Momentum-Coupled Rubric Adaptation for Detailed Image Captioning

arXiv:2609.36893 · cs.CL · Submitted 2026-09-29 · Read on arXiv

cs.CL

Submitted: 2026-09-29

Updated: 2026-09-29

Code: https://github.com/a23wen/MoCo-Rubric

Terminology

• Benchmark — 17× in this paper · explained in 2 episodes
• Hallucination — 14× in this paper · explained in 3 episodes
• Reinforcement Learning — 14× in this paper · explained in 4 episodes
• Accuracy — 12× in this paper · explained in 1 episode
• Adaptation — 12× in this paper · explained in 1 episode
• GRPO — 11× in this paper · explained in 6 episodes
• Momentum transfer — 10× in this paper · explained in 2 episodes
• LLM judge — 6× in this paper · explained in 2 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Benchmarking — 3× in this paper · explained in 3 episodes
• Commentary — 3× in this paper · explained in 2 episodes
• Fine-Tuning — 3× in this paper · explained in 5 episodes
• Aggregation — 2× in this paper · explained in 1 episode
• Alignment — 2× in this paper · explained in 1 episode
• Consistency — 2× in this paper · explained in 3 episodes
• Frustration — 2× in this paper · explained in 2 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Decoupling — 1× in this paper · explained in 2 episodes
• Exponential Moving Average (EMA) — 1× in this paper · explained in 2 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Two-Stage Framework — 1× in this paper · explained in 2 episodes
• Verifiable Rewards — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• SPICE: Semantic Propositional Image Caption Evaluation
• Qwen3-VL Technical Report
• DecisionFlow: Advancing Large Language Model as Principled Decision Maker
• CapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era
• Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models
• Benchmarking and Improving Detail Image Caption
• BLINK: Multimodal Large Language Models Can See but Not Perceive
• EvoRubric: Self-Evolving Rubric-Driven RL for Open-Ended Generation
• Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains
• RubiCap: Rubric-Guided Reinforcement Learning for Dense Image Captioning
• Reinforcement Learning with Rubric Anchors
• Open Rubric System: Scaling Reinforcement Learning with Pairwise Adaptive Rubric
• BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
• DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception
• OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment
• Decoupled Weight Decay Regularization
• OmniCaptioner: One Captioner to Rule Them All
• DocVQA: A Dataset for VQA on Document Images
• DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research
• CCCaption: Dual-Reward Reinforcement Learning for Complete and Correct Image Captioning

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering