{"total":109,"rows":[{"id":"2605.28091","title":"Qwen-Image-Bench: From Generation to Creation in Text-to-Image Evaluation","created":"2026-05-27","cited_by_count":22,"area":null},{"id":"2511.00391","title":"VinciCoder: Unifying Multimodal Code Generation via Coarse-to-fine Visual Reinforcement Learning","created":"2025-11-01","cited_by_count":21,"area":null},{"id":"2503.23907","title":"HumanAesExpert: Advancing a Multi-Modality Foundation Model for Human Image Aesthetic Assessment","created":"2025-03-31","cited_by_count":19,"area":null},{"id":"2506.03930","title":"VisCoder: Fine-Tuning LLMs for Executable Python Visualization Code Generation","created":"2025-06-04","cited_by_count":17,"area":null},{"id":"2412.11892","title":"From 2D CAD Drawings to 3D Parametric Models: A Vision-Language Approach","created":"2024-12-16","cited_by_count":15,"area":null},{"id":"2602.11164","title":"Automated Optimization Modeling via a Localizable Error-Driven Perspective","created":"2026-01-17","cited_by_count":14,"area":null},{"id":"2502.04380","title":"Diversity as a Reward: Fine-Tuning LLMs on a Mixture of Domain-Undetermined Data","created":"2025-02-05","cited_by_count":13,"area":null},{"id":"2411.11027","title":"BianCang: A Traditional Chinese Medicine Large Language Model","created":"2024-11-17","cited_by_count":12,"area":null},{"id":"2603.14473","title":"AI Can Learn Scientific Taste","created":"2026-03-15","cited_by_count":11,"area":null},{"id":"2508.01742","title":"Intention-Guided Cognitive Reasoning for Egocentric Long-Term Action Anticipation","created":"2025-08-03","cited_by_count":10,"area":null},{"id":"2606.13368","title":"IterCAD: An Iterative Multimodal Agent for Visually-Grounded CAD Generation and Editing","created":"2026-06-11","cited_by_count":10,"area":null},{"id":"2504.16427","title":"Can Large Language Models Help Multimodal Language Analysis? MMLA: A Comprehensive Benchmark","created":"2025-04-23","cited_by_count":9,"area":null},{"id":"2504.21356","title":"Nexus-Gen: Unified Image Understanding, Generation, and Editing via Prefilled Autoregression in Shared Embedding Space","created":"2025-04-30","cited_by_count":9,"area":null},{"id":"2506.21101","title":"OracleFusion: Assisting the Decipherment of Oracle Bone Script with Structurally Constrained Semantic Typography","created":"2025-06-26","cited_by_count":8,"area":null},{"id":"2509.19090","title":"Citrus-V: Advancing Medical Foundation Models with Unified Medical Image Grounding for Clinical Reasoning","created":"2025-09-23","cited_by_count":8,"area":null},{"id":"2512.14754","title":"Revisiting the Reliability of Language Models in Instruction-Following","created":"2025-12-15","cited_by_count":7,"area":null},{"id":"2502.08168","title":"SARChat-Bench-2M: A Multi-Task Vision-Language Benchmark for SAR Image Interpretation","created":"2025-02-12","cited_by_count":5,"area":null},{"id":"2603.09677","title":"Logics-Parsing-Omni Technical Report","created":"2026-03-10","cited_by_count":5,"area":null},{"id":"2605.10343","title":"EvoStreaming: Your Offline Video Model Is a Natively Streaming Assistant","created":"2026-05-11","cited_by_count":5,"area":null},{"id":"2505.22296","title":"360-LLaMA-Factory: Plug & Play Sequence Parallelism for Long Post-Training","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2506.08524","title":"Teaching Physical Awareness to LLMs through Sounds","created":"2025-06-10","cited_by_count":4,"area":null},{"id":"2506.12450","title":"Language Surgery in Multilingual Large Language Models","created":"2025-06-14","cited_by_count":4,"area":null},{"id":"2510.03666","title":"MonitorVLM:A Vision Language Framework for Safety Violation Detection in Mining Operations","created":"2025-10-04","cited_by_count":4,"area":null},{"id":"2604.05514","title":"OmniDiagram: Advancing Unified Diagram Code Generation via Visual Interrogation Reward","created":"2026-04-07","cited_by_count":4,"area":null},{"id":"2604.07837","title":"SPARD: Self-Paced Curriculum for RL Alignment via Integrating Reward Dynamics and Data Utility","created":"2026-04-09","cited_by_count":4,"area":null},{"id":"2511.21714","title":"GPS: General Per-Sample Prompter","created":"2025-11-18","cited_by_count":3,"area":null},{"id":"2512.22827","title":"FasterPy: An LLM-based Code Execution Efficiency Optimization Framework","created":"2025-12-28","cited_by_count":3,"area":null},{"id":"2603.02951","title":"CGL: Advancing Continual GUI Learning via Reinforcement Fine-Tuning","created":"2026-03-03","cited_by_count":3,"area":null},{"id":"2512.11013","title":"PIAST: Rapid Prompting with In-context Augmentation for Scarce Training data","created":"2025-12-11","cited_by_count":2,"area":null},{"id":"2601.13097","title":"RM -RF: Reward Model for Run-Free Unit Test Evaluation","created":"2026-01-19","cited_by_count":2,"area":null},{"id":"2605.21295","title":"TimeSRL: Generalizable Time-Series Behavioral Modeling via Semantic RL-Tuned LLMs -- A Case Study in Mental Health","created":"2026-05-20","cited_by_count":2,"area":null},{"id":"2605.30219","title":"When Should Models Change Their Minds? Contextual Belief Management in Large Language Models","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2606.24441","title":"S1-Omni-Image: A Unified Model for Scientific Image Understanding, Generation, and