arXivSub Start free trial

ICML 2025 Papers with Code β€” Page 6

International Conference on Machine Learning Β· 722 papers

POROver: Improving Safety and Reducing Overrefusal in Large Language Models with Overgeneration and Preference Optimization

Batuhan K. Karaman (Cornell University), Xia Song (Microsoft)

CodeOptimizationSafty and PrivacyTransformerLarge Language ModelSupervised Fine-TuningText

🎯 What it does: This paper proposes the POROver (Preference Optimization for Reducing Overrefusal) strategy by using more advanced teacher models (such as GPT-4o) for overgeneration of general and toxic instructions, aiming to reduce the overrefusal rate of large language models while maintaining high safety.

PPDiff: Diffusing in Hybrid Sequence-Structure Space for Protein-Protein Complex Design

Zhenqiao Song (Carnegie Mellon University), Martin Renqiang Min (NEC Laboratories America)

CodeDrug DiscoveryProtein Structure PredictionGraph Neural NetworkTransformerDiffusion modelBiomedical DataBenchmark

🎯 What it does: A diffusion model called PPDiff is proposed for the joint design of protein ligand sequences and structures, aimed at generating high-affinity binding proteins for any protein target.

Preconditioned Riemannian Gradient Descent Algorithm for Low-Multilinear-Rank Tensor Completion

Yuanwei Zhang (Shanghai Jiao Tong University), Jian-Feng Cai (Hong Kong University of Science and Technology)

CodeOptimizationVideo

🎯 What it does: This paper addresses the low multilinear rank tensor completion problem and proposes a Preconditioned Riemannian Gradient Descent (PRGD) algorithm, which utilizes a data-driven Riemannian metric to accelerate convergence while maintaining approximately optimal sampling complexity.

Prediction models that learn to avoid missing values

Lena Stempfle (Chalmers University of Technology), Fredrik D. Johansson (Chalmers University of Technology)

CodeTabularAlzheimer's Disease

🎯 What it does: A missing value avoidance (MA) machine learning framework is proposed, which actively encourages decision trees, sparse linear models, and tree ensemble models to minimize reliance on missing features during prediction through a penalty term, while maintaining or improving predictive performance.

Prediction via Shapley Value Regression

Amr Alkhatib (Orebro University), Michalis Vazirgiannis (Ecole Polytechnique)

CodeExplainability and InterpretabilityComputational EfficiencyConvolutional Neural NetworkImageTabular

🎯 What it does: A method called ViaSHAP is proposed, which embeds the calculation of Shapley values into model training, allowing predictions to be directly obtained by summing Shapley values, while no additional post-processing is required during inference.

Predictive Data Selection: The Data That Predicts Is the Data That Teaches

KaShun SHUM, Junxian He (Hong Kong University of Science and Technology)

CodeComputational EfficiencyData-Centric LearningTransformerLarge Language ModelText

🎯 What it does: This paper proposes a data selection method called PRESELECT, which selects the most helpful data for learning by evaluating the correlation between the loss of text on different pre-trained models and the ranking of downstream task performance.

Preference Learning for AI Alignment: a Causal Perspective

Kasia Kobalczyk, Mihaela van der Schaar (University of Cambridge)

CodeRecommendation SystemReinforcement Learning from Human FeedbackLarge Language ModelReinforcement LearningText

🎯 What it does: Proposes to view preference learning as a causal inference problem, exploring causal assumptions such as user goal confounding and potential treatment variables in LLM alignment;

Privacy-Shielded Image Compression: Defending Against Exploitation from Vision-Language Pretrained Models

Xuelin Shen (Shenzhen University), Wenhan Yang (Pengcheng Laboratory)

CodeCompressionOptimizationSafty and PrivacyAdversarial AttackVision Language ModelAuto EncoderImageText

🎯 What it does: The framework PSIC implements privacy protection during the image compression phase, generating a bitstream that can be decoded on demand into an encrypted version and a full version.

Private Federated Learning using Preference-Optimized Synthetic Data

Charlie Hou (Carnegie Mellon University), Giulia Fanti (Carnegie Mellon University)

CodeOptimizationFederated LearningSafty and PrivacyTransformerLarge Language ModelReinforcement LearningTextBenchmark

🎯 What it does: A private federated learning method based on policy optimization, POPri, is proposed, which utilizes LLM to fine-tune synthetic data generation based on client feedback as rewards.

ProDiff: Prototype-Guided Diffusion for Minimal Information Trajectory Imputation

Tianci Bu (National University of Defense Technology), Xin Lu

CodeGenerationData SynthesisDiffusion modelTime SeriesSequential

🎯 What it does: A method called ProDiff is proposed, which can complete trajectory missing point interpolation using only endpoint information. It utilizes prototype learning and diffusion models to achieve trajectory reconstruction.

Progressive Tempering Sampler with Diffusion

Severi Rissanen (Aalto University), JosΓ© Miguel HernΓ‘ndez-Lobato (University of Cambridge)

CodeGenerationData SynthesisOptimizationDiffusion modelMultimodalityStochastic Differential EquationOrdinary Differential Equation

🎯 What it does: This paper proposes a sampler that combines Parallel Tempering with diffusion models, called the Progressive Tempering Sampler with Diffusion (PTSD), which generates samples from a high-temperature model to a low-temperature model through temperature guidance.

Prompt-to-Leaderboard: Prompt-Adaptive LLM Evaluations

Evan Frick (University of California), Ion Stoica (University of California)

CodeTransformerLarge Language ModelPrompt EngineeringTextBenchmark

🎯 What it does: This paper proposes the P2L method, which trains a large language model to directly output Bradley-Terry coefficients after receiving natural language prompts, generating a model ranking for each prompt to achieve fine-grained evaluation.

