arXivSub Start free trial

ICLR 2025 Papers with Code β€” Page 8

International Conference on Learning Representations Β· 1682 papers

IFORMER: INTEGRATING CONVNET AND TRANSFORMER FOR MOBILE APPLICATION

Chuanyang Zheng (Shanghai Jiao Tong University)

CodeObject DetectionSegmentationConvolutional Neural NetworkTransformerImage

🎯 What it does: This paper proposes iFormer, a lightweight hybrid vision network designed for mobile devices.

IgGM: A Generative Model for Functional Antibody and Nanobody Design

Rubo Wang (Institute of Microelectronics, Chinese Academy of Sciences), Jianhua Yao (Tencent AI Lab)

CodeGenerationProtein Structure PredictionTransformerLarge Language ModelBiomedical Data

🎯 What it does: We propose IgGM, a consistency model that jointly generates antibody CDR sequences and complete antibody-antigen complex structures, enabling de novo antibody and nanobody design given only the antigen and framework region sequences.

IGL-Bench: Establishing the Comprehensive Benchmark for Imbalanced Graph Learning

Jiawen Qin (Beihang University), Philip S. Yu (University of Illinois, Chicago)

CodeClassificationOptimizationGraph Neural NetworkGraphBenchmark

🎯 What it does: A unified benchmark framework called IGL-Bench has been constructed, covering 17 real graph datasets and 24 imbalanced graph learning algorithms, providing standardized data processing, partitioning strategies, and experimental scripts.

Image Watermarks are Removable using Controllable Regeneration from Clean Noise

Yepeng Liu (University of Florida), Yuheng Bu (University of Florida)

CodeRestorationAdversarial AttackDiffusion modelImage

🎯 What it does: A controllable regeneration attack, CtrlRegen/CtrlRegen+, is proposed, which efficiently removes image watermarks while maintaining visual quality by starting from pure Gaussian noise and incorporating semantic and spatial control during the diffusion process.

Image-level Memorization Detection via Inversion-based Inference Perturbation

Yue Jiang (Institute of Automation Chinese Academy of Sciences), Jing Dong (Institute of Automation Chinese Academy of Sciences)

CodeImage TranslationAnomaly DetectionDiffusion modelImage

🎯 What it does: A framework for image-level memory detection (IIP) based on prompt-free DDIM inversion and random prompt perturbation is proposed to determine whether an image has been memorized by a text-to-image diffusion model.

Immunogenicity Prediction with Dual Attention Enables Vaccine Target Selection

Song Li (Shanghai Jiao Tong University), Bingxin Zhou (Shanghai Jiao Tong University)

CodeDrug DiscoveryTransformerLarge Language ModelSupervised Fine-TuningMultimodalityBiomedical Data

🎯 What it does: A deep learning model based on a dual attention mechanism, VENUSVACCINE, is proposed for immunogenicity prediction, and an ImmunoDB dataset containing over 7,000 antigens from bacterial, viral, and tumor sources is constructed, along with a posterior validation protocol.

Implicit In-context Learning

Zhuowei Li (Rutgers University), Dimitris N. Metaxas (Rutgers University)

CodeClassificationComputational EfficiencyTransformerLarge Language ModelText

🎯 What it does: A new implicit context learning method (I2CL) is proposed, aimed at reducing the reasoning cost of context learning to be comparable to zero-shot learning while maintaining minimal information loss.

Implicit Neural Surface Deformation with Explicit Velocity Fields

Lu Sang (Technical University of Munich), Daniel Cremers (University of Bonn)

CodePoint Cloud

🎯 What it does: Given two sets of point clouds, we self-supervise the simultaneous learning of time-varying neural implicit surfaces and the corresponding velocity fields using sparse correspondences, achieving physically feasible deformations without intermediate shape supervision.

Implicit Search via Discrete Diffusion: A Study on Chess

Jiacheng Ye (University of Hong Kong), Lingpeng Kong (Huawei Noah's Ark Lab)

CodeTransformerSupervised Fine-TuningDiffusion modelSequential

🎯 What it does: A model named DIFFUSEARCH is proposed, which implements implicit search during inference through a discrete diffusion model, replacing traditional explicit search methods (such as MCTS) to enhance next-step action prediction and long-term planning capabilities.

Improved Diffusion-based Generative Model with Better Adversarial Robustness

Zekun Wang (Harbin Institute of Technology), Zhi-Ming Ma (Harbin Institute of Technology)

CodeGenerationOptimizationAdversarial AttackDiffusion modelGenerative Adversarial NetworkImage

🎯 What it does: A method is proposed and implemented to incorporate efficient adversarial training (AT) into the training process of diffusion probabilistic models (DPM) and consistency models (CM) to alleviate the distribution mismatch problem between the training and sampling phases.

Improved Sampling Of Diffusion Models In Fluid Dynamics With Tweedie's Formula

Youssef Shehata (Technical University of Munich), Nils Thuerey (Technical University of Munich)

CodeDiffusion modelTime SeriesPhysics Related

🎯 What it does: This paper proposes two improved sampling methods for diffusion modelsβ€”Truncated Sampling Model (TSM) and Iterative Refinement (IR)β€”to achieve single-step or few-step sampling while maintaining or enhancing prediction accuracy, suitable for fluid dynamics simulations.

Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Xiaojun Jia (Nanyang Technological University), Min Lin (Sea AI Lab)

CodeOptimizationSafty and PrivacyAdversarial AttackTransformerLarge Language ModelPrompt EngineeringText

🎯 What it does: This paper addresses the security alignment issue of large language models by proposing an improved gradient optimization-based cracking techniqueβ€”I-GCG. By introducing diverse harmful guidance templates, an automatic multi-coordinate update strategy, and an easy-to-difficult initialization method, it achieves an almost 100% cracking success rate.

