs

Yan Sun (University of Sydney), Dacheng Tao (Nanyang Technological University)

CodeComputational EfficiencyTransformerLarge Language ModelReinforcement LearningText

🎯 What it does: Propose MaskPro, a linear-space probabilistic learning framework for large language models (LLMs) to achieve strict (N:M) sparsity;

MASS: MoErging through Adaptive Subspace Selection

Donato Crisostomi (Sapienza University of Rome), Emanuele RodolΓ  (Sapienza University of Rome)

CodeComputational EfficiencyTransformerMixture of ExpertsImageText

🎯 What it does: Designed a lightweight model merging method called MASS, which utilizes low-rank singular vectors from task updates and employs a projection router without training data to dynamically select subspaces and classification heads during inference.

Massive Editing for Large Language Models Based on Dynamic Weight Generation

Wentao Wan (Sun Yat-sen University), Keze Wang (Sun Yat-sen University)

CodeTransformerDiffusion modelScore-based ModelContrastive LearningTextBenchmark

🎯 What it does: Proposed a dynamic weight generation-based LLM knowledge editing method called MeG, which utilizes diffusion models to add a single dynamic neuron in specific layers for large-scale knowledge editing;

Massive Memorization with Hundreds of Trillions of Parameters for Sequential Transducer Generative Recommenders

Zhimin Chen (Meta), Wen-Yun Yang (Meta)

CodeRecommendation SystemTransformerSequential

🎯 What it does: Proposed the VISTA two-stage framework, which first compresses users' extremely long interaction history into a small number of cached embeddings, and then applies target-aware attention to candidate items, significantly reducing online inference computational load while maintaining prediction performance.

Mastering Sparse CUDA Generation through Pretrained Models and Deep Reinforcement Learning

Yaoyu Wang (Chinese Academy of Sciences), Guangming Tan (Chinese Academy of Sciences)

CodeComputational EfficiencyAI Code AssistantTransformerLarge Language ModelSupervised Fine-TuningReinforcement LearningTextGraph

🎯 What it does: Proposes the SparseRL framework, leveraging pre-trained language models and deep reinforcement learning to generate high-performance CUDA code for sparse matrix operations.

MATA: A Trainable Hierarchical Automaton System for Multi-Agent Visual Reasoning

Zhixi Cai (Monash University), Hamid Rezatofighi (Monash University)

CodeExplainability and InterpretabilityComputational EfficiencyTransformerLarge Language ModelSupervised Fine-TuningAgentic AIVision Language ModelImageTextMultimodality

🎯 What it does: Propose the MATA system, which divides visual reasoning into a hierarchical, trainable finite state machine, using multi-agent collaboration and competition to achieve interpretable and efficient reasoning processes.

Mathesis: Towards Formal Theorem Proving from Natural Languages

Yu Xuejun (Huawei), Zhenguo Li (Huawei)

CodeLarge Language ModelReinforcement LearningTextBenchmark

🎯 What it does: Proposed a complete pipeline (Mathesis) from natural language to formal theorem proving, including automation, verification, and proof steps.

MAVEN: A Mesh-Aware Volumetric Encoding Network for Simulating 3D Flexible Deformation

Zhe Feng (Peking University), Yunhuai Liu (Peking University)

CodeGraph Neural NetworkMeshPhysics Related

🎯 What it does: Proposes a Mesh-aware Volumetric Encoding Network (MAVEN) for 3D elastic and plastic deformation simulation.

MCP Security Bench (MSB): Benchmarking Attacks Against Model Context Protocol in LLM Agents

Dongsen Zhang (Beijing University of Posts and Telecommunications), Wenjun Xu (Beijing University of Posts and Telecommunications)

CodeSafty and PrivacyAdversarial AttackTransformerLarge Language ModelAgentic AITextBenchmark

🎯 What it does: Established the MCP security benchmark MSB, containing 12 categories of attacks, 2000 real attack instances, and evaluated the security of LLM agents in the MCP environment through real tool calls.

MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers

Zhenting Wang (Accenture), Eugene Siow (Accenture)

CodeTransformerLarge Language ModelAgentic AIPrompt EngineeringTextBenchmarkFinance Related

🎯 What it does: Developed the MCP-BENCH benchmark, connecting 28 MCP servers (with 250 tools in total), using automatic task synthesis and fuzzy instruction evaluation to assess LLM agents' performance in multi-step, cross-domain tool collaboration and long-range planning.