ProofAug: Efficient Neural Theorem Proving via Fine-grained Proof Structure Analysis

Haoxiong Liu (Tsinghua University), Andrew C Yao (Shanghai Qi Zhi Institute)

CodeLarge Language ModelPrompt Engineering

🎯 What it does: A fine-grained proof structure analysis method named ProofAug is proposed, which utilizes complete proofs generated by LLM and extracts repairable proof structures through Maximum Compatible Semi-Proofs (MCSP), combining ATP and built-in proof methods to achieve efficient neural theorem proving.

Propagate and Inject: Revisiting Propagation-Based Feature Imputation for Graphs with Partially Observed Features

Daeho Um (Samsung Electronics), Seulki Park (University of Michigan)

CodeGraph Neural NetworkGraph

🎯 What it does: This study investigates the problem of propagative imputation of missing features in graph data and proposes a new method, FISF, which addresses performance degradation caused by low-variance channels by injecting synthetic features.

Provably Cost-Sensitive Adversarial Defense via Randomized Smoothing

Yuan Xin (CISPA Helmholtz Center for Information Security), Xiao Zhang (CISPA Helmholtz Center for Information Security)

CodeOptimizationAdversarial AttackConvolutional Neural NetworkImageBiomedical Data

🎯 What it does: A provably cost-sensitive adversarial robustness defense framework based on randomized smoothing is proposed, providing a cost-sensitive certified radius and training method.

Provably Near-Optimal Federated Ensemble Distillation with Negligible Overhead

Won-Jun Jang (Korea Advanced Institute of Science and Technology), Si-Hyeon Lee (Korea Advanced Institute of Science and Technology)

CodeFederated LearningKnowledge DistillationConvolutional Neural NetworkGenerative Adversarial NetworkImage

🎯 What it does: Proposes the FedGO algorithm, which uses a GAN discriminator to achieve approximately optimal federated ensemble distillation, addressing the client heterogeneity issue.

Puzzle: Distillation-Based NAS for Inference-Optimized LLMs

Akhiad Bercovich, Ran El-Yaniv

CodeOptimizationComputational EfficiencyKnowledge DistillationNeural Architecture SearchTransformerLarge Language ModelText

🎯 What it does: This paper studies a distillation-based NAS framework called Puzzle, which can generate sub-models that efficiently infer on a single NVIDIA H100 GPU while maintaining nearly the same performance as the original large model (e.g., Llama-70B).

PyTDC: A multimodal machine learning training, evaluation, and inference platform for biomedical foundation models

Alejandro Velez-Arce (Harvard University), Marinka Zitnik (Harvard University)

CodeDrug DiscoveryGraph Neural NetworkTransformerMultimodalityBiomedical DataBenchmark

🎯 What it does: A PyTDC platform has been constructed, providing multimodal single-cell data retrieval, training, evaluation, and inference, and for the first time offering benchmarks and tools for single-cell drug-target naming tasks;

Q-VDiT: Towards Accurate Quantization and Distillation of Video-Generation Diffusion Transformers

Weilun Feng (Institute of Computing Technology, Chinese Academy of Sciences), Michele Magno (ETH Zurich)

CodeGenerationKnowledge DistillationTransformerDiffusion modelVideo

🎯 What it does: This paper proposes a quantization framework Q-VDiT specifically for video generation diffusion Transformers (DiT), addressing the issues of quantization information loss and spatiotemporal consistency loss.

QMamba: On First Exploration of Vision Mamba for Image Quality Assessment

Fengbin Guan (University of Science and Technology of China), Zhibo Chen (University of Science and Technology of China)

CodeDomain AdaptationTransformerPrompt EngineeringImage

🎯 What it does: A framework for image quality assessment based on Mamba, QMamba, is proposed, modeling task-specific, general, and transferable IQA.

QoS-Efficient Serving of Multiple Mixture-of-Expert LLMs Using Partial Runtime Reconfiguration

HamidReza Imani (George Washington University), Tarek El-Ghazawi (George Washington University)

CodeTransformerLarge Language ModelMixture of ExpertsText

🎯 What it does: A MoE LLM system has been built to efficiently serve multiple models on a single GPU, utilizing expert similarity to merge shared memory and dynamically replace non-expert layers at runtime to reduce memory usage.

QuEST: Stable Training of LLMs with 1-Bit Weights and Activations

Andrei Panferov (International Scientific and Technological Academy), Dan Alistarh (International Scientific and Technological Academy)

CodeTransformerLarge Language ModelText

🎯 What it does: A quantization-aware training method named QuEST is proposed, which can stably train large language models with weights and activations ranging from 1-bit to 4-bit.

R3DM: Enabling Role Discovery and Diversity Through Dynamics Models in Multi-agent Reinforcement Learning

Harsh Goel (University of Texas at Austin), Sandeep P. Chinchali (Honda Research Institute)

CodeReinforcement LearningContrastive LearningTabularBenchmark

🎯 What it does: Achieve multi-agent collaborative training through role learning and dynamic models to enhance coordination.

RAGGED: Towards Informed Design of Scalable and Stable RAG Systems

Jennifer Hsia (Carnegie Mellon University), Graham Neubig (Carnegie Mellon University)

CodeGenerationRetrievalTransformerPrompt EngineeringTextRetrieval-Augmented Generation

🎯 What it does: Proposes the RAGGED framework for systematic evaluation of retrieval-augmented generation systems under different retrieval depths, reader models, retrievers, and noise conditions.

Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving Testing

Han Jiang (Tongji University), Xing Xie (Microsoft Research Asia)

CodeGenerationTransformerLarge Language ModelText

🎯 What it does: This study proposes an evaluation framework based on Generative Evolutionary Testing (GETA) for dynamically measuring the value and ethical alignment levels of large language models (LLMs).

Random Policy Evaluation Uncovers Policies of Generative Flow Networks

Haoran He (Hong Kong University of Science and Technology), Ling Pan (Hong Kong University of Science and Technology)

CodeGenerationReinforcement LearningFlow-based ModelSequential

🎯 What it does: The researchers view the training of Generative Flow Networks (GFlowNets) as flow iteration in dynamic programming, discovering that it is equivalent to the value evaluation of random policies in tree structures or DAGs that satisfy path invariance. They propose the Rectified Random Policy Evaluation (RPE) algorithm based on random policy evaluation, achieving the same reward matching effect as GFlowNets.

Random Registers for Cross-Domain Few-Shot Learning

Shuai Yi (Huazhong University of Science and Technology), Ruixuan Li (Huazhong University of Science and Technology)

CodeDomain AdaptationTransformerPrompt EngineeringImage

🎯 What it does: In cross-domain few-shot learning, the authors found that using random registers instead of learnable prompts can significantly improve the cross-domain generalization performance of Vision Transformers. They proposed the REAP method, which enhances attention perturbation by randomly replacing clustering blocks in the image semantic region, resulting in a flatter loss landscape.

Ranked Entropy Minimization for Continual Test-Time Adaptation

Jisu Han (Ajou University), Wonjun Hwang (Korea University)

CodeDomain AdaptationOptimizationTransformerSupervised Fine-TuningImage

🎯 What it does: A Ranked Entropy Minimization (REM) method is proposed, which achieves efficient and stable updates for Continual Test-Time Adaptation (CTTA) using an advanced masking chain and dual losses (mask consistency loss + entropy ranking loss).

RAPID: Long-Context Inference with Retrieval-Augmented Speculative Decoding

Guanzheng Chen (National University of Singapore), Michael Qizhe Shieh (National University of Singapore)

CodeGenerationRetrievalComputational EfficiencyKnowledge DistillationTransformerLarge Language ModelTextBenchmarkRetrieval-Augmented Generation

🎯 What it does: Proposes the RAPID method, which combines retrieval-augmented speculative decoding to accelerate long-context LLM inference and improve generation quality.

RATE: Causal Explainability of Reward Models with Imperfect Counterfactuals

David Reber (University of Chicago), Victor Veitch (University of Chicago)

CodeRecommendation SystemExplainability and InterpretabilityLarge Language ModelText

🎯 What it does: The RATE (Rewrite-based Attribute Treatment Estimator) method is proposed, which uses dual LLM rewriting to estimate the causal effects of reward models on high-level attributes such as sentiment, helpfulness, length, etc.

Re-ranking Reasoning Context with Tree Search Makes Large Vision-Language Models Stronger

Qi Yang (Alibaba Cloud Computing), Shiming Xiang (University of Chinese Academy of Sciences)

CodeGenerationRetrievalTransformerVision Language ModelMultimodalityRetrieval-Augmented Generation

🎯 What it does: A multi-modal retrieval-enhanced generation framework RCTS is proposed, which constructs a knowledge base using reasoning context and improves the VQA performance of large visual language models through tree search reordering.

Reaction Graph: Towards Reaction-Level Modeling for Chemical Reactions with 3D Structures

Yingzhao Jian (Zhejiang University), Yi Yang (Zhejiang University)

CodeGraph Neural NetworkGraph

🎯 What it does: This paper proposes the Reaction Graph (RG) - a unified representation of chemical reaction graphs that can simultaneously capture the molecular structures of reactants and products, the reaction edges generated by atom mapping, and three-dimensional geometric information (edge lengths and angle edges), thereby directly learning the transformation features of reactions during the message passing process of graph neural networks.

Reasoning-as-Logic-Units: Scaling Test-Time Reasoning in Large Language Models Through Logic Unit Alignment

Cheryl Li (Independent Researcher), Steven Y. Guo

CodeTransformerLarge Language ModelTextChain-of-Thought

🎯 What it does: This paper proposes a framework RaLU that constructs reliable reasoning paths by extracting and aligning program logic units during inference, aiming to reduce the reasoning hallucinations produced by LLMs.

Rectifying Conformity Scores for Better Conditional Coverage

Vincent Plassier (Lagrange Mathematics and Computing Research Center), Eric Moulines (Mohamed bin Zayed University of Artificial Intelligence)

CodeTabularBenchmark

🎯 What it does: A new method is proposed to generate confidence sets through trainable transformations to improve conditional coverage while ensuring the accuracy of marginal coverage.

ReferSplat: Referring Segmentation in 3D Gaussian Splatting

Shuting He (Shanghai University of Finance and Economics), Henghui Ding (Fudan University)

CodeObject DetectionSegmentationContrastive LearningGaussian SplattingTextPoint Cloud

🎯 What it does: A novel task called R3DGS is proposed for object segmentation in 3D Gaussian Splatting based on natural language descriptions, along with the construction of the corresponding dataset Ref-LERF.

ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding

Xingyu Fu (University of Pennsylvania), Cha Zhang (Microsoft)

CodeRecognitionObject DetectionSegmentationTransformerLarge Language ModelVision Language ModelImageMultimodalityTabularChain-of-Thought

🎯 What it does: By allowing a multimodal LLM to generate Python code for visual editing of input images (such as drawing boxes, masking, and highlighting), a visual thinking chain is realized, enhancing selective attention and multi-hop visual reasoning.

