arXivSub Start free trial

ICLR 2026 Papers with Code β€” Page 7

International Conference on Learning Representations Β· 2207 papers

Endowing GPT-4 with a Humanoid Body: Building the Bridge Between Off-the-Shelf VLMs and the Physical World

Yingzhao Jian (Zhejiang University), Hehe Fan (Zhejiang University)

CodeRobotic IntelligenceTransformerReinforcement LearningVision Language ModelDiffusion modelAuto EncoderMultimodality

🎯 What it does: Propose the BiBo framework, leveraging existing Vision-Language Models (e.g., GPT-4o) and diffusion models to control humanoid robots to perform diverse physical interaction tasks.

Enhanced Continual Learning of Vision-Language Models with Model Fusion

Haoyuan Gao (Shanghai Jiao Tong University), Weiran Huang (Tencent)

CodeMeta LearningSupervised Fine-TuningMixture of ExpertsVision Language ModelContrastive LearningMultimodalityBenchmark

🎯 What it does: Introduces the ConDU framework, which uses model fusion to achieve continuous learning in vision-language models, compatible with full-parameter fine-tuning and parameter-efficient fine-tuning, and supports zero-shot inference.

Enhanced Generative Model Evaluation with Clipped Density and Coverage

Nicolas Salvy (Inria), Bertrand Thirion (Inria)

CodeGenerationImage

🎯 What it does: Proposed and evaluated two new generative model quality assessment metrics: Clipped Density and Clipped Coverage.

Enhancing Communication Compression via Discrepancy-aware Calibration for Federated Learning

Zhiyi Wan (Beijing University Of Posts And Telecommunications), Xiaoqi Qin (Peng Cheng Laboratory)

CodeFederated LearningComputational EfficiencyConvolutional Neural NetworkTransformerImage

🎯 What it does: This paper proposes a difference-aware communication compression method based on locally calibrated data, significantly reducing communication volume and improving model accuracy in federated learning.

Enhancing Instruction Following of LLMs via Activation Steering with Dynamic Rejection

Minjae Kang (Yonsei University), Jaehyung Kim (Yonsei University)

CodeExplainability and InterpretabilityComputational EfficiencyTransformerLarge Language ModelText

🎯 What it does: Proposes a dynamic activation regulation method called DIRECTER to enhance large language models' (LLM) instruction-following capability during inference while avoiding text quality degradation caused by over-regulation.

Enhancing Language Model Reasoning with Structured Multi-Level Modeling

Siheng Xiong (Georgia Institute of Technology), Faramarz Fekri (Georgia Institute of Technology)

CodeReinforcement Learning from Human FeedbackTransformerLarge Language ModelSupervised Fine-TuningReinforcement LearningTextChain-of-Thought

🎯 What it does: Proposes a Multi-Level Reasoning (MLR) framework that decomposes the reasoning process into high-level planning descriptors and low-level detailed reasoning, forming an alternating plan-execute cycle; simultaneously introduces an iterative Step-DPO training process and employs Twisted Sequential Monte Carlo (TSMC) to construct process-level preferences, addressing the long-sequence credit assignment challenge caused by sparse single-result rewards.

Enhancing LLMs for Knowledge Base Question Answering by Chain-of-Decomposition

Yonggang Zhang (Hong Kong University of Science and Technology), Jie Lu (University of Technology Sydney)

CodeComputational EfficiencyTransformerTextGraphBenchmarkRetrieval-Augmented GenerationChain-of-Thought

🎯 What it does: Propose the Chain-of-Decomposition (CoD) framework, decomposing the KBQA task into three steps: retrieval, reconstruction, and reasoning, reducing the burden on LLMs and improving performance.

Enhancing Multivariate Time Series Forecasting with Global Temporal Retrieval

Fanpu Cao (Hong Kong University of Science and Technology), Hui Xiong (Hong Kong University of Science and Technology)

CodeConvolutional Neural NetworkTime Series

🎯 What it does: Propose a lightweight, plug-and-play Global Temporal Retriever (GTR) module to expand the temporal awareness range of multivariate time series prediction models, thereby capturing long-term global periodic patterns.

Enhancing Trustworthiness of Fine-Tuned LLMs via Regularized Subset Selection

Kumar Shubham (Indian Institute of Science), Prathosh AP

CodeExplainability and InterpretabilityData-Centric LearningReinforcement Learning from Human FeedbackLarge Language ModelSupervised Fine-TuningText

🎯 What it does: Enhancing the reliability of LLMs by identifying and repairing training samples after SFT.

Enhancing Visual Token Representations for Video Large Language Models via Training-free Spatial-Temporal Pooling and Gridding

Bingjun Luo (Tsinghua University), Xinpeng Ding (Xidian University)

CodeComputational EfficiencyRepresentation LearningTransformerLarge Language ModelVision Language ModelVideo

🎯 What it does: Proposes ST-GridPool, a training-agnostic visual token enhancement method to improve visual representations in video large language models;

EnsembleSHAP: Faithful and Certifiably Robust Attribution for Random Subspace Method

Yanting Wang (Pennsylvania State University), Jinyuan Jia (Pennsylvania State University)

CodeExplainability and InterpretabilityComputational EfficiencyAdversarial AttackImageText

🎯 What it does: Propose EnsembleSHAP, an efficient and provably secure feature attribution method specifically designed for random subspace methods.

Entering the Era of Discrete Diffusion Models: A Benchmark for SchrΓΆdinger Bridges and Entropic Optimal Transport

Xavier Aramayo Carrasco (Applied AI Institute), Alexander Korotin (Applied AI Institute)

CodeOptimizationDiffusion modelBenchmarkPhysics Related

🎯 What it does: This paper proposes a benchmark for the Schrâdinger Bridge and Entropic Optimal Transport (EOT) in discrete space, utilizing analytical SB solutions to construct discrete distribution pairs, and develops and evaluates three new algorithms (DLightSB, DLightSB-M, α-CSBM) on this benchmark.