Editing","created":"2026-06-23","cited_by_count":2,"area":null},{"id":"2607.27756","title":"Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO","created":"2026-07-30","cited_by_count":2,"area":null},{"id":"2509.01221","title":"DaMoC: Efficiently Selecting the Optimal Large Language Model for Fine-tuning Domain Tasks Based on Data and Model Compression","created":"2025-09-01","cited_by_count":1,"area":null},{"id":"2509.24229","title":"Model Fusion with Multi-LoRA Inference for Tool-Enhanced Game Dialogue Agents","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2510.09297","title":"ShiZhi: A Chinese Lightweight Large Language Model for Court View Generation","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2510.17332","title":"iDETEX: Empowering MLLMs for Intelligent DETailed EXplainable IQA","created":"2025-10-20","cited_by_count":1,"area":null},{"id":"2512.05524","title":"VOST-SGG: VLM-Aided One-Stage Spatio-Temporal Scene Graph Generation","created":"2025-12-05","cited_by_count":1,"area":null},{"id":"2512.22603","title":"Structured Prompting and LLM Ensembling for Multimodal Conversational Aspect-based Sentiment Analysis","created":"2025-12-27","cited_by_count":1,"area":null},{"id":"2602.22584","title":"Towards Faithful Industrial RAG: A Reinforced Co-adaptation Framework for Advertising QA","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2603.22267","title":"TiCo: Time-Controllable Spoken Dialogue Model","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2603.22276","title":"Scaling DoRA: High-Rank Adaptation via Factored Norms and Fused Kernels","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2604.16881","title":"Incentivizing Parametric Knowledge via Reinforcement Learning with Verifiable Rewards for Cross-Cultural Entity Translation","created":"2026-04-18","cited_by_count":1,"area":null},{"id":"2604.20146","title":"SAKE: Self-aware Knowledge Exploitation-Exploration for Grounded Multimodal Named Entity Recognition","created":"2026-04-22","cited_by_count":1,"area":null},{"id":"2604.20878","title":"AITP: Traffic Accident Responsibility Allocation via Multimodal Large Language Models","created":"2026-04-11","cited_by_count":1,"area":null},{"id":"2605.01250","title":"EO-Gym: A Multimodal, Interactive Environment for Earth Observation Agents","created":"2026-05-02","cited_by_count":1,"area":null},{"id":"2605.22501","title":"BeLink: Biomedical Entity Linking Meets Generative Re-Ranking","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2605.22715","title":"AnyMo: Geometry-Aware Setup-Agnostic Modeling of Human Motion in the Wild","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2605.30899","title":"A Unified and Reproducible Experimentation Framework for Speech Understanding","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2606.15037","title":"ReportQA: QA-Based Radiology Report Evaluation","created":"2026-06-13","cited_by_count":1,"area":null},{"id":"2606.24162","title":"BehaviorBench: Benchmarking Foundation Models for Behavioral Science Tasks","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2607.05090","title":"Be Indiscrete: The Benefits of Learning Continuous Spine Degeneration Severity Scores","created":"2026-07-06","cited_by_count":1,"area":null},{"id":"2607.28073","title":"GVR-Coder: A Visual-Feedback Framework for Structured SVG Generation in Complex Document and Meeting Scenarios","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2608.08557","title":"OpenVisTool: An Open Recipe for Synthesizing Instructive Visual Tool-Use Trajectories","created":"2026-08-09","cited_by_count":1,"area":null},{"id":"2608.18689","title":"Aslema at NADI 2026: Data Augmentation for Intent Recognition and Slot Filling","created":"2026-08-19","cited_by_count":1,"area":null},{"id":"2608.30204","title":"When Models Hear What They Expect: Diagnosing Prosodic Heuristics in Multimodal Sarcasm Detection","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2609.01591","title":"StudentSim: Training LLM-based Student Simulators","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2609.05141","title":"SciDocBench: A Workflow-Centered Benchmark and Data Pipeline for Scientific Document Understanding","created":"2026-09-04","cited_by_count":1,"area":null},{"id":"2609.10992","title":"Demystifying the Privacy-Utility Trade-off in LLM Interactions","created":"2026-09-10","cited_by_count":1,"area":null},{"id":"2409.07482","title":"VSLLaVA: a pipeline of large multimodal foundation model for industrial vibration signal analysis","created":"2024-09-03","cited_by_count":0,"area":null},{"id":"2511.16470","title":"Arctic-Extract Technical Report","created":"2025-11-20","cited_by_count":0,"area":null},{"id":"2511.22466","title":"RoadSceneBench: A Lightweight Benchmark for Mid-Level Road Scene Understanding","created":"2025-11-27","cited_by_count":0,"area":null},{"id":"2512.02816","title":"A benchmark dataset for evaluating Syndrome Differentiation and Treatment in large language models","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2512.11321","title":"KeyframeFace: Language-Driven Facial Animation via Semantic Keyframes","created":"2025-12-12","cited_by_count":0,"area":null},{"id":"2512.20032","title":"VALLR-Pin: Uncertainty-Factorized Visual Speech Recognition for Mandarin with Pinyin Guidance","created":"2025-12-23","cited_by_count":0,"area":null},{"id":"2601.12392","title":"Psych\\=eChat: An Empathic Framework Focused on Emotion Shift Tracking and Safety Risk Analysis in Psychological