REG: Rectified Gradient Guidance for Conditional Diffusion Models

Zhengqi Gao (Massachusetts Institute of Technology), Duane S Boning

CodeGenerationData SynthesisDiffusion modelImageText

🎯 What it does: This paper reveals the contradiction between the theoretical roots and practical implementation of existing conditional diffusion model guidance methods by reconstructing the theoretical framework of joint distribution scale. Based on this framework, a new guidance strategy called Rectified Gradient Guidance (REG) is proposed to enhance the generation quality of existing guidance methods.

Regress, Don't Guess: A Regression-like Loss on Number Tokens for Language Models

Jonas Zausinger (Technical University of Munich), Jannis Born (IBM Research Europe)

CodeTransformerLarge Language ModelSupervised Fine-TuningText

🎯 What it does: Proposed and implemented Number Token Loss (NTL), allowing the language model to perform regression loss directly on numeric tokens during training, rather than using the traditional cross-entropy.

Regression for the Mean: Auto-Evaluation and Inference with Few Labels through Post-hoc Regression

Benjamin Eyre (Columbia University), David Madras (Google DeepMind)

CodeTabular

🎯 What it does: This study investigates the use of the Prediction Powered Inference (PPI) framework for mean estimation in scenarios with very few labels, and proposes regression-based improvements (Ridge-PPI and Sigmoid-PPI) to reduce estimation variance.

Regularized Langevin Dynamics for Combinatorial Optimization

Shengyu Feng (Carnegie Mellon University), Yiming Yang (Carnegie Mellon University)

CodeOptimizationGraph Neural NetworkReinforcement LearningGraph

🎯 What it does: Proposes Regularized Langevin Dynamics (RLD) and implements two CO solvers based on it: RLSA (simulated annealing version) and RLNN (neural network version).

Reinforced Lifelong Editing for Language Models

Zherui Li (Beijing University of Posts and Telecommunications), Xiang Wang (University of Science and Technology of China)

CodeTransformerLarge Language ModelReinforcement LearningText

🎯 What it does: This paper proposes the RLEdit method, which models the lifelong editing problem as a reinforcement learning task, utilizing a supernetwork for offline training across the entire knowledge sequence to achieve efficient and stable continuous knowledge updates.

Reinforcement Learning for Quantum Control under Physical Constraints

Jan Ole Ernst (University of Oxford), Axel Kuhn (University of Oxford)

CodeOptimizationReinforcement LearningPhysics Related

🎯 What it does: Using physics-constrained reinforcement learning, a control method for open quantum systems is proposed, capable of generating high-fidelity, realizable pulse sequences under noise and experimental constraints.

Reinforcement Learning with Adaptive Reward Modeling for Expensive-to-Evaluate Systems

Hongyuan Su (Tsinghua University), Yong Li (Tsinghua University)

CodeOptimizationDrug DiscoveryGraph Neural NetworkReinforcement LearningTabular

🎯 What it does: This paper proposes AdaReMo, which constructs a fast reward model for reinforcement learning systems with high reward evaluation costs, achieving decoupling of online decision-making and offline evaluation.

Reliable Algorithm Selection for Machine Learning-Guided Design

Clara Fannjiang (Genentech), Ji Won Park

CodeOptimizationProtein Structure PredictionTabular

🎯 What it does: A design algorithm configuration selection method based on predictive empowered inference and density ratio weighting is proposed, which can ensure a high probability of success within a multiple testing framework;

ResearchTown: Simulator of Human Research Community

Haofei Yu (University of Illinois Urbana-Champaign), Jiaxuan You (University of Illinois Urbana-Champaign)

CodeGraph Neural NetworkLarge Language ModelAgentic AITextBenchmark

🎯 What it does: This paper presents RESEARCHTOWN, a multi-agent LLM framework based on TextGNN, designed to simulate collaborative activities such as reading, writing, and reviewing papers in human research communities.

Residual Matrix Transformers: Scaling the Size of the Residual Stream

Brian Mak (University of California Santa Cruz), Jeffrey Flanigan (University of California Santa Cruz)

CodeTransformerText

🎯 What it does: A new variant of Transformer called Residual Matrix Transformer (RMT) is proposed, which replaces the residual flow with an outer product memory matrix to achieve scalable residual flow.

Residual TPP: A Unified Lightweight Approach for Event Stream Data Analysis

Ruoxin Yuan (Fudan University), Guanhua Fang (Fudan University)

CodeAnomaly DetectionComputational EfficiencyRecurrent Neural NetworkTransformerTabularTime SeriesSequentialBenchmarkOrdinary Differential Equation

🎯 What it does: This paper proposes Residual TPP, a lightweight hybrid model that integrates traditional Hawkes processes with neural TPP through Residual Event Decomposition (RED), capable of capturing the periodicity, self-excitement, and the difficult-to-interpret residual components of event streams.

ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank Residuals

Utkarsh Saxena (Purdue University), Xin Wang (d-Matrix)

CodeTransformerLarge Language ModelTextMultimodality

🎯 What it does: ResQ achieves efficient post-training quantization by performing low-rank PCA projection on weights, activations, and KV caches, retaining high-variance subspaces at 8-bit precision while quantizing the remaining parts to 4-bit.

Rethinking Addressing in Language Models via Contextualized Equivariant Positional Encoding

Jiajun Zhu (University of Texas at Austin), Zhangyang Wang (Georgia Tech)

CodeTransformerLarge Language ModelSupervised Fine-TuningText

🎯 What it does: A Contextualized Equivariant Positional Encoding (TAPE) is proposed, which enhances the model's representation of positional information and long sequence reasoning ability by gradually contextualizing positional encoding with the sequence content between Transformer layers.