Entropy-Based Block Pruning for Efficient Large Language Models

Liangwei Yang (Salesforce Ai Research), Shelby Heinecke (Salesforce Ai Research)

CodeComputational EfficiencyTransformerLarge Language ModelText

🎯 What it does: This paper proposes EntroDrop, a block pruning method based on the entropy increase of hidden representations, aimed at reducing the computational and storage requirements of large language models.

EquAct: An SE(3)-Equivariant Multi-Task Transformer for 3D Robotic Manipulation

Xupeng Zhu (Northeastern University), Robert Platt (Northeastern University)

CodeRobotic IntelligenceConvolutional Neural NetworkTransformerReinforcement LearningVision-Language-Action ModelTextMultimodalityPoint Cloud

🎯 What it does: Propose a multi-task keyframe manipulation strategy called EquAct, which maps language instructions, point cloud observations, and actions into a shared space through SE(3) equivariant networks, achieving theoretical generalization for 3D pose variations.

Equilibrium Language Models

Yikun Jiang (Huawei Technologies Co Ltd), John C.S. Lui (Chinese University of Hong Kong)

CodeCompressionComputational EfficiencyTransformerLarge Language ModelReinforcement LearningText

🎯 What it does: Achieve LLM compression and adaptation for edge devices by replacing Transformer layer blocks with fixed-point networks.

Equivariant Splitting: Self-supervised learning from incomplete data

Victor Sechaud (ENS de Lyon), JuliΓ‘n Tachella (ENS de Lyon)

CodeRestorationConvolutional Neural NetworkImageBiomedical DataMagnetic Resonance ImagingComputed Tomography

🎯 What it does: Proposed a self-supervised learning framework called Equivariant Splitting (ES), for image recovery using only a single incomplete measurement.

ERGO: Efficient High-Resolution Visual Understanding for Vision-Language Models

Jewon Lee (Nota Inc), Bo-Kyeong Kim (Nota Inc)

CodeComputational EfficiencyTransformerReinforcement LearningVision Language ModelMultimodality

🎯 What it does: Designed and implemented a two-stage coarse-to-fine high-resolution visual reasoning pipeline, training the model via reinforcement learning to autonomously locate task-related regions for fine-grained reasoning under low-resolution inputs.

Error as Signal: Stiffness-Aware Diffusion Sampling via Embedded Runge-Kutta Guidance

Inho Kong (Korea University), Hyunwoo J. Kim (Korea Advanced Institute of Science and Technology)

CodeGenerationDiffusion modelImageTextOrdinary Differential Equation

🎯 What it does: Proposes ERK-Guid, a method that utilizes embedded Runge-Kutta error as a guidance signal to correct local truncation errors in rigid regions during diffusion model sampling, thereby improving sampling quality and efficiency.

ES-dLLM: Efficient Inference for Diffusion Large Language Models by Early-Skipping

Zijian Zhu (Tsinghua University), Kaisheng Ma (Tsinghua University)

CodeComputational EfficiencyTransformerLarge Language ModelDiffusion modelText

🎯 What it does: Studied computational redundancy in the inference process of diffusion large language models (dLLM), and proposed a training-agnostic early skipping framework called ES-dLLM to reduce computational cost per iteration.

Escaping Low-Rank Traps: Interpretable Visual Concept Learning via Implicit Vector Quantization

Shujian Gao (Fudan University), Junjun He (Shanghai AI Laboratory)

CodeExplainability and InterpretabilityRepresentation LearningTransformerImage

🎯 What it does: Proposed a concept bottleneck model (CBM) integrating implicit vector quantization (IVQ) and magnet attention, addressing visual feature collapse and enabling many-to-many visual concept learning.

Estimating Dimensionality of Neural Representations from Finite Samples

Chanwoo Chun (Harvard University), Daniel Lee (Flatiron Institute)

CodeRepresentation LearningTextBiomedical DataMagnetic Resonance Imaging

🎯 What it does: Investigated estimating the global dimension of neural representations from limited samples and noise, proposing an unbiased participation ratio estimator.

Estimating Semantic Alphabet Size for LLM Uncertainty Quantification

Lucas Hurley McCabe (George Washington University), H Howie Huang (George Washington University)

CodeExplainability and InterpretabilityLarge Language ModelText

🎯 What it does: To address uncertainty estimation in large language models, this paper proposes an improved method for estimating the size of the semantic alphabet and uses it to correct discrete semantic entropy (DSE), achieving more accurate entropy estimation and error detection with only a small number of samples.

ETGS: Explicit Thermodynamics Gaussian Splatting for Dynamic Thermal Reconstruction

Zhongwen Wang (Nanjing University of Science and Technology), Quansen Sun (Nanjing University of Science and Technology)

CodeGaussian SplattingVideoTime SeriesPhysics Related

🎯 What it does: Proposed the ETGS method, which achieves dynamic thermal field reconstruction using 3D Gaussian splatting with explicit thermodynamic modeling.

Evaluating Cross-Modal Reasoning Ability and Problem Characteristics with Multimodal Item Response Theory

Shunki Uebayashi, Koh Takeuchi (CyberAgent)

CodeExplainability and InterpretabilityComputational EfficiencyData-Centric LearningLarge Language ModelVision Language ModelMultimodalityBenchmark

🎯 What it does: This paper proposes Multimodal Multidimensional Item Response Theory (M3IRT) and its simplified version M2IRT to evaluate the cross-modal reasoning capabilities of Multimodal Large Language Models (MLLMs). By decomposing item difficulty and model ability into image, text, and cross-modal dimensions, it achieves automatic construction of high-quality subsets and significantly reduces evaluation costs.