Counseling","created":"2026-01-18","cited_by_count":0,"area":null},{"id":"2601.13995","title":"From Tags to Trees: Structuring Fine-Grained Knowledge for Controllable Data Selection in LLM Instruction Tuning","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2603.05275","title":"SarcasmMiner: A Dual-Track Post-Training Framework for Robust Audio-Visual Sarcasm Reasoning","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2603.12983","title":"Is Human Annotation Necessary? Iterative MBR Distillation for Error Span Detection in Machine Translation","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2603.28474","title":"CiQi-Agent: Aligning Vision, Tools and Aesthetics in Multimodal Agent for Cultural Reasoning on Chinese Porcelains","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2603.29897","title":"UniRank: End-to-End Domain-Specific Reranking of Hybrid Text-Image Candidates","created":"2026-02-08","cited_by_count":0,"area":null},{"id":"2604.06098","title":"JU\\'A -- A Benchmark for Information Retrieval in Brazilian Legal Text Collections","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.13847","title":"SparseBalance: Load-Balanced Long Context Training with Dynamic Sparse Attention","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2604.15871","title":"UniEditBench: A Unified and Cost-Effective Benchmark for Image and Video Editing via Distilled MLLMs","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2604.19124","title":"Detoxification for LLM: From Dataset Itself","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2604.21414","title":"SemanticAgent: A Semantics-Aware Framework for Text-to-SQL Data Synthesis","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2605.12022","title":"SAGE: Scalable Automated Robustness Augmentation for LLM Knowledge Evaluation","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.26967","title":"CodecCap: High-Fidelity Codec-Inspired Residual Modeling for Dense Video Captioning","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2605.28109","title":"Long Live The Balance: Information Bottleneck Driven Tree-based Policy Optimization","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2605.30639","title":"PInVerify: An Offline Embodied Benchmark for Active Instance Verification","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.01304","title":"When Hard Negatives Hurt: Bridging the Generative-Discriminative Gap in Hard Negative Synthesis for Retrieval","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2606.04591","title":"Fine-grained Fragment Retrieval in Multi-modal Long-form Dialogues","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.09278","title":"Internalizing Geometric Law: Learning from Solver Residuals for Precision-Critical Generation","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.15663","title":"OneFocus: Enabling Real-World X-ray Security Screening with a Unified Vision-Language Model","created":"2026-06-14","cited_by_count":0,"area":null},{"id":"2606.17436","title":"UoU: A Universal Fingerprint Foundation Model Based on Large-Scale Unsupervised Learning","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2606.17871","title":"StepGuard: Guarding Web Navigation via Single-Step Calibration","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2607.17230","title":"Robust Summarization of Doctor-Patient Conversations: TalTech Systems for the Beyond Transcription Challenge","created":"2026-07-19","cited_by_count":0,"area":null},{"id":"2607.18997","title":"Benchmarking Deep Learning Approaches for AEC Engineering Drawing Layout Detection and Information Extraction","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2607.19847","title":"Auto-Fill: Learning to Predict Missing Values Accurately with Specialist Language Models","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2607.27122","title":"Towards Grounded GI Endoscopy VQA via Multi-Task Learning on Small VLMs","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.10764","title":"FADE: From Passive Verification to Active Discovery in Counterfactual Video Understanding","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.19920","title":"Learning how to Forget: Fine-tuning for Long-Context Sparse Attention","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2608.21180","title":"Toward Vision Language Model-based Assessment of Clinical Quality and Usability of LGE-MR Images for Cardiac Ablation Planning","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2608.23329","title":"Thinking Beyond Videos: Unifying Video Reasoning and Deep Research for Open-World Video Agents","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.23391","title":"Cross-Domain, Multi-Task Data-to-Text Generation without In-Domain Training Data","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.26495","title":"Video-FLAIR: Not Whether to Reason, But How","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.01422","title":"From Rollouts to Recipes: Self-Contained Post-Training for LLMs","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.11724","title":"The Eloquence submission for Task 2 of the Interspeech 2026 MLC-SLM challenge","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.14467","title":"Bridging the Modality Gap in Long-Form Clinical Audio: A Comparative Study of Lightweight and Heavyweight End-to-End SOAP Generation","created":"2026-09-13","cited_by_count":0,"area":null}],"next_cursor":"100"}