Improved Training Technique for Latent Consistency Models

Quan Dao (Rutgers University), Dimitris N. Metaxas

CodeGenerationData SynthesisDiffusion modelAuto EncoderImage

🎯 What it does: This paper proposes an improved training framework for training consistency models in latent space, capable of generating high-quality images in one to two steps.

ImProver: Agent-Based Automated Proof Optimization

Riyaz Ahuja (Carnegie Mellon University), Sean Welleck (Carnegie Mellon University)

CodeOptimizationTransformerLarge Language ModelPrompt EngineeringTextRetrieval-Augmented Generation

🎯 What it does: ImProver has been developed, a Lean proof optimizer based on large language models, capable of automatically rewriting and optimizing proof length, declarative aspects, and other metrics while maintaining proof correctness.

Improving Data Efficiency via Curating LLM-Driven Rating Systems

Jinlong Pang (University of California), Wei Wei (Accenture)

CodeRecommendation SystemOptimizationData-Centric LearningTransformerLarge Language ModelSupervised Fine-TuningPrompt EngineeringText

🎯 What it does: Proposes the DS2 data filtering pipeline, which corrects the quality scores generated by LLMs and combines diversity filtering, retaining only 3.3% of the data to complete instruction fine-tuning.

Improving Equivariant Networks with Probabilistic Symmetry Breaking

Hannah Lawrence (Massachusetts Institute of Technology), SΓ©kou-Oumar Kaba (McGill University)

CodeGraph Neural NetworkAuto EncoderGraph

🎯 What it does: Under the premise of maintaining the equivariance of the network, this study investigates how to break the self-symmetry of the input, proposing Symmetry Breaking Position Encoding (SymPE) and providing a corresponding theoretical framework.

Improving Generalization and Robustness in SNNs Through Signed Rate Encoding and Sparse Encoding Attacks

Bhaskar Mukhoty (Mohamed bin Zayed University of Artificial Intelligence), Bin Gu (Jilin University)

CodeOptimizationAdversarial AttackSpiking Neural NetworkImage

🎯 What it does: This paper proposes Symbol Rate Encoding (SRATE) and Sparse Encoding Attack (SEA) to improve the generalization and robustness of spiking neural networks.

Improving Instruction-Following in Language Models through Activation Steering

Alessandro Stolfo (ETH Zurich), Besmira Nushi (Microsoft Research)

CodeTransformerLarge Language ModelPrompt EngineeringText

🎯 What it does: This paper proposes to control fine-grained constraints such as format, length, and keywords by comparing activation differences to compute instruction-specific vectors, and directly weighting the model's residual flow during inference.

Improving Language Model Distillation through Hidden State Matching

Sayantan Dasgupta (University of Melbourne), Trevor Cohn (University of Melbourne)

CodeCompressionKnowledge DistillationTransformerLarge Language ModelSupervised Fine-TuningText

🎯 What it does: In language model distillation, Centered Kernel Alignment (CKA) is proposed to match hidden layers of different dimensions, achieving a higher compression rate for the student model.

Improving Long-Text Alignment for Text-to-Image Diffusion Models

Luping Liu (University of Hong Kong), Dong Xu (University of Hong Kong)

CodeGenerationTransformerLarge Language ModelDiffusion modelImageText

🎯 What it does: Proposes the LongAlign method to address the insufficient text-image alignment caused by long text inputs, improving the generation of high-quality images corresponding to long texts in Stable Diffusion.

Improving Pretraining Data Using Perplexity Correlations

Tristan Thrush (Stanford University), Tatsunori Hashimoto (Stanford University)

CodeLarge Language ModelTextBenchmark

🎯 What it does: A framework for selecting pre-training data without training or manual screening is constructed by utilizing the correlation between the perplexity of existing large language models and the performance on downstream tasks.

Improving Probabilistic Diffusion Models With Optimal Diagonal Covariance Matching

Zijing Ou (Imperial College London), David Barber (Imperial College London)

CodeGenerationData SynthesisOptimizationDiffusion modelImage

🎯 What it does: An unbiased optimal covariance matching (OCM) objective is proposed to learn the diagonal covariance of diffusion models, significantly improving sampling quality, likelihood estimation, and sampling efficiency while preserving the original mean.

Improving Reasoning Performance in Large Language Models via Representation Engineering

Bertram HΓΈjer (IT University of Copenhagen), Stefan Heinrich (IT University of Copenhagen)

CodeTransformerLarge Language ModelContrastive LearningText

🎯 What it does: Using representation engineering techniques, control vectors are generated in the residual flow of LLMs and injected during inference to enhance the model's performance on reasoning tasks.

Improving Semantic Understanding in Speech Language Models via Brain-tuning

Omer Moussa (Max Planck Institute for Software Systems), Mariya Toneva (Max Planck Institute for Software Systems)

CodeSupervised Fine-TuningMultimodalityMagnetic Resonance ImagingAudio

🎯 What it does: For the speech language model, the authors developed a 'brain fine-tuning' method by fine-tuning a pre-trained model on fMRI recordings while listening to natural stories.

Improving Unsupervised Constituency Parsing via Maximizing Semantic Information

Junjie Chen (University of Tokyo), Danushka Bollegala (University of Liverpool)

CodeLarge Language ModelReinforcement LearningText

🎯 What it does: Introducing the SemInfo objective in unsupervised constituent syntax analysis to maximize the semantic information encoded in the structure, thereby improving parsing accuracy.