Evaluating Text Creativity across Diverse Domains: a Dataset and Large Language Model Evaluator

Qian Cao (Renmin University of China), Ruihua Song (Beijing Normal University)

CodeLarge Language ModelReinforcement LearningPrompt EngineeringTextBenchmark

🎯 What it does: Propose a context-based dual comparison framework for evaluating text creativity, and develop a large cross-domain dataset CreataSet and the corresponding LLM evaluator CrEval

EventFlash: Towards Efficient MLLMs for Event-Based Vision

Shaoyu Liu (Xidian University), Xiangyang Ji (Tsinghua University)

CodeComputational EfficiencyRepresentation LearningTransformerLarge Language ModelVision Language ModelMultimodalityTime Series

🎯 What it does: Proposed EventFlash, an efficient event-based visual multimodal large language model that achieves fast inference and long sequence processing through spatiotemporal token sparsification.

Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models

Zengbin Wang (AMAP, Alibaba Group), Xiangxiang Chu (AMAP, Alibaba Group)

CodeGenerationData SynthesisLarge Language ModelSupervised Fine-TuningPrompt EngineeringVision Language ModelDiffusion modelImageTextMultimodalityBenchmark

🎯 What it does: Proposed the SpatialGenEval benchmark, which evaluates the spatial intelligence of T2I models with information-dense long prompts and multiple-choice questions across 10 spatial subdomains, and constructed the SpatialT2I dataset for supervised fine-tuning.

Evolution and compression in LLMs: on the emergence of human-aligned categorization

Nathaniel Imel (New York University), Noga Zaslavsky (New York University)

CodeClassificationCompressionLarge Language ModelPrompt EngineeringText

🎯 What it does: This paper investigates the semantic systems of large language models (LLMs) in color classification tasks. It first evaluates their alignment with human English systems and information bottleneck (IB) efficiency in an English color naming experiment. Subsequently, it simulates cultural evolution through the proposed iterative contextual language learning (IICLL) method, observing how LLMs evolve near-human color category systems without explicit supervision. Preliminary validation is conducted in different semantic domains such as Shepard circles.

Evolution of Concepts in Language Model Pre-Training

Xuyang Ge (OpenMOSS Team, Shanghai Innovation Institute; Fudan University), Xipeng Qiu (OpenMOSS Team, Shanghai Innovation Institute; Fudan University)

CodeExplainability and InterpretabilityRepresentation LearningTransformerLarge Language ModelAuto EncoderText

🎯 What it does: Track and analyze the evolution of features during the pre-training process of large-scale language models, using cross-snapshot sparse autoencoder (crosscoder) to capture the emergence, rotation, and disappearance of features across different training stages, and further associate micro-level evolution with downstream task performance through feature attribution.

Evolving Graph Structured Programs for Circuit Generation with Large Language Models

Yinqi Bai (University of Science and Technology of China), Enhong Chen (University of Science and Technology of China)

CodeGenerationOptimizationTransformerLarge Language ModelPrompt EngineeringGraphBenchmark

🎯 What it does: This paper proposes CircuitEvo, an evolutionary circuit program generation framework based on large language models, which iteratively evolves circuit programs and achieves functionally accurate and more compact logic synthesis through structure-aware functional optimization.

EvoTest: Evolutionary Test-Time Learning for Self-Improving Agentic Systems

Yufei He (National University of Singapore), Bryan Hooi (National University of Singapore)

CodeMeta LearningLarge Language ModelAgentic AIPrompt EngineeringTextBenchmark

🎯 What it does: Proposed the J-TTL benchmark to evaluate AI agents' ability to progressively improve across multiple attempts in the same game, and designed the EvoTest framework to achieve gradient-free self-evolution during testing

EXP-Bench: Can AI Conduct AI Research Experiments?

Patrick Tser Jern Kon, Ang Chen (University Of Michigan)

CodeLarge Language ModelAgentic AITextBenchmark

🎯 What it does: Propose the EXP-Bench benchmark to evaluate AI agents' ability to complete the full scientific experiment process, from experimental design, implementation, execution, to conclusion.

Expanding Reasoning Potential in Foundation Model by Learning Diverse Chains of Thought Patterns

Xuemiao Zhang (Peking University), Xunliang Cai (Meituan)

CodeExplainability and InterpretabilityReinforcement Learning from Human FeedbackTransformerSupervised Fine-TuningReinforcement LearningMixture of ExpertsTextBenchmarkChain-of-Thought

🎯 What it does: By defining the model's reasoning potential (i.e., the reciprocal of the number of attempts required to solve a problem), a core set containing high-value chain reasoning patterns is constructed, and a dual-granularity algorithm (based on reasoning pattern chains and token entropy) is designed to efficiently select training samples that conform to the core set distribution from massive CoT data, thereby significantly improving the performance of large language models on complex mathematical reasoning tasks.

Expert Divergence Learning for MoE-based Language Models

Jiaang Li (Alibaba Group), Bo Zheng (Alibaba Group)

CodeLarge Language ModelMixture of ExpertsText

🎯 What it does: This paper proposes the Expert Divergence Learning (EDL) pre-training strategy, which introduces a domain label-driven auxiliary loss in MoE models to encourage experts to generate separated routing distributions across different data domains, thereby achieving significant differentiation in expert functions;

Expert Merging in Sparse Mixture of Experts with Nash Bargaining

Dung Viet Nguyen, Tan Minh Nguyen

CodeOptimizationComputational EfficiencyMixture of ExpertsImageText

🎯 What it does: This paper proposes a Nash equilibrium-based expert merging method called NAMEx, combining complex momentum to achieve efficient convergence.

Expert Merging: Model Merging with Unsupervised Expert Alignment and Importance-Guided Layer Chunking

Dengming Zhang (Huawei Technologies), Xinghao Chen (Huawei Technologies)

CodeKnowledge DistillationRepresentation LearningTransformerLarge Language ModelMixture of ExpertsTextMultimodalityBenchmark

🎯 What it does: Proposed Expert Merging and its improved version Expert Merging++, achieving unsupervised fusion of multi-domain expert models by learning hierarchical (or block-wise) coefficients and aligning hidden states and logits on unlabeled calibration data.

ExpGuard: LLM Content Moderation in Specialized Domains

Minseok Choi (KAIST), Jungmin Son (KakaoBank Corp)

CodeTransformerLarge Language ModelSupervised Fine-TuningPrompt EngineeringTextFinance RelatedChain-of-Thought

🎯 What it does: Proposed a content safety model for LLMs in professional fields such as finance, healthcare, and law called EXPGUARD, and constructed a large-scale professional safety dataset named EXPGUARDMIX.