Rethinking Causal Ranking: A Balanced Perspective on Uplift Model Evaluation

Minqin Zhu (Zhejiang University), Kun Kuang (Zhejiang University)

CodeRecommendation SystemOptimizationTabular

🎯 What it does: This paper proposes the Principled Uplift Curve (PUC) for a fairer and unbiased evaluation of uplift models, and based on this curve, introduces the Principled Treatment and Outcome Network (PTONet) uplift model;

Rethinking Chain-of-Thought from the Perspective of Self-Training

Zongqian Wu (University of Electronic Science and Technology of China), Lei Feng (Southeast University)

CodeLarge Language ModelPrompt EngineeringTextChain-of-Thought

🎯 What it does: Revisiting Chain-of-Thought reasoning from the perspective of self-training, a new CoT framework is proposed, consisting of task-specific prompts and adaptive reasoning iterations, aimed at improving the accuracy of large language models in complex reasoning tasks.

Rethinking Confidence Scores and Thresholds in Pseudolabeling-based SSL

Harit Vishwakarma (University of Wisconsin-Madison), Frederic Sala

CodeClassificationOptimizationConvolutional Neural NetworkImage

🎯 What it does: A pseudo-labeling confidence learning framework based on error tolerance is designed, replacing traditional threshold and confidence selection;

Rethinking Point Cloud Data Augmentation: Topologically Consistent Deformation

Jian Bi (Nanjing University of Science and Technology), Jian Yang (Nanjing University of Science and Technology)

CodeClassificationSegmentationPoint Cloud

🎯 What it does: The SinPoint method is proposed, which utilizes sine transformations and homotopy to maintain the topological consistency of point clouds for data augmentation.

Rethinking Score Distilling Sampling for 3D Editing and Generation

Xingyu Miao (Durham University), Jungong Han (Tsinghua University)

CodeGenerationData SynthesisKnowledge DistillationScore-based ModelGaussian SplattingPoint CloudMesh

🎯 What it does: A new method called Unified Distillation Sampling (UDS) is proposed, aimed at simultaneously supporting the generation and editing of 3D assets.

Rethinking the Stability-Plasticity Trade-off in Continual Learning from an Architectural Perspective

Aojun Lu (Sichuan University), Yanan Sun (Sichuan University)

CodeKnowledge DistillationRepresentation LearningConvolutional Neural NetworkTransformerImage

🎯 What it does: Proposes the Dual-Arch framework, which utilizes two networks with different architectures (a wide shallow stable network and a deep thin flexible network) to jointly complete continual learning tasks, leveraging knowledge distillation for new knowledge transfer.

Retraining-free Merging of Sparse MoE via Hierarchical Clustering

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

CodeCompressionMixture of ExpertsText

🎯 What it does: This paper proposes HC-SMoE, a hierarchical clustering expert merging framework that does not require retraining and is task-agnostic, aimed at compressing sparse mixture of experts models.

Retrieval Augmented Time Series Forecasting

Sungwon Han (Gwangju Institute of Science and Technology), Jinsung Yoon (Google Cloud AI)

CodeRetrievalAnomaly DetectionTime SeriesRetrieval-Augmented Generation

🎯 What it does: A retrieval-enhanced time series forecasting method called RAFT is proposed, which retrieves historical segments from the training set that are similar to the current input and uses their subsequent values in conjunction with the model input to predict the future.

Retrieval-Augmented Perception: High-resolution Image Perception Meets Visual RAG

Wenbin Wang (Wuhan University), Dacheng Tao (Nanyang Technological University)

CodeRecognitionRetrievalComputational EfficiencyLarge Language ModelImageMultimodalityBenchmarkRetrieval-Augmented Generation

🎯 What it does: A training-free Retrieval-Augmented Perception (RAP) framework is proposed, which enhances the perception ability of multimodal large language models (MLLM) for high-resolution (HR) images by retrieving and fusing high-resolution image patches related to the query.

Return of the Latent Space COWBOYS: Re-thinking the use of VAEs for Bayesian Optimisation of Structured Spaces

Henry Moss, Tom Diethe (AstraZeneca)

CodeOptimizationDrug DiscoveryAuto EncoderTabular

🎯 What it does: A Bayesian optimization framework called COWBOYS is proposed, which completely separates the Variational Autoencoder (VAE) from the Gaussian Process (GP). It utilizes GP to directly predict the target in the structural space and restricts sampling to areas where the VAE prior probability is high and the GP predicted values are also high through Bayesian updating.

Revisiting Continuity of Image Tokens for Cross-domain Few-shot Learning

Shuai Yi (Huazhong University of Science and Technology), Ruixuan Li (Huazhong University of Science and Technology)

CodeDomain AdaptationTransformerImageAgriculture Related

🎯 What it does: This paper studies the impact of disrupting the continuity of image tokens in Vision Transformers on cross-domain few-shot learning and proposes the ReCIT method, which reduces domain gaps and enhances model generalization by first performing spatial layer block shuffling followed by frequency domain amplitude balancing shuffling.

Reward Translation via Reward Machine in Semi-Alignable MDPs

Yun Hua (Shanghai Jiao Tong University), Xiangfeng Wang (East China Normal University)

CodeLarge Language ModelReinforcement LearningSequential

🎯 What it does: A Neural Reward Translation (NRT) framework is proposed in the context of semi-aligned MDP environments, utilizing reward machines and graph matching to achieve cross-domain reward transfer.