ImpScore: A Learnable Metric For Quantifying The Implicitness Level of Sentences

Yuxin Wang (Dartmouth), Soroush Vosoughi (Dartmouth)

CodeContrastive LearningText

🎯 What it does: A learnable, reference-free metric IMPSCORE is proposed and implemented to quantify the implicitness of English sentences.

Imputation for prediction: beware of diminishing returns.

Marine Le Morvan (Inria), Gael Varoquaux

CodeTabular

🎯 What it does: This paper evaluates the impact of different imputation methods on predictive performance through systematic experiments and analyzes the moderating effects of factors such as model expressiveness, missing indicators, and response nonlinearity.

Incorporating Visual Correspondence into Diffusion Model for Virtual Try-On

Siqi Wan (University of Science and Technology of China), Tao Mei (HiDream.ai)

CodeGenerationData SynthesisConvolutional Neural NetworkDiffusion modelImage

🎯 What it does: A virtual try-on method based on diffusion models, SPM-Diff, is proposed, which guides image generation through explicit semantic point matching and 3D perception enhancement. It employs a dual-branch UNet and introduces point focus loss, significantly improving the retention of clothing details and shapes.

INFER: A Neural-symbolic Model For Extrapolation Reasoning on Temporal Knowledge Graph

Ningyuan Li (Beijing University of Posts and Telecommunications), Yifan Zhu (Beijing University of Posts and Telecommunications)

CodeGraph Neural NetworkGraphTime Series

🎯 What it does: A neural symbolic model INFER for temporal knowledge graph extrapolation reasoning is proposed.

Influence Functions for Scalable Data Attribution in Diffusion Models

Bruno Kacper Mlodozeniec (University of Cambridge), Richard E. Turner (University of Cambridge)

CodeOptimizationData-Centric LearningDiffusion modelImage

🎯 What it does: Construct a scalable influence function framework in diffusion models, using (K)E-KFAC to implement data attribution via the Generalised Gauss-Newton approximation;

InfoGS: Efficient Structure-Aware 3D Gaussians via Lightweight Information Shaping

Yunchao Zhang (University of Hong Kong), Yanchao Yang (University of Hong Kong)

CodeObject DetectionSegmentationOptimizationContrastive LearningGaussian SplattingPoint Cloud

🎯 What it does: The mutual information (MI) shaping of the attribute decoding network in the 3D Gaussian Splatting (3DGS) model explicitly encodes the correlation between different Gaussians in the scene, enabling efficient object-level editing (such as segmentation, removal, recoloring, etc.) by fine-tuning network parameters.

Information Theoretic Text-to-Image Alignment

CHAO WANG, Pietro Michiardi (Eurecom)

CodeGenerationData SynthesisDiffusion modelImageText

🎯 What it does: Self-supervised fine-tuning of text-to-image diffusion models using mutual information (MI) from information theory to enhance the semantic consistency between generated images and prompts.

Injecting Universal Jailbreak Backdoors into LLMs in Minutes

Zhuowei Chen (Guangdong University of Foreign Studies), Shichao Pei (University of Massachusetts Boston)

CodeTransformerLarge Language ModelReinforcement LearningPrompt EngineeringText

🎯 What it does: The JailbreakEdit method is proposed, which allows for the injection of a universal jailbreak backdoor into a securely aligned LLM with a single model edit;

Innovative Thinking, Infinite Humor: Humor Research of Large Language Models through Structured Thought Leaps

Han Wang (Xi'an Jiaotong University), Hui Wang (Tencent QQ)

CodeGenerationOptimizationTransformerLarge Language ModelSupervised Fine-TuningReinforcement LearningPrompt EngineeringText

🎯 What it does: This paper proposes the LoL framework, which first enhances humor judgment and multi-hop reasoning abilities through instruction tuning, then constructs external knowledge using a teacher-student dialogue loop and GPT-4o reasoning, and finally achieves more creative humor generation through Direct Preference Optimization (DPO).

InsightBench: Evaluating Business Analytics Agents Through Multi-Step Insight Generation

Gaurav Sahu (ServiceNow Research), Issam H. Laradji

CodeTransformerLarge Language ModelAgentic AITabularBenchmarkFinance Related

🎯 What it does: Created InsightBench, an end-to-end data analysis benchmark with 100 enterprise business use cases, and proposed the AgentPoirot agent and LLaMA-3-Eval evaluation method;

Instance-dependent Early Stopping

Suqin Yuan (Sydney AI Centre, University of Sydney), Tongliang Liu (Sydney AI Centre, University of Sydney)

CodeObject DetectionSegmentationComputational EfficiencyImage

🎯 What it does: An instance-level early stopping method called IES is proposed, which determines whether an instance has been 'mastered' by monitoring the second-order difference of the loss for each sample, and stops backpropagation for that instance once it is deemed mastered, thereby reducing the computational load of training.

InstaRevive: One-Step Image Enhancement via Dynamic Score Matching

Yixuan Zhu (Tsinghua University), Jiwen Lu (Tsinghua University)

CodeRestorationGenerationSuper ResolutionDiffusion modelScore-based ModelImage

🎯 What it does: A single-step image enhancement framework based on dynamic score matching and text prompts (InstaRevive) is proposed.

Instruct-SkillMix: A Powerful Pipeline for LLM Instruction Tuning

Simran Kaur (Princeton University), Sanjeev Arora (Meta)

CodeGenerationData SynthesisTransformerLarge Language ModelSupervised Fine-TuningText

🎯 What it does: A fully automated INSTRUCT-SKILLMIX process is proposed, which uses a powerful LLM to first extract a list of 'skills' required for instruction execution, and then randomly combines these skills to generate diverse (instruction, response) training samples.

InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales

Zhepei Wei (University of Virginia), Yu Meng (University of Virginia)

CodeGenerationRetrievalExplainability and InterpretabilityTransformerLarge Language ModelSupervised Fine-TuningTextRetrieval-Augmented Generation

🎯 What it does: A retrieval-augmented generation framework called INSTRUCTRAG is proposed, which explicitly denoises the retrieved text and generates an interpretable answer reasoning process.

Integrative Decoding: Improving Factuality via Implicit Self-consistency

Yi Cheng (Hong Kong Polytechnic University), Wayne Xiong (Microsoft Research)

CodeGenerationTransformerLarge Language ModelPrompt EngineeringText

🎯 What it does: A new decoding strategy called Integrative Decoding (ID) is proposed, which implicitly integrates self-consistency during the decoding process to enhance the factuality of large language models.

Intelligence at the Edge of Chaos

Shiyang Zhang (Columbia University), David van Dijk (Yale University)

CodeTransformerLarge Language ModelTextTime Series

🎯 What it does: Pre-trained the GPT-2 model on data generated from elementary cellular automata (ECA) of varying complexity for next-token prediction, and evaluated its transfer performance on ARC-inspired reasoning tasks and Lichess elite chess move prediction tasks to explore the relationship between data complexity and model intelligence.

Intent3D: 3D Object Detection in RGB-D Scans Based on Human Intention

Weitai Kang (University of Illinois Chicago), Yan Yan (University of Illinois Chicago)

CodeObject DetectionLarge Language ModelContrastive LearningTextPoint Cloud

🎯 What it does: This paper proposes a 3D intent localization task, constructs the Intent3D dataset, and designs the IntentNet model based on intent understanding, candidate box matching, and cascading adaptive learning, achieving automatic detection of targets in 3D scenes based on free-text intents.

Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence

Weize Chen (Tsinghua University), Maosong Sun (Tsinghua University)

CodeLarge Language ModelAgentic AITextBenchmark

🎯 What it does: This paper proposes the Internet of Agents (IoA), a distributed multi-agent collaboration framework based on an instant messaging architecture, supporting heterogeneous third-party agents, cross-device collaboration, and dynamic team and dialogue process management.

Interpretable Vision-Language Survival Analysis with Ordinal Inductive Bias for Computational Pathology

Pei Liu (University of Electronic Science and Technology of China), Mao Ye (University of Electronic Science and Technology of China)

CodeExplainability and InterpretabilityTransformerVision Language ModelImageBiomedical Data

🎯 What it does: This study proposes a survival analysis framework for pathological slides based on a visual-language model, VLSA, which utilizes language-encoded prognostic priors to assist multi-instance aggregation for predicting survival risk in panoramic slides.

Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations

Nicholas Jiang, Yossi Gandelsman (University of California)

CodeSegmentationExplainability and InterpretabilityTransformerVision Language ModelImage

🎯 What it does: The paper decodes the intermediate image representations in visual-language models (VLM) to a language vocabulary, using their internal confidence to distinguish between real objects and hallucinations, and suppresses hallucinations through linear orthogonalization of image embeddings (PROJECTAWAY);

IntersectionZoo: Eco-driving for Benchmarking Multi-Agent Contextual Reinforcement Learning

Vindula Jayawardana (Massachusetts Institute of Technology), Cathy Wu (Massachusetts Institute of Technology)

CodeAutonomous DrivingReinforcement LearningTabularTime SeriesBenchmark

🎯 What it does: A multi-agent contextual reinforcement learning benchmark package, IntersectionZoo, based on real intersections has been established to evaluate the generalization of eco-driving algorithms.

Intervening Anchor Token: Decoding Strategy in Alleviating Hallucinations for MLLMs

Feilong Tang (Hong Kong University of Science and Technology), Ser-Nam Lim (University of Central Florida)

CodeGenerationData SynthesisTransformerLarge Language ModelVision Language ModelTextMultimodality

🎯 What it does: This paper explores the causes of hallucination phenomena in multimodal large language models (MLLMs) and proposes a decoding strategy called TAME (Dynamic Intervention of Anchor Tag Propagation) to mitigate the hallucination problem.

Intrinsic Dimension Correlation: uncovering nonlinear connections in multimodal representations

Lorenzo Basile (University of Trieste), Alex Rodriguez (University of Trieste)

CodeAnomaly DetectionRepresentation LearningImageTextMultimodality

🎯 What it does: A nonlinear correlation measure based on intrinsic dimensionality, ID Cor, is proposed to detect nonlinear associations between high-dimensional datasets and the hidden layers of neural networks.

Intrinsic User-Centric Interpretability through Global Mixture of Experts

Vinitra Swamy (Γ‰cole Polytechnique FΓ©dΓ©rale de Lausanne), Tanja KΓ€ser (Γ‰cole Polytechnique FΓ©dΓ©rale de Lausanne)

CodeExplainability and InterpretabilityLarge Language ModelMixture of ExpertsTextTabularTime SeriesBiomedical Data

🎯 What it does: We propose InterpretCC, an interpretable neural network with adaptive sparse feature/concept gating and expert mixture, providing locally interpretable and easily operable prediction explanations.

Inverse Constitutional AI: Compressing Preferences into Principles

Arduin Findeis (University of Cambridge), Robert D. Mullins

CodeCompressionExplainability and InterpretabilityTransformerLarge Language ModelText

🎯 What it does: Proposes the Inverse Constitutional AI (ICAI) method, which compresses preference data into an interpretable set of natural language principles (the constitution) and reconstructs the original preferences through LLM.

InversionGNN: A Dual Path Network for Multi-Property Molecular Optimization

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

CodeOptimizationDrug DiscoveryGraph Neural NetworkGraph

🎯 What it does: A dual-path graph neural network called InversionGNN is proposed, which learns chemical knowledge through predictive paths and utilizes reverse generation paths for molecular optimization via gradients, thereby seeking Pareto optimal solutions in multi-objective molecular optimization.

InvestESG: A multi-agent reinforcement learning benchmark for studying climate investment as a social dilemma

Xiaoxuan Hou (University of Washington), Natasha Jaques (Google Deepmind)

CodeReinforcement LearningTabularBenchmarkFinance Related

🎯 What it does: A multi-agent reinforcement learning benchmark, InvestESG, has been designed and implemented to simulate the long-term interactions between companies and investors under mandatory ESG disclosure policies, and to study the incentive effects of this policy on corporate emission reduction investments.

Investigating the Pre-Training Dynamics of In-Context Learning: Task Recognition vs. Task Learning

Xiaolei Wang (Renmin University of China), Ji-Rong Wen (Renmin University of China)

CodeClassificationTransformerLarge Language ModelText

🎯 What it does: This study investigates the competitive relationship between task recognition (TR) and task learning (TL) during the pre-training phase of large language models, and quantifies their impact on in-context learning (ICL) performance using metrics.

IRIS: LLM-Assisted Static Analysis for Detecting Security Vulnerabilities

Ziyang Li (University of Pennsylvania), Mayur Naik (University of Pennsylvania)

CodeAI Code AssistantTransformerLarge Language ModelPrompt EngineeringText

🎯 What it does: Combining large language models (LLM) with static analysis for vulnerability detection across entire Java projects, automatically inferring taint specifications and filtering false positives through contextual analysis.

Is In-Context Learning Sufficient for Instruction Following in LLMs?

Hao Zhao (Γ‰cole Polytechnique FΓ©dΓ©rale de Lausanne), Nicolas Flammarion (Γ‰cole Polytechnique FΓ©dΓ©rale de Lausanne)

CodeTransformerLarge Language ModelSupervised Fine-TuningPrompt EngineeringTextBenchmark

🎯 What it does: This study investigates the effect of in-context learning (ICL) on instruction alignment for large language models and conducts a systematic comparison with traditional instruction fine-tuning (IFT).

Iterative Substructure Extraction for Molecular Relational Learning with Interactive Graph Information Bottleneck

Shuai Zhang (University of Science and Technology of China), Yang Wang (University of Science and Technology of China)

CodeDrug DiscoveryGraph Neural NetworkContrastive LearningGraph

🎯 What it does: An iterative substructure extraction framework (ISE) and an interactive graph information bottleneck (IGIB) are proposed, which can accurately extract core interactive substructures from molecular pairs and perform molecular relationship learning.

IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation

Xinchen Zhang (Tsinghua University), Bin CUI

CodeGenerationData SynthesisReinforcement LearningDiffusion modelImageTextMultimodality

🎯 What it does: A multi-model ensemble preference dataset is constructed, and an IterComp iterative feedback learning framework is proposed, utilizing a reward model and a benchmark diffusion model for closed-loop co-evolution to enhance the text-to-image combination generation capability.

IterGen: Iterative Semantic-aware Structured LLM Generation with Backtracking

Shubham Ugare (University of Illinois Urbana-Champaign), Sasa Misailovic (University of Illinois Urbana-Champaign)

CodeGenerationSafty and PrivacyTransformerLarge Language ModelText

🎯 What it does: Designed the ITERGEN framework, achieving forward and backward LLM generation control based on grammatical symbols, supporting semantic constraints and backtracking.

IV-mixed Sampler: Leveraging Image Diffusion Models for Enhanced Video Synthesis

Shitong Shao (Hong Kong University of Science and Technology), Zeke Xie (Baidu Inc.)

CodeGenerationData SynthesisDiffusion modelVideoOrdinary Differential Equation

🎯 What it does: A training-free sampling algorithm called IV-Mixed Sampler is designed, which enhances the visual quality of video diffusion models (VDM) by utilizing high-quality sampling from image diffusion models (IDM), and ensures temporal consistency through the alternating use of DDIM and DDIM-Inversion.

Jailbreaking as a Reward Misspecification Problem

Zhihui Xie (University of Hong Kong), Lingpeng Kong (University of Hong Kong)

CodeAdversarial AttackReinforcement Learning from Human FeedbackTransformerLarge Language ModelReinforcement LearningPrompt EngineeringText

🎯 What it does: Proposes viewing LLM vulnerabilities as a reward mis-specification problem, defines ReGap to measure reward mis-specification, and designs the ReMiss automated red team attack system based on this;

Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks

Maksym Andriushchenko (Γ‰cole Polytechnique FΓ©dΓ©rale de Lausanne), Nicolas Flammarion (Γ‰cole Polytechnique FΓ©dΓ©rale de Lausanne)

CodeSafty and PrivacyAdversarial AttackTransformerLarge Language ModelPrompt EngineeringText

🎯 What it does: The study demonstrates that even the latest safety-aligned large language models (LLMs) remain highly vulnerable to simple adaptive jailbreak attacks, and proposes a set of adaptive attack frameworks utilizing techniques such as prompt templates, random search, self-transfer, and pre-filling.

Joint Graph Rewiring and Feature Denoising via Spectral Resonance

Jonas LinkerhÀgner (University of Basel), Ivan Dokmanić (University of Basel)

CodeClassificationOptimizationGraph Neural NetworkGraph

🎯 What it does: This paper proposes a joint algorithm for graph structure rearrangement and feature denoising (JDR), which enhances the performance of downstream graph neural networks in node classification tasks by aligning the principal spectral spaces of the graph adjacency matrix and the node feature matrix.