MCP-SafetyBench: A Benchmark for Safety Evaluation of Large Language Models with Real-World MCP Servers

Xuanjun Zong (East China Normal University), Chao Yang (Shanghai AI Laboratory)

CodeLarge Language ModelPrompt EngineeringTextBenchmark

🎯 What it does: Proposed and implemented MCP-SafetyBench, a multi-round, multi-domain safety evaluation benchmark based on real MCP servers;

MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP Use

Zijian Wu (National University of Singapore), Michael Qizhe Shieh (National University of Singapore)

CodeLarge Language ModelAgentic AITextBenchmark

🎯 What it does: Proposed the MCPMark benchmark to evaluate large language models' MCP usage capabilities in multi-tool, multi-step, real-world scenarios;

Measure Twice, Cut Once: A Semantic-Oriented Approach to Video Temporal Localization with Video LLMs

Zongshang Pang (University of Osaka), Yuta Nakashima (University of Osaka)

CodeSegmentationLarge Language ModelSupervised Fine-TuningVision Language ModelContrastive LearningVideoMultimodality

🎯 What it does: Propose a semantics-driven video LLM framework called MeCo, which achieves semantic segmentation and localization of video temporal events through structured token generation, query-focused description, and contrastive learning.

Measurement Score-Based Diffusion Model

Chicago Y. Park (University of Wisconsin Madison), Ulugbek S. Kamilov (University of Wisconsin Madison)

CodeRestorationMixture of ExpertsDiffusion modelScore-based ModelImageBiomedical DataMagnetic Resonance Imaging

🎯 What it does: Propose a Measurement Score-based Diffusion Model (MSM), which generates complete measurements and solves linear inverse problems by learning partial scores dependent only on downsampling and noise measurements in the measurement domain, without requiring training on clear images.

Measuring Physical-World Privacy Awareness of Large Language Models: An Evaluation Benchmark

Xinjie Shen (Georgia Tech), Pan Li (Georgia Tech)

CodeSafty and PrivacyLarge Language ModelPrompt EngineeringTextMultimodalityBenchmarkChain-of-Thought

🎯 What it does: Propose the EAPrivacy benchmark to evaluate the privacy awareness of large language models (LLMs) in physical environments.

Measuring the Intrinsic Dimension of Earth Representations

Arjun Rao (University of Colorado Boulder), Esther Rolf (University of Colorado Boulder)

CodeRepresentation LearningData-Centric LearningVision Language ModelMultimodality

🎯 What it does: This paper studies the intrinsic dimensionality of geographic implicit neural representations (INR) to quantify their information content.

Mechanistic Detection and Mitigation of Hallucination in Large Reasoning Models

Zhongxiang Sun (Renmin University of China), Jun Xu (Renmin University of China)

CodeExplainability and InterpretabilityReinforcement Learning from Human FeedbackTransformerLarge Language ModelReinforcement LearningTextChain-of-Thought

🎯 What it does: This paper investigates the phenomenon of reasoning hallucinations in large-scale models, proposing a reasoning score based on model internal representations. This score identifies three categories of hallucination patterns, and based on this, constructs a reasoning hallucination detection framework (RHD) and incorporates a reward shaping mechanism based on the reasoning score in reinforcement learning (GRPO-R) to reduce hallucination rates.

MedAgentGym: A Scalable Agentic Training Environment for Code-Centric Reasoning in Biomedical Data Science

Ran Xu (Emory University), Wenqi Shi (University of Washington)

CodeDrug DiscoveryAI Code AssistantReinforcement Learning from Human FeedbackTransformerLarge Language ModelReinforcement LearningAgentic AIMultimodalityBiomedical DataElectronic Health RecordsBenchmark

🎯 What it does: Developed an executable and scalable medical code reasoning training platform called MedAgentGym, and trained and enhanced the medical coding capabilities of LLM agents on this platform.

MedAraBench: Large-scale Arabic Medical Question Answering Dataset and Benchmark

Mouath Abu Daoud, Farah E. Shamout (Cleveland Clinic Abu Dhabi)

CodeTransformerLarge Language ModelSupervised Fine-TuningPrompt EngineeringTextBiomedical DataBenchmark

🎯 What it does: Constructed and released MedAraBench, a large-scale benchmark containing 24,883 Arabic medical multiple-choice questions for evaluating the medical reasoning capabilities of large language models.

