ConceptSeg-R1 uses Meta-GRPO meta-RL to learn transferable rules from visual demonstrations and apply them via concept translation for generalized concept segmentation across CI, CD, and CR levels.
Seg-r1: Segmentation can be surprisingly simple with reinforcement 33 ConceptSeg-R1 learning
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
verdicts
UNVERDICTED 9roles
baseline 1polarities
baseline 1representative citing papers
WebEye benchmark and Pixel-Searcher agent enable visual perception tasks by using web search to resolve object identities before precise localization or answering.
PhySe-RPO enables diffusion-based surgical smoke removal by converting restoration into a stochastic policy optimized with physics consistency and CLIP semantic rewards under limited supervision.
CamReasoner uses structured O-T-A reasoning and RL on 56k samples to lift camera movement classification from 73.8% to 78.4% and VQA from 60.9% to 74.5% on Qwen2.5-VL-7B.
InstanceControl uses VLMs to auto-generate instance masks from text and visual conditions, with adaptive refinement, to enable controllable multi-object image generation without manual labeling.
A group-revision paradigm for GRPO-based RL fine-tuning of VLMs converts failure responses into improvement signals that refine rewards and advantages, yielding gains on referring segmentation, REC, and counting benchmarks.
EARL uses analysis-guided RL with a two-stage parsing and AFS module to achieve 65.48% cIoU in pixel grounding on Ego-IRGBench, outperforming prior RL methods.
GETok partitions images with grid tokens and refines locations via offset tokens to enable better native 2D spatial reasoning in MLLMs.
OneThinker unifies image and video reasoning in one model across 10 tasks via a 600k corpus, CoT-annotated SFT, and EMA-GRPO reinforcement learning, reporting strong results on 31 benchmarks plus some cross-task transfer.
citing papers explorer
-
ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning
ConceptSeg-R1 uses Meta-GRPO meta-RL to learn transferable rules from visual demonstrations and apply them via concept translation for generalized concept segmentation across CI, CD, and CR levels.
-
From Web to Pixels: Bringing Agentic Search into Visual Perception
WebEye benchmark and Pixel-Searcher agent enable visual perception tasks by using web search to resolve object identities before precise localization or answering.
-
PhySe-RPO: Physics and Semantics Guided Relative Policy Optimization for Diffusion-Based Surgical Smoke Removal
PhySe-RPO enables diffusion-based surgical smoke removal by converting restoration into a stochastic policy optimized with physics consistency and CLIP semantic rewards under limited supervision.
-
CamReasoner: Reinforcing Camera Movement Understanding via Structured Spatial Reasoning
CamReasoner uses structured O-T-A reasoning and RL on 56k samples to lift camera movement classification from 73.8% to 78.4% and VQA from 60.9% to 74.5% on Qwen2.5-VL-7B.
-
InstanceControl: Controllable Complex Image Generation without Instance Labeling
InstanceControl uses VLMs to auto-generate instance masks from text and visual conditions, with adaptive refinement, to enable controllable multi-object image generation without manual labeling.
-
From Failure to Feedback: Group Revision Unlocks Hard Cases in Object-Level Grounding
A group-revision paradigm for GRPO-based RL fine-tuning of VLMs converts failure responses into improvement signals that refine rewards and advantages, yielding gains on referring segmentation, REC, and counting benchmarks.
-
EARL: Towards a Unified Analysis-Guided Reinforcement Learning Framework for Egocentric Interaction Reasoning and Pixel Grounding
EARL uses analysis-guided RL with a two-stage parsing and AFS module to achieve 65.48% cIoU in pixel grounding on Ego-IRGBench, outperforming prior RL methods.
-
Grounding Everything in Tokens for Multimodal Large Language Models
GETok partitions images with grid tokens and refines locations via offset tokens to enable better native 2D spatial reasoning in MLLMs.
-
OneThinker: All-in-one Reasoning Model for Image and Video
OneThinker unifies image and video reasoning in one model across 10 tasks via a 600k corpus, CoT-annotated SFT, and EMA-GRPO reinforcement learning, reporting strong results on 31 benchmarks plus some cross-task transfer.