Reward-Guided Iterative Refinement in Diffusion Models at Test-Time with Applications to Protein and DNA Design

Masatoshi Uehara (EvolutionaryScale), Tommaso Biancalani (EvolutionaryScale)

CodeOptimizationDrug DiscoveryReinforcement LearningDiffusion modelBiomedical Data

🎯 What it does: A new framework is proposed for reward-guided iterative optimization during the testing phase of diffusion models, specifically applied to protein and DNA design.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Baohao Liao (Language Technology Lab, University of Amsterdam), Caiming Xiong (Salesforce AI Research)

CodeComputational EfficiencyReinforcement Learning from Human FeedbackTransformerLarge Language ModelReinforcement LearningText

🎯 What it does: A Reward-Guided Speculative Decoding (RSD) framework is proposed, which dynamically mixes a lightweight draft model with a powerful target model and evaluates the quality of each step through a process reward model to enhance the inference efficiency of large language models.

Right Now, Wrong Then: Non-Stationary Direct Preference Optimization under Preference Drift

Seongho Son (University College London), Ilija Bogunovic (University College London)

CodeRecommendation SystemOptimizationTransformerLarge Language ModelReinforcement LearningText

🎯 What it does: This paper studies the algorithm NS-DPO, which directly optimizes preferences for time drift in large language models (LLMs), and provides theoretical analysis and experimental validation.

RISE: Radius of Influence based Subgraph Extraction for 3D Molecular Graph Explanation

Jingxiang Qu (Stony Brook University), Yi Liu (Stony Brook University)

CodeExplainability and InterpretabilityDrug DiscoveryGraph Neural NetworkGraph

🎯 What it does: A subgraph extraction method based on the influence radius of each atom, RISE, is proposed to explain the predictive decisions of 3D molecular graph neural networks.

Risk and cross validation in ridge regression with correlated samples

Alexander Atanasov (Harvard University), Cengiz Pehlevan (Harvard University)

CodeTime Series

🎯 What it does: The study investigates the risk of high-dimensional ridge regression in the presence of correlated samples and provides precise asymptotic analysis.

Robust Conformal Outlier Detection under Contaminated Reference Data

Meshi Bashari (Technion Israel Institute of Technology), Yaniv Romano (Technion Israel Institute of Technology)

CodeAnomaly DetectionTabular

🎯 What it does: The study investigates the robustness of conformal prediction in anomaly detection tasks when there are a small number of outlier samples in the reference data, and proposes an active data cleaning method (Label-Trim) based on a limited labeling budget to improve detection rates.

Robust ML Auditing using Prior Knowledge

Jade Garcia BourrΓ©e, Milos Vujasinovic (Γ‰cole Polytechnique FΓ©dΓ©rale de Lausanne)

CodeImageTabular

🎯 What it does: A theoretical and experimental framework is proposed to improve the robustness of black-box fairness auditing using auditors' prior knowledge.

Robust Noise Attenuation via Adaptive Pooling of Transformer Outputs

Greyson Brothers (Johns Hopkins University Applied Physics Laboratory)

CodeClassificationRecognitionRestorationTransformerReinforcement LearningImage

🎯 What it does: Research and improve the global pooling method of Transformer outputs, proposing Adaptive Pooling (AdaPool) to better extract useful signals in noisy environments.

Robust Offline Reinforcement Learning with Linearly Structured $f$-Divergence Regularization

Cheng Tang (University of Illinois Urbana-Champaign), Pan Xu (Duke University)

CodeReinforcement LearningTabularFinance Related

🎯 What it does: In the offline robust reinforcement learning task, a d-rectangular linear RRMDP framework is proposed, and the R2PVI algorithm is designed to achieve robustness against dynamic shifts through f-divergence regularization.

Robust Secure Swap: Responsible Face Swap With Persons of Interest Redaction and Provenance Traceability

Yunshu Dai (Sun Yat-sen University), Chip Hong Chang (Nanyang Technological University)

CodeRecognitionImage TranslationSafty and PrivacyKnowledge DistillationGenerative Adversarial NetworkImage

🎯 What it does: Proposes the Secure Swap model, which combines the ID Passport layer to achieve person identity (POI) recognition and occlusion, and embeds an invisible watermark in the generated non-POI images for identity tracing and abuse prevention.

Robust Spatio-Temporal Centralized Interaction for OOD Learning

Jiaming Ma (University of Science and Technology of China), Yang Wang (University of Science and Technology of China)

CodeGraph Neural NetworkTime Series

🎯 What it does: A spatiotemporal graph neural network (STOP) based on centralized message passing and message perturbation mechanisms is proposed to address the spatiotemporal OOD learning problem.

rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking

Xinyu Guan (Microsoft Research Asia), Mao Yang (Microsoft Research Asia)

CodeTransformerLarge Language ModelReinforcement LearningTextChain-of-Thought

🎯 What it does: The deep thinking framework rStar-Math, based on a small LLM, achieves high-level mathematical reasoning through self-evolution training strategies and reward models.

RULEBREAKERS: Challenging LLMs at the Crossroads between Formal Logic and Human-like Reasoning

Jason Chan (University of Sheffield), Zhixue Zhao (University of Sheffield)

CodeTransformerLarge Language ModelPrompt EngineeringText

🎯 What it does: This paper systematically evaluates the reasoning abilities of large language models in the context of logical rule violations (rulebreakers) and normal reasoning (non-rulebreakers) by constructing a dataset called RULEBREAKERS.

SADA: Stability-guided Adaptive Diffusion Acceleration

Ting Jiang (Duke University), Hai Li (Duke University)

CodeGenerationComputational EfficiencyDiffusion modelImageTextMultimodalityOrdinary Differential Equation

🎯 What it does: This paper proposes a training-free, stability criterion-based adaptive acceleration framework SADA, designed to accelerate the sampling process of diffusion models (Diffusion and Flow-matching) in ODE form.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets

Ning Lu (Southern University of Science and Technology), Ke Tang (Southern University of Science and Technology)

CodeOptimizationSafty and PrivacyTransformerLarge Language ModelSupervised Fine-TuningText

🎯 What it does: This paper proposes Safe Delta, a post-training defense method that is safety-aware for incremental parameters after fine-tuning LLMs, aimed at maintaining model safety and enhancing task performance.