MedGMAE: Gaussian Masked Autoencoders for Medical Volumetric Representation Learning

Xueming Fu (University of Science and Technology of China), S Kevin Zhou

CodeClassificationRestorationSegmentationRepresentation LearningTransformerAuto EncoderContrastive LearningGaussian SplattingBiomedical DataComputed Tomography

🎯 What it does: Leverages a self-supervised pre-trained 3D Gaussian mask autoencoder (MedGMAE) to predict complete 3D Gaussian parameters from sparse visible image patches, and applies them to subsequent segmentation, classification, registration, and reconstruction tasks.

Medical thinking with multiple images

Zonghai Yao (University of Massachusetts Amherst), hong yu

CodeLarge Language ModelVision Language ModelMultimodalityBiomedical DataBenchmarkChain-of-Thought

🎯 What it does: Proposed MedThinkVQAβ€”a multi-modal medical question-answering benchmark based on real multi-image cases, incorporating expert-annotated step-by-step diagnostic traces;

MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents

Zijian Zhou (Singapore-MIT Alliance for Research and Technology Centre), Paul Pu Liang (Massachusetts Institute of Technology)

CodeComputational EfficiencyTransformerReinforcement LearningAgentic AITextSequentialRetrieval-Augmented Generation

🎯 What it does: Propose the MEM1 framework, training language model agents to achieve memory compression and reasoning through a unified internal state in multi-round interactions, maintaining nearly constant context size.

Memba: Membrane-driven Parameter-Efficient Fine-Tuning for Mamba

Donghyun Lee (University of Southern California), Priyadarshini Panda (University of Southern California)

CodeClassificationRecognitionImageTextBenchmark

🎯 What it does: A parameter-efficient fine-tuning (PEFT) method called Memba, based on membrane potential, is proposed for the Mamba model, specifically designed for the SSM architecture.

Membership Privacy Risks of Sharpness Aware Minimization

Young In Kim (Purdue University), Rajiv Khanna (Purdue University)

CodeOptimizationSafty and PrivacyAdversarial AttackImageTabular

🎯 What it does: Studied that Sharpness-Aware Minimization (SAM) enhances generalization performance while amplifying the privacy leakage risk to membership inference attacks (MIA).

MemGen: Weaving Generative Latent Memory for Self-Evolving Agents

Guibin Zhang (National University of Singapore), Shuicheng YAN (National University of Singapore)

CodeRobotic IntelligenceReinforcement Learning from Human FeedbackTransformerLarge Language ModelSupervised Fine-TuningReinforcement LearningAgentic AITextBenchmarkRetrieval-Augmented Generation

🎯 What it does: Propose MemGen, a framework that dynamically generates latent memories within LLM agents, intertwining memory and reasoning at the token level.

Memorization Through the Lens of Sample Gradients

Deepak Ravikumar (Purdue University), Kaushik Roy (Purdue University)

CodeExplainability and InterpretabilityComputational EfficiencyConvolutional Neural NetworkTransformerImage

🎯 What it does: Proposes cumulative sample gradient (CSG) as an efficient proxy for memorization, based on the theoretical relationship between input gradients and learning time;

Memorizing Long-tail Data Can Help Generalization Through Composition

Mo Zhou (University of Washington), Rong Ge (Duke University)

CodeOptimizationRepresentation LearningConvolutional Neural NetworkImage

🎯 What it does: Studied the synergistic effects of memorization and simple composition in deep learning models under long-tailed data distributions, provided theoretical proofs for linear models, and conducted experimental validation on custom tasks using MNIST and Omniglot.

Memory-T1: Reinforcement Learning for Temporal Reasoning in Multi-session Agents

Yiming Du (Chinese University of Hong Kong), Kam-Fai Wong (Huawei Technologies Co Ltd)

CodeReinforcement Learning from Human FeedbackTransformerLarge Language ModelReinforcement LearningTextSequentialRetrieval-Augmented Generation

🎯 What it does: Propose the MEMORY-T1 framework, which uses reinforcement learning to precisely filter time-related memories in multi-session dialogues, thereby enhancing temporal reasoning capabilities in long contexts.

MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding

Xin Jin (Westlake University), Huan Wang (Westlake University)

CodeClassificationRecognitionTransformerSupervised Fine-TuningReinforcement LearningVision Language ModelImageMultimodality

🎯 What it does: Propose MergeMix, a unified mixed augmentation framework that generates hybrid images through token merge for image classification and alignment training of multimodal large models.

MergePRAG: Orthogonal Merging of Passage-experts for Multi-hop Parametric RAG

Xuebing Liu (Jeonbuk National University), Seung-Hoon Na (Ulsan National Institute of Science and Technology)

CodeRetrievalComputational EfficiencyTransformerMixture of ExpertsTextRetrieval-Augmented Generation

🎯 What it does: Proposed the MERGEPRAG framework, extending Parametric RAG to multi-hop reasoning scenarios and achieving continuous knowledge injection through orthogonal merging and key layer parameterization.

MergeTune: Continued Fine-Tuning of Vision-Language Models

Wenqing Wang (University of Surrey), Josef Kittler (University of Surrey)

CodeClassificationRetrievalKnowledge DistillationPrompt EngineeringVision Language ModelContrastive LearningImageMultimodality

🎯 What it does: Propose a post-hoc continuous fine-tuning (MERGETUNE) method that identifies weights combining knowledge from pre-trained CLIP and fine-tuned models by leveraging linear mode connectivity, thereby recovering pre-training knowledge lost during fine-tuning.

MeSH: Memory-as-State-Highways for Recursive Transformers

Chengting Yu (Alibaba Group), Bo Zheng (Alibaba Group)

CodeComputational EfficiencyRepresentation LearningTransformerLarge Language ModelText

🎯 What it does: Proposed and implemented a recursive Transformer architecture named MeSH (Memory-as-State-Highways), which externalizes state management through explicit memory buffers and learnable step-level routers, addressing issues of indiscriminate computation and information overload in traditional recursive Transformers.

Meta-Adaptive Prompt Distillation for Few-Shot Visual Question Answering

Akash Gupta (University of Edinburgh), Mirella Lapata (University of Edinburgh)

CodeKnowledge DistillationMeta LearningPrompt EngineeringVision Language ModelImageTextMultimodalityBenchmark

🎯 What it does: Propose Meta-Adaptive Prompt Distillation (MAPD), achieving rapid adaptation on LMM for few-shot visual question answering through meta-learning based soft prompt distillation and attention mapper.

Meta-RL Induces Exploration in Language Agents

Yulun Jiang (EPFL), Maria Brbic

CodeMeta LearningLarge Language ModelReinforcement LearningAgentic AIPrompt EngineeringText

🎯 What it does: Propose LAMERβ€”a Meta-RL-based training framework for large language model agents, enabling agents to actively explore and adaptively learn through environmental feedback in multi-round tasks.

Meta-Router: Bridging Gold-standard and Preference-based Evaluations in LLM Routing

Yichi Zhang (Indiana University Bloomington), Chong Wu (University Of Texas Md Anderson Cancer Center)

CodeData-Centric LearningMeta LearningTextBenchmark

🎯 What it does: Constructed a causal meta-learning based LLM router that jointly trains routing decisions using gold standard and preference data.

MetaCaptioner: Towards Generalist Visual Captioning with Open-source Suites

Zhenxin Lei (Shanghai AI Laboratory), Gen Luo (Shanghai AI Laboratory)

CodeGenerationData SynthesisTransformerLarge Language ModelSupervised Fine-TuningAgentic AIPrompt EngineeringVision Language ModelImageVideoTextMultimodality

🎯 What it does: This paper proposes the CapFlow multi-agent collaboration framework for generating high-quality visual descriptions across domains, and builds MetaCaptioner based on this, becoming a general-purpose visual caption model in the open-source field.

MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction

Zilin Xiao (Meta Superintelligence Labs), Vijai Mohan (Meta Superintelligence Labs)

CodeRetrievalRepresentation LearningTransformerSupervised Fine-TuningContrastive LearningMultimodality

🎯 What it does: METAEMBED proposes an expandable multimodal retrieval framework that generates multi-vector Late Interaction embeddings in Vision-Language Models by leveraging learnable Meta Tokens;

Metis: Training LLMs with FP4 Quantization

Hengjie Cao (Fudan University), Li Shang (Fudan University)

CodeComputational EfficiencyRepresentation LearningTransformerLarge Language ModelText

🎯 What it does: Propose a spectral domain quantization framework, Metis, in LLM training, which splits wide distributions into narrow sub-distributions by leveraging singular value spectral heterogeneity, achieving efficient training in FP4 format.