Explain in Your Own Words: Improving Reasoning via Token-Selective Dual Knowledge Distillation

Minsang Kim (Korea University), Seung Jun Baek (Korea University)

CodeKnowledge DistillationTextChain-of-Thought

🎯 What it does: This paper proposes a bidirectional knowledge distillation framework called TSD-KD based on token selection, aiming to enhance the Chain-of-Thought generation capability of small models in complex reasoning tasks.

Explainable LLM Unlearning through Reasoning

Junfeng Liao (University of Technology Sydney), Zhen Fang (RIKEN Center for Advanced Intelligence Project)

CodeExplainability and InterpretabilityTransformerLarge Language ModelSupervised Fine-TuningTextBenchmark

🎯 What it does: Propose a reasoning-based unlearning target and a method named TRU that combines a supervised reasoning loss with a gradient ascent (GA) loss, aiming to specifically remove undesirable knowledge from large language models while preserving other model capabilities.

Explaining Grokking and Information Bottleneck through Neural Collapse Emergence

Keitaro Sakamoto (University of Tokyo), Issei Sato (University of Tokyo)

CodeOptimizationExplainability and InterpretabilityRepresentation LearningConvolutional Neural NetworkTransformerImage

🎯 What it does: By analyzing the 'neural collapse' phenomenon in the internal representations of neural networks, this paper provides a unified explanation for two late-stage training phenomena in deep learning: grokking (sudden improvement in generalization performance after training) and the information bottleneck (IB) compression phase.

Exploiting Low-Dimensional Manifold of Features for Few-Shot Whole Slide Image Classification

Conghao Xiong (Chinese University of Hong Kong), Irwin King (Chinese University of Hong Kong)

CodeClassificationRepresentation LearningMeta LearningImageBiomedical Data

🎯 What it does: To address few-shot pathological whole-slide image classification, the authors propose a geometry-aware Manifold Residual (MR) block, which fixes random projections to preserve the low-dimensional manifold structure of pre-trained features and learns task-specific adaptations through low-rank residual learning, significantly enhancing model generalization.

Exploratory Diffusion Model for Unsupervised Reinforcement Learning

Chengyang Ying (Tsinghua University), Jun Zhu (Tsinghua University)

CodeReinforcement LearningDiffusion modelScore-based Model

🎯 What it does: Propose a framework called Exploratory Diffusion Model (ExDM), which utilizes diffusion models to estimate the state distribution density in reward-free environments, generating score-based intrinsic rewards that guide agents to explore efficiently and pretrain diverse policies.

Explore-on-Graph: Incentivizing Autonomous Exploration of Large Language Models on Knowledge Graphs with Path-refined Reward Modeling

Shiqi Yan (Zhongguancun Laboratory), Yunqi Zhang (Zhongguancun Laboratory)

CodeExplainability and InterpretabilityReinforcement Learning from Human FeedbackGraph Neural NetworkLarge Language ModelSupervised Fine-TuningReinforcement LearningGraphBenchmarkChain-of-Thought

🎯 What it does: Propose a framework called EoG that encourages large language models to autonomously explore and discover new reasoning paths on knowledge graphs through reinforcement learning

Exploring Cross-Modal Flows for Few-Shot Learning

Ziqi Jiang (Hong Kong University of Science and Technology), Long Chen (Hong Kong University of Science and Technology)

CodeClassificationMeta LearningFlow-based ModelMultimodality

🎯 What it does: This paper proposes a multi-step feature alignment framework based on flow matching (Flow Matching Alignment, FMA) for cross-modal alignment and classification in few-shot vision-language models.

Exploring Interpretability for Visual Prompt Tuning with Cross-layer Concepts

Yubin Wang (Microsoft Research Asia), Cairong Zhao (Tongji University)

CodeClassificationExplainability and InterpretabilityTransformerPrompt EngineeringImage

🎯 What it does: Introduce interpretable cross-layer concept prototypes in visual prompt tuning to generate interpretable visual prompts corresponding to human-understandable concepts.

Exploring Real-Time Super-Resolution: Benchmarking and Fine-Tuning for Streaming Content

Evgeney Bogatyrev (Lomonosov Moscow State University), Dmitriy S. Vatolin (Lomonosov Moscow State University)

CodeSuper ResolutionComputational EfficiencyConvolutional Neural NetworkSupervised Fine-TuningVideoBenchmark

🎯 What it does: Proposed a StreamSR dataset containing 5,200 YouTube videos specifically for streaming compressed video, conducted benchmark testing of 11 real-time super-resolution models on this dataset, and subsequently designed and implemented the EfRLFN model, significantly improving the quality and efficiency of real-time super-resolution.

Exploring Synthesizable Chemical Space with Iterative Pathway Refinements

Seul Lee (Korea Advanced Institute Of Science And Technology), Arash Vahdat (NVIDIA)

CodeDrug DiscoveryTransformerFlow-based ModelBiomedical Data

🎯 What it does: Proposes the ReaSyn framework, achieving a synthetically feasible projection of a synthetically accessible chemical space through iterative bottom-up and top-down path generation combined with global editing.

Exploring the Potential of Encoder-free Architectures in 3D LMMs

Yiwen Tang (Shanghai AI Laboratory), Xuelong Li (Tele AI)

CodeClassificationRecognitionComputational EfficiencyRepresentation LearningTransformerLarge Language ModelPoint Cloud

🎯 What it does: This paper introduces an encoder-free architecture into 3D multimodal large models, proposes strategies such as LLM embedded semantic encoding and hierarchical geometric aggregation, and implements the ENEL model, completing the full training process from pre-training to instruction tuning.