JPEG Inspired Deep Learning

Ahmed H. Salamah (University of Waterloo), EN-HUI YANG

CodeClassificationCompressionAdversarial AttackImage

🎯 What it does: A new deep learning framework called JPEG-DL is proposed, which adds a trainable JPEG compression layer in front of any base deep neural network (DNN) architecture to enhance deep learning performance.

JudgeLM: Fine-tuned Large Language Models are Scalable Judges

Lianghui Zhu (Beijing Academy of Artificial Intelligence), Xinlong Wang (Beijing Academy of Artificial Intelligence)

CodeTransformerLarge Language ModelSupervised Fine-TuningText

🎯 What it does: A scalable language model evaluator, JudgeLM, is proposed for efficiently and accurately assessing the responses of large language models in open-ended tasks.

Jump Your Steps: Optimizing Sampling Schedule of Discrete Diffusion Models

Yong-Hyun Park, Yuki Mitsufuji (Sony Group Corporation)

CodeData SynthesisOptimizationComputational EfficiencyDiffusion modelImageText

🎯 What it does: A sampling schedule optimization method called Jump Your Steps (JYS) is proposed to improve the sampling quality and speed of the Discrete Diffusion Model (DDM) without incurring additional computational costs.

K-HALU: Multiple Answer Korean Hallucination Benchmark for Large Language Models

Jaehyung Seo (Korea University), Heuiseok Lim (Korea University)

CodeLarge Language ModelTextBenchmark

🎯 What it does: A large language model hallucination detection benchmark for Korean, K-HALU, is proposed, which includes multiple answer types and temporal consistency checks.

KAA: Kolmogorov-Arnold Attention for Enhancing Attentive Graph Neural Networks

Taoran Fang (Zhejiang University), Yang Yang (Zhejiang University)

CodeGraph Neural NetworkGraph

🎯 What it does: Proposed the Kolmogorov-Arnold Attention (KAA), introducing the Kolmogorov-Arnold Network (KAN) into the scoring function of attention graph neural networks, unifying and enhancing their expressive capability.

KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models

Fan Wang (Hong Kong University of Science and Technology), Jing Tang (Hong Kong University of Science and Technology)

CodeTransformerLarge Language ModelSupervised Fine-TuningText

🎯 What it does: This paper proposes a new parameter-efficient fine-tuning method called KaSA, which utilizes knowledge-aware singular value decomposition to dynamically activate task-related model knowledge.

KBLaM: Knowledge Base augmented Language Model

Xi Wang (Johns Hopkins University), James Hensman (Microsoft Research)

CodeTransformerLarge Language ModelSupervised Fine-TuningTextRetrieval-Augmented Generation

🎯 What it does: This study investigates a method to convert external knowledge bases into continuous key-value vectors without modifying the weights of the LLM, and injects these vectors into the LLM through rectangular attention, achieving scalable and dynamically updatable knowledge enhancement.

Kernel-based Optimally Weighted Conformal Time-Series Prediction

Jonghyeok Lee (Georgia Institute of Technology), Yao Xie (Georgia Institute of Technology)

CodeOptimizationTime SeriesFinance Related

🎯 What it does: An adaptive weighted confidence interval method for time series, KOWCPI, is proposed, which constructs conditional confidence intervals using the reweighted Nadaraya-Watson (RNW) estimator for quantile regression.

KGARevion: An AI Agent for Knowledge-Intensive Biomedical QA

Xiaorui Su (Harvard University), Marinka Zitnik (Harvard University)

CodeTransformerLarge Language ModelSupervised Fine-TuningAgentic AITextBiomedical DataBenchmark

🎯 What it does: This paper proposes a KG-based LLM agentβ€”KGAREVION, which can first generate triples related to a question using LLM, then verify and correct these triples on a knowledge graph, ultimately providing reliable answers.

Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks

Michael Matthews (FLAIR University of Oxford), Jakob Nicolaus Foerster

CodeRobotic IntelligenceTransformerReinforcement LearningAgentic AISequentialPhysics Related

🎯 What it does: This paper presents Kinetixβ€”a 2D physics simulation framework based on Jax2D, which trains general RL agents using tens of millions of procedurally generated tasks, achieving zero-shot generalization and fine-tuning improvements on 74 manually designed benchmark tasks.

KinPFN: Bayesian Approximation of RNA Folding Kinetics using Prior-Data Fitted Networks

Dominik Scheuer (University of Freiburg), Frank Hutter (University of Freiburg)

CodeOptimizationComputational EfficiencyNeural Architecture SearchTransformerSequentialBiomedical Data

🎯 What it does: A deep learning framework based on the Prior Data Fitting Network (KinPFN) has been developed for the rapid approximation of the cumulative distribution function (CDF) of the first passage time (FPT) of RNA folding.

KiVA: Kid-inspired Visual Analogies for Testing Large Multimodal Models

Eunice Yiu (University of California), Kate Saenko (Boston University)

CodeRecognitionGenerationTransformerLarge Language ModelPrompt EngineeringVision Language ModelImageMultimodalityBenchmark

🎯 What it does: A visual analogy benchmark called KiVA based on real everyday objects is proposed, and it is used to evaluate the capabilities of large multimodal models (LMM) in visual analogy reasoning, comparing their performance with that of children aged three to five and adults.

KLay: Accelerating Arithmetic Circuits for Neurosymbolic AI

Jaron Maene (KU Leuven), Pedro Zuidberg Dos Martires (Γ–rebro University)

CodeComputational EfficiencyGraph

🎯 What it does: This paper proposes KLAY, a data structure for arithmetic circuits based on layered indexing and hashing, which significantly accelerates the backward and forward propagation of neural symbolic AI.