MIAM: Modality Imbalance-Aware Masking for Multimodal Ecological Applications

Robin Zbinden (Γ‰cole Polytechnique FΓ©dΓ©rale de Lausanne), Devis Tuia (Γ‰cole Polytechnique FΓ©dΓ©rale de Lausanne)

CodeClassificationTransformerMultimodality

🎯 What it does: Proposed and implemented a dynamic masking strategy called MIAM for ecological multimodal learning to handle missing data and enhance model robustness.

MicroMix: Efficient Mixed-Precision Quantization with Microscaling Formats for Large Language Models

Wenyuan Liu (Tianjin University), Xindian Ma (Tianjin University)

CodeComputational EfficiencyTransformerText

🎯 What it does: Proposed a mixed-precision quantization framework called MicroMix, achieving efficient inference on NVIDIA Blackwell architecture using MXFP4/6/8 formats.

MicroVerse: A Preliminary Exploration Toward a Micro-World Simulation

Rongsheng Wang (Chinese University of Hong Kong Shenzhen), Benyou Wang (Chinese University of Hong Kong Shenzhen)

CodeGenerationData SynthesisTransformerLarge Language ModelSupervised Fine-TuningDiffusion modelAuto EncoderVideoTextBenchmark

🎯 What it does: This paper proposes the concept of Micro-World Simulation and constructs the MicroWorldBench evaluation benchmark, the MicroSim-10K experimental dataset, and a specialized video generation model for micro-scale simulation called MicroVerse;

MILCO: Learned Sparse Retrieval Across Languages via a Multilingual Connector

Thong Nguyen (University of Amsterdam), Andrew Yates (Johns Hopkins University)

CodeRetrievalTransformerContrastive LearningText

🎯 What it does: Propose MILCO, a sparse retrieval model that maps multilingual queries and documents into a shared English vocabulary space;

MILPnet: A Multi-Scale Architecture with Geometric Feature Sequence Representations for Advancing MILP Problems

Ruobing Wang (Beijing Institute of Technology), Mingzhong Wang (University of the Sunshine Coast)

CodeOptimizationTransformerSequentialBenchmark

🎯 What it does: This paper proposes MILPnet, a multi-scale hybrid attention framework based on sequence modeling, which represents mixed integer linear programming (MILP) problems using geometric feature sequences;

MILR: Improving Multimodal Image Generation via Test-Time Latent Reasoning

Yapeng Mi (University of Science and Technology of China), Qing Li (State Key Laboratory of General Artificial Intelligence, BIGAI)

CodeGenerationTransformerReinforcement LearningVision Language ModelImageTextMultimodality

🎯 What it does: Propose MILR, an inference-enhanced method for multimodal image generation that optimizes image and text latent vectors through reinforcement learning in a unified latent space during testing.

MindMix: A Multimodal Foundation Model for Auditory Perception Decoding via Deep Neural-Acoustic Alignment

RUI LIU, KC Tan

CodeRepresentation LearningTransformerContrastive LearningMultimodalityBiomedical DataAudio

🎯 What it does: Propose MindMix, a multimodal foundation model that utilizes deep neural-acoustic alignment to achieve cross-modal representations between EEG and audio, addressing the limitation of single-modal pre-training in capturing acoustic information.

MindPilot: Closed-loop Visual Stimulation Optimization for Brain Modulation with EEG-guided Diffusion

Dongyang Li (Southern University of Science and Technology), Quanying Liu (Southern University of Science and Technology)

CodeGenerationOptimizationVision Language ModelDiffusion modelImageTime SeriesBiomedical Data

🎯 What it does: Proposed MindPilot, a closed-loop EEG-guided visual stimulus generation framework that continuously optimizes natural images through non-invasive EEG feedback to modulate brain states.

Mini-cluster Guided Long-tailed Deep Clustering

Zhixin Li (Southeast University), Junhui Hou (City University of Hong Kong)

CodeRepresentation LearningContrastive LearningImage

🎯 What it does: Propose a mini-cluster guided long-tailed deep clustering method called MiniClustering to address the class bias problem in unsupervised long-tailed clustering.