ExPO-HM: Learning to Explain-then-Detect for Hateful Meme Detection

Jingbiao Mei (University of Cambridge), Bill Byrne (University of Cambridge)

CodeClassificationExplainability and InterpretabilityTransformerLarge Language ModelSupervised Fine-TuningReinforcement LearningVision Language ModelMultimodality

🎯 What it does: Proposed an explain-then-detect method for hateful meme detection called ExPO-HM.

EXPO: Stable Reinforcement Learning with Expressive Policies

Perry Dong (Stanford University), Chelsea Finn (Stanford University)

CodeReinforcement LearningDiffusion modelFlow-based ModelTabularSequential

🎯 What it does: This paper proposes EXPO, an algorithm that performs online reinforcement learning fine-tuning on expression strategies (e.g., diffusion, flow matching).

Exposing and Defending the Achilles' Heel of Video Mixture-of-Experts

Songping Wang (Nanjing University), Caifeng Shan (Nanjing University)

CodeClassificationAdversarial AttackMixture of ExpertsVideo

🎯 What it does: Propose temporal Lipschitz-guided attacks (TLGA, J-TLGA) targeting the router and expert components in video Mixture-of-Experts (MoE), revealing their independent and collaborative vulnerabilities, and design hierarchical joint adversarial training (J-TLAT) based on these weaknesses to enhance robustness.

Expressive Power of Implicit Models: Rich Equilibria and Test-Time Scaling

Jialin Liu (University of Central Florida), Wotao Yin (Alibaba)

CodeOptimizationImageTextTabularPhysics Related

🎯 What it does: Investigate the expressive power of implicit models, proving that they can achieve any local Lipschitz mapping through iteration.

ExpVid: A Benchmark for Experiment Video Understanding & Reasoning

Yicheng Xu (Shanghai AI Laboratory), Yi Wang (Shanghai AI Laboratory)

CodeTransformerLarge Language ModelVision Language ModelVideoTextMultimodalityBenchmark

🎯 What it does: Proposed the ExpVid benchmark specifically designed for scientific experiment videos, covering three-tier tasks of fine-grained perception, procedural understanding, and scientific reasoning.

Extending Sequence Length is Not All You Need: Effective Integration of Multimodal Signals for Gene Expression Prediction

Zhao Yang (Renmin University of China), Bing Su (Renmin University of China)

CodeMultimodalityBiomedical Data

🎯 What it does: This paper proposes the Prism framework, which can predict gene expression using short sequences by effectively integrating proximal multi-modal epigenetic signals.

Extreme Weather Nowcasting via Local Precipitation Pattern Prediction

Chang hoon Song, Youngjoon Hong (Seoul National University)

CodeComputational EfficiencyTransformerVideo

🎯 What it does: Proposes exPreCast, a deterministic radar forecasting framework based on video Swin Transformer, aiming to efficiently and finely predict extreme precipitation events;

FACM: Flow-Anchored Consistency Models

Yansong Peng (University of Science and Technology of China), Feng Wu (University of Science and Technology of China)

CodeGenerationDiffusion modelFlow-based ModelImageTextStochastic Differential Equation

🎯 What it does: Proposed and trained the Flow-Anchored Consistency Model (FACM), achieving efficient few-step generation by combining flow matching with a hybrid objective of continuous-time consistency models.

Fair Conformal Classification via Learning Representation-Based Groups

Senrong Xu (Nanjing University), Xiaoxing Ma (Nanjing University)

CodeClassificationRepresentation LearningAuto EncoderTabularBiomedical Data

🎯 What it does: Propose the FAREG method, using a variational information bottleneck encoder-decoder to learn subgroups in the latent representation space, and constructing an adaptive balanced coverage synthetic prediction set based on this.

Fair Decision Utility in Human-AI Collaboration: Interpretable Confidence Adjustment for Humans with Cognitive Disparities

Jiashi Gao (Southern University of Science and Technology), Xuetao Wei (Southern University of Science and Technology)

CodeExplainability and InterpretabilityImageTextTabular

🎯 What it does: This paper investigates the utility unfairness problem in human-AI collaborative decision-making caused by differences in human decision-makers' cognitive abilities, and proposes a new AI confidence adjustment objective called inter-group-alignment, along with a cognition-aware multicalibration method to achieve dual goals of fairness and optimal utility.

Fair Graph Machine Learning under Adversarial Missingness Processes

Debolina Halder Lina (Rice University), Arlei Silva (Rice University)

CodeOptimizationSafty and PrivacyGraph Neural NetworkGraph

🎯 What it does: To address the fairness issue of graph neural networks in scenarios with missing sensitive attributes (especially adversarial missingness), we propose the BFtS (Better Fair than Sorry) three-player adversarial framework, which improves the balance between model fairness and accuracy through worst-case sensitive attribute imputation.

FaithCoT-Bench: Benchmarking Instance-Level Faithfulness of Chain-of-Thought Reasoning

Xu Shen (Jilin University), Tianlong Chen (University of North Carolina at Chapel Hill)

CodeExplainability and InterpretabilityTextBenchmarkChain-of-Thought

🎯 What it does: Propose the FAITHCOT-BENCH framework, construct the expert-annotated FINE-COT dataset, and systematically evaluate instance-level CoT untrustworthiness detection methods.

Faithful Bi-Directional Model Steering via Distribution Matching and Distributed Interchange Interventions

Yuntai Bao (Zhejiang Normal University), Jianwei Yin (Zhejiang Normal University)

CodeExplainability and InterpretabilityComputational EfficiencyTransformerLarge Language ModelPrompt EngineeringTextBenchmark

🎯 What it does: This paper proposes a lightweight, interpretable bidirectional control method for LLMs based on distribution matching and distributed interactive intervention (CDAS).

Faithfulness Under the Distribution: A New Look at Attribution Evaluation

Zhiyu Zhu (University of Technology Sydney), Jianlong Zhou (University of Technology Sydney)

CodeExplainability and InterpretabilityConvolutional Neural NetworkTransformerDiffusion modelScore-based ModelImageStochastic Differential Equation

🎯 What it does: To assess the credibility of explanation methods, a novel distribution-aware evaluation framework named FUD is proposed. It utilizes a score diffusion model to reconstruct masked regions into data distribution samples while preserving important features, thereby eliminating biases caused by out-of-distribution (OOD) scenarios in traditional methods.