Knowing Your Target: Target-Aware Transformer Makes Better Spatio-Temporal Video Grounding

Xin Gu (University of Chinese Academy of Sciences), Libo Zhang (Institute of Software Chinese Academy of Sciences)

CodeRecognitionObject DetectionTransformerVideoText

🎯 What it does: This paper proposes a Target-Aware Spatial-Temporal Video Grounding (TA-STVG) model that enhances spatiotemporal video localization accuracy by directly utilizing target features from both video and text to generate object queries.

Knowledge Entropy Decay during Language Model Pretraining Hinders New Knowledge Acquisition

Jiyeon Kim (Korea Advanced Institute of Science and Technology), Minjoon Seo (Korea Advanced Institute of Science and Technology)

CodeTransformerLarge Language ModelTextBiomedical Data

🎯 What it does: This study investigates the changes in knowledge entropy during the pre-training process of large language models and its impact on the acquisition of new knowledge and forgetting in continual learning, proposing to enhance the model's plasticity by activating inactive memory vectors.

KooNPro: A Variance-Aware Koopman Probabilistic Model Enhanced by Neural Process for Time Series Forecasting

Ronghua Zheng (Fudan University), Weiyang Ding (Fudan University)

CodeAnomaly DetectionTime Series

🎯 What it does: A probabilistic time series forecasting framework KooNPro is proposed, which combines the variational Koopman model with Neural Process to capture local dynamics using variance-aware continuous spectra (pseudo-spectra) and global dynamics using Neural Process.

Kronecker Mask and Interpretive Prompts are Language-Action Video Learners

Yang JingYi, Hui Li (University of Science and Technology of China)

CodeClassificationRecognitionTransformerLarge Language ModelPrompt EngineeringContrastive LearningVideo

🎯 What it does: In the video action recognition task, the CLAVER model is proposed, which realigns CLIP to action behaviors and verbs through Kronecker mask temporal attention and interpretive prompts.

L3Ms β€” Lagrange Large Language Models

Guneet S. Dhillon (University of Oxford), Alex Smola (Boson AI)

CodeOptimizationTransformerLarge Language ModelSupervised Fine-TuningReinforcement LearningText

🎯 What it does: This paper proposes a method that unifies supervised fine-tuning and alignment into a constrained optimization framework, and based on this, trains L3M (Lagrange Large Language Models) to meet application-specific constraints.

LancBiO: Dynamic Lanczos-aided Bilevel Optimization via Krylov Subspace

Yan Yang (Academy of Mathematics and Systems Science Chinese Academy of Sciences University of Chinese Academy of Sciences), Ya-xiang Yuan (Academy of Mathematics and Systems Science Chinese Academy of Sciences)

CodeOptimizationHyperparameter Search

🎯 What it does: A new bi-level optimization framework called LancBiO is proposed, which utilizes Krylov subspace and the Lanczos process to dynamically construct a low-dimensional subspace for efficiently approximating the Hessian inverse-vector product, thereby improving the accuracy of the hypergradient estimation.

Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning

Haque Ishfaq (Mila), Doina Precup (Mila)

CodeRobotic IntelligenceReinforcement LearningDiffusion modelSequential

🎯 What it does: A new model-free continuous control reinforcement learning algorithm LSAC is proposed, which enhances critic learning by approximating Thompson sampling through Langevin Monte Carlo sampling, thereby achieving efficient exploration and improving sample efficiency.

Language Model Alignment in Multilingual Trolley Problems

Zhijing Jin (University of Toronto), Bernhard SchΓΆlkopf (Max Planck Institute for Intelligent Systems)

CodeTransformerLarge Language ModelPrompt EngineeringText

🎯 What it does: This paper constructs a cross-linguistic dataset for the trolley problem, MULTITP, to evaluate the moral alignment of 19 large language models across more than 100 languages.

Language Models Are Implicitly Continuous

Samuele Marro (University of Oxford), Michael J. Wooldridge

CodeTransformerLarge Language ModelText

🎯 What it does: This paper views large-scale language models (LLMs) as implicit continuous-time functions and proposes a Continuous Causal Transformer (CCT) framework that does not alter the original weights. The framework is experimentally validated on trained LLMs to assess the model's perception of temporal continuity and spatial interpolation.

Language Models Need Inductive Biases to Count Inductively

Yingshan Chang (Carnegie Mellon University), Yonatan Bisk (Carnegie Mellon University)

CodeRecurrent Neural NetworkTransformerSequential

🎯 What it does: This study investigates the learning and reasoning capabilities of language models in counting tasks, particularly in out-of-distribution (OOD) scenarios with inconsistent training lengths and vocabularies; it compares the performance of Transformer models with different position encodings (PE) and various RNN variants by designing multiple counting tasks (vanilla, helper token, shifted start, modular, selective, etc.).

LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding

Doohyuk Jang (Korea Advanced Institute of Science and Technology), Eunho Yang (Korea Advanced Institute of Science and Technology)

CodeGenerationComputational EfficiencyTransformerLarge Language ModelImageText

🎯 What it does: This study explores how to combine visual autoregressive models like LlamaGen with the inference acceleration technology of EAGLE-2, achieving significant inference speed improvements by introducing a relaxation of acceptable conditions (LANTERN).

Large (Vision) Language Models are Unsupervised In-Context Learners

Artyom Gadetsky (Swiss Federal Institute of Technology), Maria Brbic

CodeTransformerLarge Language ModelReinforcement LearningVision Language ModelImageTextMultimodality

🎯 What it does: Proposes a joint reasoning framework to achieve unsupervised task adaptation.