Minimax-Optimal Aggregation for Density Ratio Estimation

Lukas Gruber (Johannes Kepler University Linz), Werner Zellinger (Johannes Kepler University Linz)

CodeDomain AdaptationOptimizationImageTextTime Series

🎯 What it does: Proposed and implemented a density ratio estimation model that aggregates different hyperparameter settings, ensuring minimax optimal error convergence under unknown smoothness.

Mirage or Method? How Model–Task Alignment Induces Divergent RL Conclusions

Haoze Wu (Zhejiang University), Junxian He (HKUST)

CodeTransformerLarge Language ModelReinforcement LearningText

🎯 What it does: This paper systematically experimentally verifies several counterintuitive phenomena in reinforcement learning (RL) for large language model reasoning and explores whether these phenomena depend on the alignment strength between the model and the task.

MiSS: Revisiting the Trade-off in LoRA with an Efficient Shard-Sharing Structure

Jiale Kang (Yuanshi Inc), Qingyu Yin (Zhejiang University)

CodeOptimizationComputational EfficiencyTextMultimodality

🎯 What it does: Proposed the MiSS structure, which uses a single shared matrix D to update weights through a sharding expansion approach, addressing the slow convergence caused by LoRA's synchronous updates.

Missingness Bias Calibration in Feature Attribution Explanations

Shailesh Sridhar (University of Pennsylvania), Eric Wong (University of Pennsylvania)

CodeExplainability and InterpretabilityImageTextTabularBiomedical DataMagnetic Resonance ImagingComputed Tomography

🎯 What it does: Proposed a post-calibration method named MCal, which corrects missingness bias caused by feature masks by applying a simple linear transformation on the outputs of a frozen model, thereby enhancing the reliability of explanation methods.

Mitigating Noise Shift in Denoising Generative Models with Noise Awareness Guidance

Jincheng Zhong (Tsinghua University), Mingsheng Long (Tsinghua University)

CodeGenerationSupervised Fine-TuningDiffusion modelFlow-based ModelImage

🎯 What it does: Propose and address the noise shift problem occurring during the sampling process of diffusion generative models, introducing Noise Awareness Guidance (NAG) and its classifier-free version.

Mitigating Semantic Collapse in Generative Personalization with Test-Time Embedding Adjustment

Anh Tuan Bui (Monash University), Dinh Phung (Monash University)

CodeGenerationPrompt EngineeringVision Language ModelDiffusion modelImageText

🎯 What it does: This paper proposes a Test-time Embedding Adjustment (TEA) method to address the semantic collapse problem in personalized models, enabling personalized tokens to no longer suppress other semantics in multi-concept prompts.

Mitigating the Safety Alignment Tax with Null-Space Constrained Policy Optimization

Yifan Niu (Hong Kong University of Science and Technology Guangzhou), Jia Li (Hong Kong University of Science and Technology Guangzhou)

CodeOptimizationReinforcement Learning from Human FeedbackLarge Language ModelReinforcement LearningText

🎯 What it does: Propose an RL framework NSPO that projects safety policy gradients into the zero space of general tasks, achieving LLM safety alignment without compromising original capabilities.

Mixture-of-Visual-Thoughts: Exploring Context-Adaptive Reasoning Mode Selection for General Visual Reasoning

Zejun Li (Fudan University), zhongyu wei

CodeLarge Language ModelSupervised Fine-TuningReinforcement LearningPrompt EngineeringMixture of ExpertsVision Language ModelMultimodalityChain-of-Thought

🎯 What it does: Proposed the MoVT framework and the two-stage AdaVaR training method, unifying multiple visual reasoning modes and achieving context-adaptive mode selection.

MLP Memory: A Retriever-Pretrained Memory for Large Language Models

Rubin Wei (Shanghai Jiao Tong University), Zhouhan Lin (Shanghai Jiao Tong University)

CodeRetrievalComputational EfficiencyLarge Language ModelText

🎯 What it does: Train a lightweight full MLP module in large language models (LLMs) to mimic the distribution of a k-NN retriever, enabling memory and invocation of external knowledge without explicit retrieval.