FakeXplain: AI-Generated Image Detection via Human-Aligned Grounded Reasoning

Yikun Ji (Shanghai Jiao Tong University), Jianfu Zhang (Shanghai Jiao Tong University)

CodeObject DetectionAnomaly DetectionExplainability and InterpretabilityLarge Language ModelSupervised Fine-TuningReinforcement LearningPrompt EngineeringVision Language ModelImageMultimodalityChain-of-Thought

🎯 What it does: Developed FakeXplainer, an explainable AI-generated image detection system capable of detecting, locating, and explaining forged images.

Falcon: Fast Proximal Linearization of Normalized Cuts for Unsupervised Image Segmentation

Xiao Zhang (University of Pennsylvania), Konrad Kording (University of Pennsylvania)

CodeSegmentationImageBenchmark

🎯 What it does: Propose Falcon, a primal gradient solver based on first-order approximation, directly optimizing the discrete K-way NCut objective, eliminating recursive bipartitioning and spectral relaxation processes, achieving unsupervised image segmentation.

FALCON: Few-step Accurate Likelihoods for Continuous Flows

Danyal Rehman (Mila - QuΓ©bec AI Institute), Alexander Tong (Mila - QuΓ©bec AI Institute)

CodeDrug DiscoveryTransformerFlow-based ModelBiomedical Data

🎯 What it does: Proposed FALCON, a few-step reversible continuous flow model, for efficient and accurate sampling from Boltzmann distributions.

FAME: Formal Abstract Minimal Explanation for Neural Networks

Ryma Boumazouza (Airbus SAS), Guy Katz (Hebrew University of Jerusalem)

CodeExplainability and InterpretabilityConvolutional Neural NetworkImage

🎯 What it does: Propose the FAME framework, which utilizes abstract interpretation to generate scalable formal minimal explanations;

FantasyWorld: Geometry-Consistent World Modeling via Unified Video and 3D Prediction

Yixiang Dai (AMAP Alibaba Group), Yonggang Qi (Beijing University Of Posts And Telecommunications)

CodeGenerationDiffusion modelWorld ModelVideoPoint Cloud

🎯 What it does: Proposed FANTASYWORLD, a unified forward network that can simultaneously generate video frames and implicit 3D representations in a single inference.

FARTrack: Fast Autoregressive Visual Tracking with High Performance

Guijie Wang (Xi'an Jiaotong University), Xing Wei (Xi'an Jiaotong University)

CodeObject TrackingKnowledge DistillationTransformerVideo

🎯 What it does: Designed and implemented a fast, high-performance multi-template autoregressive visual tracking framework called FARTrack for real-time tracking.

FASA: FREQUENCY-AWARE SPARSE ATTENTION

Yifei Wang (Alibaba Group), Julian McAuley (University of California San Diego)

CodeCompressionComputational EfficiencyTransformerLarge Language ModelTextSequential

🎯 What it does: This paper proposes FASA, a training-free, query-aware KV cache compression framework that dynamically predicts and removes unimportant tokens by leveraging the sparsity of frequency blocks (FC) in RoPE, followed by performing full attention computation only on the retained, limited number of tokens;

Fast and Stable Riemannian Metrics on SPD Manifolds via Cholesky Product Geometry

Ziheng Chen, Nicu Sebe (University of Trento)

CodeClassificationRecognition

🎯 What it does: Leverage Cholesky decomposition to reveal the product structure of SPD matrix space, and design two new Riemannian metricsβ€”Power-Cholesky Metric (PCM) and Bures-Wasserstein-Cholesky Metric (BWCM)β€”to provide closed-form, fast, and numerically stable geometric operations for SPD neural networks.

Fast Estimation of Wasserstein Distances via Regression on Sliced Wasserstein Distances

Khai Nguyen (University of Texas at Austin), Nhat Ho (University of Texas at Austin)

CodeOptimizationComputational EfficiencyPoint CloudBiomedical Data

🎯 What it does: Propose a framework for fast estimation of Wasserstein distance by regressing Wasserstein distance on sliced Wasserstein distance (SW);

Fast Frank–Wolfe Algorithms with Adaptive Bregman Step-Size for Weakly Convex Functions

Shota Takahashi (University of Tokyo), Akiko Takeda (University of Tokyo)

CodeOptimizationComputational Efficiency

🎯 What it does: Proposed an adaptive Bregman step size Frank-Wolfe algorithm applicable to L-smooth adaptable (L-smad) and weakly convex objective functions, providing linear convergence analysis for both convex and non-convex scenarios.

Fast Proteome-Scale Protein Interaction Retrieval via Residue-Level Factorization

Jianan Zhao (Mila - QuΓ©bec AI Institute), Jian Tang (Mila - QuΓ©bec AI Institute)

CodeRetrievalTransformerBiomedical Data

🎯 What it does: A fast protein interaction retrieval was achieved by constructing a factorizable residue-level interaction model.

FastAvatar: Towards Unified and Fast 3D Avatar Reconstruction with Large Gaussian Reconstruction Transformers

Yue Wu (Tongji University), Kairui Feng (Tongji University)

CodeGenerationPose EstimationTransformerDiffusion modelGaussian SplattingImageVideoPoint Cloud

🎯 What it does: Propose an end-to-end feed-forward 3D avatar reconstruction framework called FastAvatar, which can rapidly generate high-quality animatable 3D Gaussian Splatting (3DGS) models from any number of images or video frames, and supports progressive incremental reconstruction.

