REC-RL: Referring expression counting via Gaussian and range-based reward optimization

• URL: http://arxiv.org/abs/2605.16460v1
• Date: Fri, 15 May 2026 07:37:45 GMT
• Title: REC-RL: Referring expression counting via Gaussian and range-based reward optimization
• Abstract summary: Referring expression counting (REC) is an intention-driven task that requires context-aware visual reasoning.<n>We propose REC-RL, a reinforcement learning framework that introduces a think-range-answer paradigm to explicitly optimize the visual reasoning process.
• Score: 28.33789155610508
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Referring expression counting (REC) is an intention-driven task that requires context-aware visual reasoning. While recent vision-language models incorporate language for visual understanding, most existing REC methods rely on rulebased reinforcement learning with rewards focused primarily on final accuracy, overlooking the quality of intermediate reasoning. We propose REC-RL, a reinforcement learning framework that introduces a think-range-answer paradigm to explicitly optimize the visual reasoning process. RECRL employs Group Relative Policy Optimization and two lightweight rewards: an accuracy reward that combines range-based interval supervision with Gaussian-based precision guidance, and a format reward that enforces structured outputs. By modeling intermediate focus prediction as internal decision-making, REC-RL avoids additional annotations and better aligns with human perception. Extensive experiments demonstrate consistent improvements over strong baselines and robust generalization across benchmarks.

Related papers

• Reinforced Preference Optimization for Reasoning-Augmented Recommendations [34.99578717556569]
  We introduce RPORec, a reinforced preference optimization framework for Recommender systems.<n>RPORec unifies an LLM backbone's reasoning ability with a dedicated recommendation head (Rechead) for precise item retrieval.<n>Extensive experiments on public benchmarks and large-scale online deployments show that RPORec consistently outperforms state-of-the-art LLM-based recommendation methods.
  arXiv  Detail & Related papers  (2026-05-21T03:56:42Z)
• Learning from Failures: Correction-Oriented Policy Optimization with Verifiable Rewards [73.44333771806282]
  Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective paradigm for improving the reasoning capabilities of large language models.<n>We propose Correction-Oriented Policy Optimization (CIPO), a simple and effective extension to RLVR that converts on-policy failed trajectories into correction-oriented supervision.<n>CIPO improves learning effectiveness while explicitly enhancing the model's ability to correct its own errors.
  arXiv  Detail & Related papers  (2026-05-14T08:22:21Z)
• RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time [51.256131853751754]
  We show that teaching reward models to produce explicit, multi-dimensional critiques transforms them from passive evaluators into active optimization tools.<n>We introduce Preference-Anchored Rationalization (PARROT), a principled framework that recovers high-quality rationales from readily available preference data.<n>The resulting model, RationalRewards (8B), achieves state-of-the-art preference prediction among open-source reward models.
  arXiv  Detail & Related papers  (2026-04-13T15:38:09Z)
• Bridging Visual Representation and Reinforcement Learning from Verifiable Rewards in Large Vision-Language Models [35.97638821723309]
  KAWHI is a plug-and-play reward reweighting mechanism that explicitly incorporates structured visual information into uniform reward policy optimization methods.<n>It adaptively localizes semantically salient regions through hierarchical geometric aggregation, identifies vision-critical attention heads via structured attribution, and performs paragraph-level credit reallocation to align spatial visual evidence with semantically decisive reasoning steps.
  arXiv  Detail & Related papers  (2026-03-28T18:40:14Z)
• RASPRef: Retrieval-Augmented Self-Supervised Prompt Refinement for Large Reasoning Models [0.0]
  We introduce Retrieval-Augmented Self-Supervised Prompt Refinement (RASPRef), a framework that improves prompts without requiring human annotations or task-specific supervision.<n>RASPRef directly treats the prompt as the optimization target and improves it through an iterative retrieval-guided refinement process.
  arXiv  Detail & Related papers  (2026-03-27T21:49:21Z)
• Alternating Reinforcement Learning with Contextual Rubric Rewards [2.1172256884504588]
  Reinforcement Learning with Rewards (RLRR) is a framework that extends conventional reinforcement learning from human feedback.<n>Existing approaches in RLRR are limited to linearly compressing vector rewards into a scalar reward with a fixed weightings.<n>This work proposes Alternating Reinforcement Learning with Rewards (ARL-RR) to overcome the limitations of reward aggregation.
  arXiv  Detail & Related papers  (2026-03-04T04:18:39Z)
• Learning in Context, Guided by Choice: A Reward-Free Paradigm for Reinforcement Learning with Transformers [55.33468902405567]
  We propose a new learning paradigm, In-Context Preference-based Reinforcement Learning (ICPRL), in which both pretraining and deployment rely solely on preference feedback.<n>ICPRL enables strong in-context generalization to unseen tasks, achieving performance comparable to ICRL methods trained with full reward supervision.
  arXiv  Detail & Related papers  (2026-02-09T03:42:16Z)
• From Absolute to Relative: Rethinking Reward Shaping in Group-Based Reinforcement Learning [7.6602542594279335]
  We propose Reinforcement Learning with Relative Rewards to shift reward shaping from absolute scoring to relative ranking.<n>We show that RLRR yields consistent performance improvements over standard group-based baselines across reasoning benchmarks and open-ended generation tasks.
  arXiv  Detail & Related papers  (2026-01-30T15:07:06Z)
• Generative Actor Critic [74.04971271003869]
  Generative Actor Critic (GAC) is a novel framework that decouples sequential decision-making by reframing textitpolicy evaluation as learning a generative model of the joint distribution over trajectories and returns.<n>Experiments on Gym-MuJoCo and Maze2D benchmarks demonstrate GAC's strong offline performance and significantly enhanced offline-to-online improvement compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-12-25T06:31:11Z)
• Coupled Variational Reinforcement Learning for Language Model General Reasoning [83.82392089177841]
  We propose textitbCoupled bVari bReinforcement bLearning (CoVRL) to bridge variational inference and reinforcement learning.<n>CoVRL improves performance by 12.4% over the base model and achieves an additional 2.3% improvement over strong state-of-the-art verifier-free RL baselines.
  arXiv  Detail & Related papers  (2025-12-14T07:03:51Z)
• AURORA: Augmented Understanding via Structured Reasoning and Reinforcement Learning for Reference Audio-Visual Segmentation [113.75682363364004]
  AURORA is a framework designed to enhance genuine reasoning and language comprehension in reference audio-visual segmentation.<n>AURORA achieves state-of-the-art performance on Ref-AVS benchmarks and generalizes effectively to unreferenced segmentation.
  arXiv  Detail & Related papers  (2025-08-04T07:47:38Z)
• Direct Reasoning Optimization: LLMs Can Reward And Refine Their Own Reasoning for Open-Ended Tasks [6.881699020319577]
  We propose Direct Reasoning Optimization (DRO), a reinforcement learning framework for fine-tuning Large Language Models (LLMs)<n>DRO is guided by a new reward signal: the Reasoning Reflection Reward (R3)<n>DRO consistently outperforms strong baselines while remaining broadly applicable across both open-ended and structured domains.
  arXiv  Detail & Related papers  (2025-06-16T10:43:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.