SAFER: A Calibrated Risk-Aware Multimodal Recommendation Model for Dynamic Treatment Regimes

Yishan Shen (University of Pennsylvania), Yong Chen (University of Pennsylvania)

CodeRecommendation SystemTransformerMultimodalityBiomedical DataElectronic Health Records

🎯 What it does: We propose SAFER, a multimodal recommendation framework that achieves risk awareness in dynamic treatment plans;

SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization

Jintao Zhang (Tsinghua University), Jianfei Chen (Tsinghua University)

CodeGenerationComputational EfficiencyTransformerLarge Language ModelImageVideoText

🎯 What it does: To address the quantization bottleneck in attention computation, SageAttention2 is proposed, utilizing INT4 quantization for Q and K, FP8 quantization for ˜P and V, and enhancing accuracy through Q and K smoothing, thread-level quantization, and a dual-layer accumulation method, significantly accelerating attention operations while maintaining unchanged end-to-end metrics.

SAH-Drive: A Scenario-Aware Hybrid Planner for Closed-Loop Vehicle Trajectory Generation

Yuqi Fan (Beihang University), Haiyang Yu (Beihang University)

CodeAutonomous DrivingOptimizationDiffusion modelTime SeriesBenchmark

🎯 What it does: Proposes SAH-Drive, which integrates rule-based planning PDM-Closed with diffusion learning planning to form a context-aware hybrid trajectory planner;

Sample Efficient Demonstration Selection for In-Context Learning

Kiran Purohit (Indian Institute of Technology), Avishek Anand (Delft University of Technology)

CodeTransformerLarge Language ModelPrompt EngineeringText

🎯 What it does: A sample-efficient demonstration subset selection algorithm named CASE is proposed for selecting the optimal example set in in-context learning (ICL) of large language models.

Sample-specific Noise Injection for Diffusion-based Adversarial Purification

Yuhao Sun (University of Melbourne), Feng Liu (University of Melbourne)

CodeAdversarial AttackDiffusion modelScore-based ModelImage

🎯 What it does: This paper proposes a score-adaptive noise injection framework based on diffusion, called SSNI, which can dynamically adjust the noise level for each input sample, thereby better removing adversarial noise while preserving image semantics.

Sassha: Sharpness-aware Adaptive Second-order Optimization with Stable Hessian Approximation

Dahun Shin (POSTECH), Namhoon Lee (POSTECH)

CodeOptimizationConvolutional Neural NetworkTransformerImageText

🎯 What it does: Designed and implemented SASSHA, an optimizer that enhances generalization performance through stable Hessian approximation and sharpness reduction mechanisms within a second-order optimization framework.

Scalable Approximation Algorithms for $p$-Wasserstein Distance and Its Variants

Nathaniel Lahn (Radford University), Pouyan Shirzadian (Virginia Tech)

CodeOptimizationTabular

🎯 What it does: Proposed a scalable relative and additive approximation algorithm that uses multiple HSTs and a dynamic weighted bi-colored nearest point (BCP) data structure to compute the p-Wasserstein distance and its (p,k)-RPW variant;

Scalable First-order Method for Certifying Optimal k-Sparse GLMs

Jiachang Liu (Cornell University), Andrea Lodi (Cornell University)

CodeOptimizationComputational EfficiencyTabular

🎯 What it does: This paper studies the optimality proof problem of sparse generalized linear models (GLMs) and proposes a method based on a first-order proximal gradient algorithm to address the perspective relaxation issue within the branch-and-bound (BnB) framework.

Scalable Gaussian Processes with Latent Kronecker Structure

Jihao Andreas Lin (Meta), Eytan Bakshy (Meta)

CodeOptimizationComputational EfficiencyTabular

🎯 What it does: A Gaussian Process method utilizing the latent Kronecker structure is proposed, allowing for efficient and accurate inference even in the presence of missing observations.

Scalable Non-Equivariant 3D Molecule Generation via Rotational Alignment

Yuhui Ding (ETH Zurich), Thomas Hofmann (ETH Zurich)

CodeGenerationDrug DiscoveryGraph Neural NetworkTransformerDiffusion modelAuto EncoderGraph

🎯 What it does: By learning molecular adaptive rotation and training non-equivariant diffusion models in aligned latent space, efficient 3D molecular generation is achieved with quality comparable to equivariant models.

Scaling Laws for Task-Optimized Models of the Primate Visual Ventral Stream

Abdulkadir Gokce (Γ‰cole Polytechnique FΓ©dΓ©rale de Lausanne), Martin Schrimpf (Γ‰cole Polytechnique FΓ©dΓ©rale de Lausanne)

CodeConvolutional Neural NetworkTransformerImage

🎯 What it does: Systematically train artificial neural networks of different architectures and data scales, evaluating their alignment with the primate ventral visual pathway (V1–IT) and behavior;

SCENIR: Visual Semantic Clarity through Unsupervised Scene Graph Retrieval

Nikolaos Chaidos (National Technical University of Athens), Giorgos Stamou (National Technical University of Athens)

CodeRetrievalGraph Neural NetworkAuto EncoderGraph

🎯 What it does: This paper proposes an unsupervised scene graph retrieval framework (SCENIR) based on graph autoencoders, using Graph Edit Distance (GED) as a deterministic criterion for assessing retrieval similarity.

scSSL-Bench: Benchmarking Self-Supervised Learning for Single-Cell Data

Olga Ovcharenko (BIFOLD & TU Berlin), Valentina Boeva (ETH Zurich)

CodeRepresentation LearningData-Centric LearningContrastive LearningBiomedical DataBenchmark

🎯 What it does: Constructed scSSL-Bench, a systematic evaluation of 19 self-supervised learning (SSL) methods on single-cell data;

SDMG: Smoothing Your Diffusion Models for Powerful Graph Representation Learning

Junyou Zhu (Potsdam Institute for Climate Impact Research), Frank Hellmann (Potsdam Institute for Climate Impact Research)

CodeRepresentation LearningGraph Neural NetworkDiffusion modelGraph

🎯 What it does: Designed the SDMG (Smooth Diffusion Model for Graphs) framework, which utilizes a diffusion probability model for unsupervised representation learning on graph data, and enhances representation quality through a low-frequency encoder and multi-scale smooth loss.

SDP-CROWN: Efficient Bound Propagation for Neural Network Verification with Tightness of Semidefinite Programming

Hong-Ming Chiu (University of Illinois), Richard Y. Zhang (University of Illinois)

CodeOptimizationComputational EfficiencyConvolutional Neural NetworkSupervised Fine-TuningImage

🎯 What it does: Proposes the SDP-CROWN framework, which combines SDP and linear bound propagation to achieve scalable robustness verification of neural networks under β„“β‚‚ error;

SecEmb: Sparsity-Aware Secure Federated Learning of On-Device Recommender System with Large Embedding

Peihua Mai (National University of Singapore), Yan Pang (National University of Singapore)

CodeRecommendation SystemFederated LearningSafty and PrivacyComputational EfficiencyTabularSequential

🎯 What it does: A sparse encrypted federated recommendation system protocol named SecEmb is proposed, which utilizes point functions and function secret sharing (FSS) to ensure that users only download item embeddings they have interacted with, while securely aggregating sparse gradients on the server side, ensuring that the server cannot obtain any user's rated item indices or gradient information.

SEFE: Superficial and Essential Forgetting Eliminator for Multimodal Continual Instruction Tuning

Jinpeng Chen (City University of Hong Kong), Sam Kwong (Lingnan University)

CodeRecognitionGenerationTransformerLarge Language ModelSupervised Fine-TuningMultimodality

🎯 What it does: A forgetting elimination framework SEFE for multimodal continual instruction tuning is proposed, which separates and simultaneously suppresses superficial forgetting and essential forgetting.

Selective Prompt Anchoring for Code Generation

Yuan Tian (Purdue University), Tianyi Zhang (Purdue University)

CodeGenerationAI Code AssistantTransformerLarge Language ModelPrompt EngineeringText

🎯 What it does: This study investigates the phenomenon of attention decay in the code generation process of large language models and proposes the Selective Prompt Anchoring (SPA) method, which enhances the impact of keywords in user prompts on model attention to improve generation quality.

Self-Bootstrapping for Versatile Test-Time Adaptation

Shuaicheng Niu (Nanyang Technological University), Zhiqi Shen (Nanyang Technological University)

CodeClassificationObject DetectionSegmentationDomain AdaptationImage

🎯 What it does: A universal self-guided adaptive (SPA) framework is proposed, which can perform model adaptation on image, object, and pixel-level tasks without source data or changes in the training process.

Self-Organizing Visual Prototypes for Non-Parametric Representation Learning

Thalles Silva (University of Campinas), AdΓ­n RamΓ­rez Rivera (University of Oslo)

CodeObject DetectionSegmentationRetrievalRepresentation LearningTransformerContrastive LearningImage

🎯 What it does: Proposes the Self-Organizing Prototypes (SOP) method, which constructs dynamic prototypes using non-parametric Support Embedding (SE) for unsupervised visual feature learning, and designs the SOP-Masked Image Modeling (SOP-MIM) task.

SEMU: Singular Value Decomposition for Efficient Machine Unlearning

Marcin Sendera (Jagiellonian University), Dawid Damian Rymarczyk

CodeClassificationGenerationComputational EfficiencyData-Centric LearningDiffusion modelImage

🎯 What it does: This paper proposes a method that utilizes Singular Value Decomposition (SVD) to project model gradients, selecting the most important weight subspace and fine-tuning only less than 1% of the parameters, thereby achieving efficient forgetting of specific data or concepts.

SERENA: A Unified Stochastic Recursive Variance Reduced Gradient Framework for Riemannian Non-Convex Optimization

Yan Liu (Nankai University), Ruxin Wang (Shenzhen Institutes of Advanced Technology)

CodeOptimizationTabular

🎯 What it does: This paper proposes the SRVRG estimator, the SRGE unified estimator, and the SERENA framework, extending variance reduction methods to Riemannian geometric non-convex optimization, and provides theoretical convergence analysis and experimental validation.

SHE: Streaming-media Hashing Retrieval

Ruitao Pu (Sichuan University), Yuan Sun (Sichuan University)

CodeRetrievalMultimodality

🎯 What it does: A Streaming-media Hashing Retrieval (SHE) method is proposed, supporting parallel learning and retrieval of streaming multimodal data.

SITCOM: Step-wise Triple-Consistent Diffusion Sampling For Inverse Problems

Ismail Alkhouri, Rongrong Wang (Michigan State University)

CodeRestorationOptimizationDiffusion modelImageBiomedical DataMagnetic Resonance Imaging

🎯 What it does: This paper proposes an optimized sampler named SITCOM, which utilizes diffusion models to achieve more efficient reconstruction in inverse problem solving through three consistency constraints.