Fastcar: Cache Attentive Replay for Fast Auto-Regressive Video Generation on the Edge

Xuan Shen (Northeastern University), Jiuxiang Gu (Adobe)

CodeGenerationTransformerVideo

🎯 What it does: Propose the FastCar framework, which utilizes temporal redundancy in autoregressive video generation by caching and replaying the MLP output of the previous frame to significantly reduce computational costs; and implement a dynamic resource scheduling hardware accelerator on FPGA;

Faster Gradient Methods for Highly-smooth Stochastic Bilevel Optimization

Lesi Chen (Tsinghua University & Shanghai Qizhi Institute), Jingzhao Zhang (Tsinghua University & Shanghai Qizhi Institute)

CodeOptimizationText

🎯 What it does: This paper studies fully gradient-based stochastic bilevel optimization algorithms and proposes the FSA^p method, which achieves faster convergence speeds by approximating the supergradient using high-order finite differences.

FastFlow: Accelerating The Generative Flow Matching Models with Bandit Inference

Divya Jyoti Bajpai (Indian Institute of Technology Bombay), Manjesh Kumar Hanawal (Indian Institute of Technology Bombay)

CodeGenerationComputational EfficiencyFlow-based ModelImageVideoTextOrdinary Differential Equation

🎯 What it does: Significantly accelerate generation by adaptively skipping redundant denoising steps during the inference of flow matching models, using a multi-armed bandit to determine when to approximate.

FastGRPO: Accelerating Policy Optimization via Concurrency-aware Speculative Decoding and Online Draft Learning

Yizhou Zhang (Lanzhou University), Jisheng Dang (Lanzhou University)

CodeOptimizationComputational EfficiencyLarge Language ModelReinforcement LearningText

🎯 What it does: Significantly improved the throughput during the generation phase by introducing concurrent-aware speculative decoding and online draft model learning in GRPO training, thereby accelerating the overall training process.

FATE: A Formal Benchmark Series for Frontier Algebra of Multiple Difficulty Levels

Jiedong Jiang (Westlake University), Bin Dong (Peking University)

CodeAI Code AssistantLarge Language ModelTextBenchmark

🎯 What it does: This study proposes the FATE (Formal Algebra Theorem Evaluation) benchmark series, focusing on constructing two new difficulty levelsβ€”FATE-H (undergraduate to graduate level) and FATE-X (doctoral qualifying exams and above)β€”to assess the capability of large language models in formal algebraic proofs; and reveals the bottlenecks in the formalization process through a two-phase evaluation (first natural language reasoning, then conversion to Lean code).

Fathom-DeepResearch: Unlocking Long Horizon Information Retrieval and Synthesis for SLMs

Shreyas Singh (Fractal AI Research), Pradeep Moturi (Fractal AI Research)

CodeGenerationData SynthesisRetrievalTransformerLarge Language ModelSupervised Fine-TuningReinforcement LearningTextRetrieval-Augmented GenerationChain-of-Thought

🎯 What it does: Built a two-model proxy system Fathom-DeepResearch, including a specialized search inference model Fathom-Search-4B and a structured report generation model Fathom-Synthesizer-4B;

FeDaL: Federated Dataset Learning for General Time Series Foundation Models

Shengchao Chen (University of Technology Sydney), Jing Jiang (University of Technology Sydney)

CodeAnomaly DetectionFederated LearningTransformerTime Series

🎯 What it does: Proposes FeDaL, a federated learning framework for time series foundation models, capable of training models from scratch that can achieve cross-domain generalization on distributed and heterogeneous datasets.

Federated Learning with Profile Mapping under Distribution Shifts and Drifts

Mohan Li (UniversitΓ  della Svizzera italiana), Marc Langheinrich (UniversitΓ  della Svizzera italiana)

CodeFederated LearningSafty and PrivacyImageBiomedical Data

🎯 What it does: Propose the FEROMA framework, which utilizes differential privacy distribution summaries to map federated learning distributions, dynamically selects aggregation strategies, handles distribution shifts and drifts during both training and testing phases, and supports model allocation for unlabelled clients.

FedOpenMatch: Towards Semi-Supervised Federated Learning in Open-Set Environments

Hongquan Liu (Fudan University), Shuigeng Zhou (Fudan University)

CodeClassificationAnomaly DetectionFederated LearningImageBenchmark

🎯 What it does: Proposed and implemented the first framework for open-set semi-supervised federated learning (OSSFL), FedOpenMatch, which can simultaneously handle samples from both known classes and unknown classes in the unlabeled data distributed across clients;

FERD: Fairness-Enhanced Data-Free Adversarial Robustness Distillation

Zhengxiao Li (Nanjing University of Science and Technology), Shuchao Pang (Nanjing University of Science and Technology)

CodeKnowledge DistillationConvolutional Neural NetworkImage

🎯 What it does: Studied the fairness issue in data-free robustness distillation and proposed the FERD framework to enhance the robust fairness of student models

Fewer Battles, More Gain: An Information-Efficient Framework for Arena-based LLM Evaluation

Zirui Liu (University of Science and Technology of China), Shijin Wang (iFLYTEK Co., Ltd)

CodeOptimizationComputational EfficiencyText

🎯 What it does: Propose an adaptive model pair selection framework based on Fisher information, using A-optimality and D-optimality to iteratively select the most informative model pairs, significantly reducing the number of required matches for evaluation;

Fewer Weights, More Problems: A Practical Attack on LLM Pruning

Kazuki Egashira (ETH Zurich), Martin Vechev (ETH Zurich)

CodeAdversarial AttackTransformerLarge Language ModelSupervised Fine-TuningText

🎯 What it does: Proposes an attack method that leverages LLM pruning to activate malicious behaviors;

FideDiff: Efficient Diffusion Model for High-Fidelity Image Motion Deblurring

Xiaoyang Liu (Shanghai Jiao Tong University), Yulun Zhang (Shanghai Jiao Tong University)

CodeRestorationDiffusion modelAuto EncoderGenerative Adversarial NetworkImage

🎯 What it does: Proposed a single-step high-fidelity motion deblurring diffusion model called FideDiff, achieving one-time restoration during inference.