Large Convolutional Model Tuning via Filter Subspace

Wei Chen (Purdue University), Qiang Qiu (Purdue University)

CodeClassificationGenerationConvolutional Neural NetworkDiffusion modelImage

🎯 What it does: This paper proposes a parameter-efficient fine-tuning method based on convolutional filter subspaces, adjusting only the filter atoms while keeping the channel mixing coefficients unchanged, thereby adapting to downstream tasks while maintaining the prior capabilities of large models.

Large Language Models can Become Strong Self-Detoxifiers

Ching-Yun Ko (IBM Research), Luca Daniel (Massachusetts Institute of Technology)

CodeTransformerLarge Language ModelText

🎯 What it does: Proposed the SASA self-discipline autoregressive sampling method, using internal representations to achieve LLM detoxification.

Large Language Models Meet Symbolic Provers for Logical Reasoning Evaluation

Chengwen Qi (Beihang University), Conghui He (Shanghai Artificial Intelligence Laboratory)

CodeTransformerLarge Language ModelSupervised Fine-TuningTextChain-of-Thought

🎯 What it does: ProverGen framework is proposed, which combines LLM and symbolic provers to automatically generate a high-quality FOL reasoning dataset called ProverQA.

Large Language Models Often Say One Thing and Do Another

Ruoxi Xu (University of Chinese Academy of Sciences), Yingfei Sun (University of Chinese Academy of Sciences)

CodeLarge Language ModelSupervised Fine-TuningTextBenchmarkChain-of-Thought

🎯 What it does: A benchmark called 'Word and Behavior Consistency Test' (WDCT) is proposed and implemented to evaluate the consistency between the statements and actual behaviors of large language models in four domains: opinions, non-ethical values, ethical values, and theory. The causal relationship between word and behavior consistency is explored through alignment experiments.

Large Scale Knowledge Washing

Yu Wang (University of California San Diego), Julian McAuley (University of Illinois Urbana-Champaign)

CodeTransformerLarge Language ModelText

🎯 What it does: Proposes a large-scale knowledge washing problem and designs an optimization objective on the MLP layer of LLMs to achieve seamless deletion of specified knowledge while maintaining reasoning ability.

Large-scale and Fine-grained Vision-language Pre-training for Enhanced CT Image Understanding

Zhongyi Shui (DAMO Academy, Alibaba Group), Ling Zhang (DAMO Academy, Alibaba Group)

CodeClassificationSegmentationGenerationTransformerVision Language ModelContrastive LearningImageTextMultimodalityComputed Tomography

🎯 What it does: This paper proposes a fine-grained visual-language pre-training model fVLM, which achieves precise alignment and pre-training of CT images and reports at the anatomical level through anatomical structure segmentation and report decomposition.

LASeR: Towards Diversified and Generalizable Robot Design with Large Language Models

Junru Song (Shanghai Jiao Tong University), Feifei Wang (Renmin University of China)

CodeRobotic IntelligenceTransformerLarge Language ModelReinforcement LearningPrompt EngineeringMultimodality

🎯 What it does: This paper studies a large language model (LLM)-driven evolutionary search framework called LASeR for the automated design of soft robots (VSR);

Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation

Yiming Wang (Shanghai Jiao Tong University), Rui Wang (Shanghai Jiao Tong University)

CodeTransformerLarge Language ModelText

🎯 What it does: This paper proposes the Chain-of-Embedding (CoE) method, achieving output-free and label-free self-evaluation of LLMs by directly utilizing all hidden states during the model inference process.

Lawma: The Power of Specialization for Legal Annotation

Ricardo Dominguez-Olmedo (Max Planck Institute for Intelligent Systems), Michael Livermore (University of Virginia School of Law)

CodeClassificationTransformerLarge Language ModelSupervised Fine-TuningPrompt EngineeringTextBenchmarkChain-of-Thought

🎯 What it does: A legal text classification task set, CaselawQA, consisting of 260 tasks based on data from the U.S. Supreme Court and appellate courts, was constructed, and the performance of large language models and the self-developed Lawma series models was systematically evaluated.

LayerDAG: A Layerwise Autoregressive Diffusion Model for Directed Acyclic Graph Generation

Mufei Li (Georgia Institute of Technology), Pan Li (Georgia Institute of Technology)

CodeGenerationData SynthesisGraph Neural NetworkDiffusion modelGraph

🎯 What it does: LayerDAG constructs a layer-wise autoregressive diffusion model to generate DAGs by treating the DAG as a hierarchical sequence of bipartite graphs.

Layerwise Recurrent Router for Mixture-of-Experts

Zihan Qiu (Alibaba Group), Jie Fu (Shanghai AI Lab)

CodeOptimizationComputational EfficiencyRecurrent Neural NetworkTransformerSupervised Fine-TuningMixture of ExpertsTextSequential

🎯 What it does: This paper proposes a hierarchical recursive router RMoE, which utilizes GRU to share routing information between different Transformer layers, thereby improving the parameter efficiency and overall performance of Mixture-of-Experts.

LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics

Thomas Robert (Institut Polytechnique de Paris), Dan Alistarh (Institute of Science and Technology Austria)

CodeOptimizationTransformerLarge Language ModelText

🎯 What it does: An efficient memory adaptive optimizer LDAdam is proposed, which can perform Adam-level optimization in low-dimensional subspaces while continuously exploring the full parameter space during training.

LeanAgent: Lifelong Learning for Formal Theorem Proving

Adarsh Kumarappan (California Institute of Technology), Anima Anandkumar (University of Wisconsin)

CodeTransformerLarge Language ModelRetrieval-Augmented Generation

🎯 What it does: This paper presents LeanAgent, a lifelong learning framework for formal theorem proving that can continuously expand knowledge across multiple mathematical libraries and generate new formal proofs.