MMPD: Diverse Time Series Forecasting via Multi-Mode Patch Diffusion Loss

Yunhao Zhang (Shanghai Jiao Tong University), Junchi Yan (Shanghai Jiao Tong University)

CodeTransformerDiffusion modelTime Series

🎯 What it does: Proposed a multi-modal differentiable time series prediction loss based on diffusion models (MMPD), which can achieve multi-modal (multiple possible futures) prediction on any patch-based prediction backbone while also considering deterministic prediction.

MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence

Sihan Yang (Shanghai AI Laboratory), Jiangmiao Pang (Shanghai AI Laboratory)

CodeTransformerPrompt EngineeringVision Language ModelImageTextMultimodalityBenchmarkChain-of-Thought

🎯 What it does: Proposed MMSI-Bench - a VQA benchmark for multi-image spatial reasoning, containing 1000 multi-step multi-image multiple-choice questions with human-annotated reasoning processes;

MMTok: Multimodal Coverage Maximization for Efficient Inference of VLMs

Sixun Dong (Arizona State University), Qi Qian (Zoom Communications)

CodeComputational EfficiencyTransformerVision Language ModelMultimodality

🎯 What it does: Propose a training-free multi-modal maximum coverage method called MMTok, which selects the most informative subset from a large number of visual tokens to enhance the inference efficiency of Vision-Language Models (VLMs).

MnemoDyn: Learning Resting State Dynamics from $40$K FMRI sequences

Sourav Pal (University of Wisconsin Madison), Vikas Singh (University of Wisconsin Madison)

CodeClassificationRepresentation LearningConvolutional Neural NetworkSupervised Fine-TuningAuto EncoderTime SeriesSequentialBiomedical DataMagnetic Resonance ImagingAlzheimer's DiseaseStochastic Differential EquationOrdinary Differential Equation

🎯 What it does: Propose a dynamic system model called MnemoDyn, which combines multiscale wavelet subbasis functions with pseudodifferential operators, for large-scale self-supervised pretraining and fine-tuning on multiple prediction tasks under resting-state fMRI (rs-fMRI);

MOAI: Module-Optimizing Architecture for Non-Interactive Secure Transformer Inference

Linru Zhang (Nanyang Technological University), Kwok-Yan Lam (Nanyang Technological University)

CodeComputational EfficiencyTransformerText

🎯 What it does: MOAI proposes an efficient non-interactive secure Transformer inference framework

MobiEdit: Resource-efficient Knowledge Editing for Personalized On-device LLMs

Zhenyan Lu (Beijing University of Posts and Telecommunications), Mengwei Xu (Beijing University of Posts and Telecommunications)

CodeComputational EfficiencyTransformerLarge Language ModelText

🎯 What it does: Developed the MobiEdit framework, enabling resource-efficient knowledge editing of 3B-scale LLMs on mobile devices.

MobileLLM-R1: Exploring the Limits of Sub-Billion Language Model Reasoners with Open Training Recipes

Changsheng Zhao (Meta AI), Vikas Chandra (Meta AI)

CodeData-Centric LearningReinforcement Learning from Human FeedbackTransformerLarge Language ModelSupervised Fine-TuningText

🎯 What it does: Built a series of small-scale (≀1B parameters) inference language models called MobileLLM‑R1, achieving strong inference capabilities through efficient data curation and adaptive sampling.

MobileRL: Online Agentic Reinforcement Learning for Mobile GUI Agents

Yifan Xu (Tsinghua University), Yuxiao Dong (Z.AI)

CodeReinforcement Learning from Human FeedbackTransformerSupervised Fine-TuningReinforcement LearningAgentic AIVision Language ModelMultimodality

🎯 What it does: Proposed an online agent-based reinforcement learning framework called MOBILERL, specifically designed for training mobile GUI agents, and designed the difficulty-adaptive GRPO (ADAGRPO) algorithm based on this framework.

Modal Aphasia: Can Unified Multimodal Models Describe Images From Memory?

Michael Aerni (ETH Zurich), Florian Tramèr (ETH Zurich)

CodeSafty and PrivacyAdversarial AttackTransformerLarge Language ModelSupervised Fine-TuningImageTextMultimodality

🎯 What it does: The study reveals that unified multimodal models excel in visual generation but suffer significant failures in textual descriptions, introducing and validating the 'modal aphasia' phenomenon and demonstrating its potential threat to AI safety.