Fine-Grained Activation Steering: Steering Less, Achieving More

Zijian Feng (Nanyang Technological University), Kezhi Mao (Nanyang Technological University)

CodeTransformerLarge Language ModelContrastive LearningText

🎯 What it does: Investigated and demonstrated the heterogeneity of block-level activation in large language models (LLMs), proposing a fine-grained atomic unit (AU)-level activation modulation method called AUSteer;

Fine-Grained Class-Conditional Distribution Balancing for Debiased Learning

Miaoyun Zhao (Dalian University of Technology), Qiang Zhang (Dalian University of Technology)

CodeDomain AdaptationImageText

🎯 What it does: Proposes an unbiased annotation bias exploration and fine-grained class-conditional distribution balancing (FG-CCDB) method to achieve robust group-level generalization in the presence of spurious correlations.

Fine-R1: Make Multi-modal LLMs Excel in Fine-Grained Visual Recognition by Chain-of-Thought Reasoning

Hulingxiao He (Peking University), Yuxin Peng (Peking University)

CodeRecognitionTransformerLarge Language ModelSupervised Fine-TuningReinforcement LearningVision Language ModelContrastive LearningImageTextMultimodalityChain-of-Thought

🎯 What it does: Designed and trained a multimodal large language model, Fine-R1, for fine-grained visual recognition (FGVR), enabling it to identify both known and unknown subcategories with a small number of training samples.

Fine-tuning Behavioral Cloning Policies with Preference‑Based Reinforcement Learning

Mael Macuglia (University of Zurich), Giorgia Ramponi (University of Zurich)

CodeOptimizationReinforcement Learning from Human FeedbackSupervised Fine-TuningReinforcement LearningSequential

🎯 What it does: Integrate offline expert demonstrations with online preference feedback, proposing the BRIDGE algorithm. By constructing a Hellinger confidence ball to constrain online search, it achieves safe and efficient behavior cloning fine-tuning.

Fine-tuning Done Right in Model Editing

Wanli Yang (Institute of Computing Technology, Chinese Academy of Sciences), Fei Sun (Institute of Computing Technology, Chinese Academy of Sciences)

CodeComputational EfficiencyTransformerLarge Language ModelSupervised Fine-TuningText

🎯 What it does: Re-evaluated and corrected the implementation of fine-tuning in model editing, transforming it into a standard breadth-first (BF) training pipeline combined with local parameter fine-tuning, and proposed the LocFT-BF method;

Fine-tuning Quantized Neural Networks with Zeroth-order Optimization

Sifeng SHANG, Kaiyang Zhou (Hong Kong Baptist University)

CodeOptimizationComputational EfficiencyTransformerSupervised Fine-TuningDiffusion modelImageText

🎯 What it does: Propose a method called Quantized Zeroth-order Optimization (QZO) for fine-tuning quantized large language models (LLMs), achieving extreme memory compression by only updating the quantization scale and eliminating gradients and optimizer states.

FingerTip 20K: A Benchmark for Proactive and Personalized Mobile LLM Agents

Qinglong Yang (Tsinghua University), Yong Li (Tsinghua University)

CodeTransformerLarge Language ModelSupervised Fine-TuningAgentic AIPrompt EngineeringImageTextSequentialBenchmark

🎯 What it does: This paper proposes the FingerTip 20K benchmark to evaluate the capabilities of mobile large language model agents in proactive task suggestion and personalized task execution, and constructs the dataset by collecting 20,000 real user multi-step Android interaction examples.

Fixing the Broken Compass: Diagnosing and Improving Inference-Time Reward Modeling

Jiachun Li (University of Chinese Academy of Sciences), Jun Zhao (University of Chinese Academy of Sciences)

CodeComputational EfficiencyReinforcement Learning from Human FeedbackTransformerLarge Language ModelTextBenchmark

🎯 What it does: Proposed a reward model-based reasoning acceleration algorithm called CRISP, which enhances LLM inference effectiveness through answer clustering, reward aggregation, and step-by-step prefix guidance.

Flash-Searcher: Fast and Effective Web Agents via DAG-Based Parallel Execution

Tianrui Qin (OPPO AI Center), Wangchunshu Zhou (OPPO Reseach Institute)

CodeComputational EfficiencyKnowledge DistillationTransformerLarge Language ModelAgentic AITextTabularBenchmark

🎯 What it does: Propose the Flash-Searcher framework, which utilizes a DAG structure to decompose complex tasks into parallelizable subtasks, achieving efficient Web Agent reasoning through multi-path parallel inference and tool calls.

FlashDLM: Accelerating Diffusion Language Model Inference via Efficient KV Caching and Guided Diffusion

Zhanqiu Hu (Cornell University), Udit Gupta (Cornell University)

CodeComputational EfficiencyTransformerLarge Language ModelDiffusion modelText

🎯 What it does: Propose two training-agnostic acceleration methods: FreeCache uses KV caching to reduce redundant computations in DLM inference, while Guided Diffusion employs a lightweight AR model to provide consistency guidance during the diffusion process, thereby reducing denoising steps and improving parallel generation efficiency.

FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging

Ziyang Fan (Harbin Institute of Technology), Zhuotao Tian (Harbin Institute of Technology)

CodeCompressionComputational EfficiencyTransformerVision Language ModelVideoMultimodality

🎯 What it does: Proposed FlashVID, a training-agnostic, plug-and-play acceleration framework that leverages attention + diversity screening and tree-structured spatiotemporal merging to significantly compress video visual tokens, achieving efficient inference.

FlashWorld: High-quality 3D Scene Generation within Seconds

Xinyang Li (Xiamen University), Liujuan Cao (Tencent)

CodeGenerationData SynthesisTransformerDiffusion modelGaussian SplattingImageVideoTextMultimodality

🎯 What it does: Propose FlashWorld, a 3D scene generation framework based on dual-mode pre-training and cross-modal fine-tuning;

Flatter Tokens are More Valuable for Speculative Draft Model Training

Jiaming Fan (Southeast University), Xu Yang (Southeast University)

CodeComputational EfficiencyKnowledge DistillationTransformerLarge Language ModelText

🎯 What it does: Studied speculative decoding for accelerating large language model inference, proposing a data selection method based on 'flatness' to enhance the training efficiency of the draft model.