{"total":56,"rows":[{"id":"2602.12205","title":"DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing","created":"2026-02-12","cited_by_count":14,"area":null},{"id":"2606.14777","title":"JoyAI-VL-Interaction: Real-Time Vision-Language Interaction Intelligence","created":"2026-06-10","cited_by_count":14,"area":null},{"id":"2605.04128","title":"JoyAI-Image: Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation","created":"2026-05-05","cited_by_count":12,"area":null},{"id":"2605.20164","title":"Not Every Rubric Teaches Equally: Policy-Aware Rubric Rewards for RLVR","created":"2026-05-19","cited_by_count":11,"area":null},{"id":"2606.11167","title":"Multi-Faceted Interactivity Alignment in Full-Duplex Speech Models","created":"2026-06-09","cited_by_count":10,"area":null},{"id":"2605.22817","title":"Vector Policy Optimization: Training for Diversity Improves Test-Time Search","created":"2026-05-21","cited_by_count":8,"area":null},{"id":"2602.22732","title":"Generative Recommendation for Large-Scale Advertising","created":"2026-02-26","cited_by_count":7,"area":null},{"id":"2605.12480","title":"OmniNFT: Modality-wise Omni Diffusion Reinforcement for Joint Audio-Video Generation","created":"2026-05-12","cited_by_count":7,"area":null},{"id":"2605.13803","title":"EvoGround: Self-Evolving Video Agents for Video Temporal Grounding","created":"2026-05-13","cited_by_count":4,"area":null},{"id":"2605.00015","title":"TimeRFT: Stimulating Generalizable Time Series Forecasting for TSFMs via Reinforcement Finetuning","created":"2026-04-18","cited_by_count":3,"area":null},{"id":"2605.13467","title":"PDCR: Perception-Decomposed Confidence Reward for Vision-Language Reasoning","created":"2026-05-13","cited_by_count":3,"area":null},{"id":"2606.26947","title":"Scaling Multi-Reference Image Generation with Dynamic Reward Optimization","created":"2026-06-25","cited_by_count":3,"area":null},{"id":"2605.07394","title":"BalCapRL: A Balanced Framework for RL-Based MLLM Image Captioning","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2606.31711","title":"Arena-T2I Hard: Benchmarking and Improving Faithfulness with Dependency-Aware Checklist","created":"2026-06-30","cited_by_count":2,"area":null},{"id":"2608.07565","title":"What to Edit Next: Visually Aligned Image-Editing Follow-Up Suggestions in Conversational Systems","created":"2026-08-03","cited_by_count":2,"area":null},{"id":"2601.22648","title":"UCPO: Uncertainty-Aware Policy Optimization","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2602.10609","title":"Online Causal Kalman Filtering for Stable and Effective Policy Optimization","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2604.06159","title":"Target Policy Optimization","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2605.07244","title":"Experience Sharing in Mutual Reinforcement Learning for Heterogeneous Language Models","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.18899","title":"Don't Let Bandit Feedback Pull Continual LLM-Recommender Updates Off Target","created":"2026-05-17","cited_by_count":1,"area":null},{"id":"2605.23281","title":"DepthAgent: Towards Better Universal Depth Estimation via Sample-wise Expert Selection","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2606.05671","title":"QueryAgent-R1: Bridging Query Generation and Product Retrieval for E-Commerce Query Recommendation","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2609.07072","title":"Detect Anything in Graphic Design: Element-Level Rewards for Autoregressive Detection","created":"2026-09-07","cited_by_count":1,"area":null},{"id":"2609.19164","title":"Advantage Scale Calibration Imbalance in Group-Relative Optimization under Low-Variance Rewards: Diagnosis and Bounded Recovery","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2603.26610","title":"Think over Trajectories: Leveraging Video Generation to Reconstruct GPS Trajectories from Cellular Signaling","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2604.23061","title":"C-MORAL: Controllable Multi-Objective Molecular Optimization with Reinforcement Alignment for LLMs","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2606.19103","title":"ProductConsistency: Improving Product Identity Preservation in Instruction-Based Image Editing via SFT and RL","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2606.21447","title":"Precision Recall Controllable Radiology Report Generation via Hybrid Natural Language and Clinical Reward Learning","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2607.01849","title":"Decomposer: Learning to Decompile Symbolic Music to Programs","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.26515","title":"HiFloat4 Format for End-To-End Reinforcement Learning Post-Training of Large Language Models","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.06778","title":"Retrieval-Constrained Policy Optimization for Attack Technique Extraction from Cyber Threat Intelligence","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.10714","title":"Conversational Orchestration for Organic 6G","created":"2026-08-11","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":"2608.17713","title":"Cross-View Correspondence Is a Measurement Intervention: Two-Sided Validation for Agent Evaluation and Credit Assignment","created":"2026-08-18","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":"2609.02250","title":"RideSkill: A Hierarchical Algorithm for Generalized Ride Sharing with LLM-Driven Automatic Evolution","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.03206","title":"Learning to Zoom Efficiently with a Contrastive Curriculum","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.12623","title":"SteerDuplex: Steerable Duplex Speech Dialogue Models","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.23457","title":"RLVR$^{2}$: Reinforcement Learning with Verifiable Rubric-based Ranking","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.29816","title":"AV-GRPO: Modality-Anchored Decoupling Diffusion Reinforcement Learning for Joint Audio-Video Generation","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.32019","title":"Decentralized Master-Mind: Joint Action Refinement through Iterative Intent Denoising in Multi-Agent Pathfinding","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.36190","title":"FigAct: Turning Scientific Figures into Active Canvases for Explanation","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36934","title":"VLALight: A Vision-Language-Action Model for Traffic Signal Control","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.37035","title":"Watch-Think-Interact: Bootstrapping Long-Horizon Multi-Turn Streaming Video Reasoning with Reinforcement Learning","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38397","title":"SimTrace: Grounded Multimodal User Trajectories Generation for Online User Modeling","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39055","title":"The Missing Coefficients: Bayesian Pairwise Merging for Model Personalization","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.39088","title":"SCIC: Scope- and Codebook-Aware Instruction Conditioning for Speaker-Adapted Expressive TTS","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.39383","title":"From Search to Signal: Online Post-Training in Automatic Heuristic Design","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.00389","title":"MatrixReward: Reward from Rubric Matrix for Open-Ended Generation","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.00574","title":"Make Sparse Rewards Count: Density-Aware Reward Aggregation for Multi-Reward RL","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.02197","title":"HiPhy: Hierarchical Alignment for Physically-Plausible Multi-Principle Video Generation","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.06021","title":"Scalable Minimal-Change Learning for Controllable Image Editing","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.16441","title":"VisExMEM: Visual Evidence-Based Explainable Multimodal Evaluation Metric","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.18860","title":"AesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.19705","title":"RouteWeaver: Weaving Mode Selection and Execution into Unified LLM Routing","created":"2026-10-14","cited_by_count":0,"area":null},{"id":"2610.20261","title":"Harness Policy Distillation: Aligning Agent Policies with Runtime Semantics","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}