WebEye benchmark and Pixel-Searcher agent enable visual perception tasks by using web search to resolve object identities before precise localization or answering.
hub Mixed citations
Univg- r1: Reasoning guided universal visual grounding with re- inforcement learning.arXiv preprint arXiv:2505.14231
Mixed citation behavior. Most common role is background (60%).
16
Pith papers citing it
Background
60% of classified citations
hub tools
citation-role summary
background 3
baseline 2
citation-polarity summary
representative citing papers
Latent visual reasoning improves multimodal models via training effects even without using latent tokens at inference, enabled by an attention-based RL reward that promotes interaction with text tokens.
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.
Vision-language models contain identifiable grounding and hallucination pathways; suppressing the latter reduces object hallucinations by up to 76% while preserving accuracy.
Visual latents in MLLMs are systematically silenced by autoregressive training but can be unsilenced at inference via query-guided contrastive alignment followed by a confidence-progression reward.
GRASP improves multimodal sarcasm target identification by anchoring visual regions in grounded chain-of-thought reasoning and using dual-stage optimization on a new balanced dataset.
AdaTooler-V trains MLLMs to adaptively use vision tools via AT-GRPO reinforcement learning and new datasets, reaching 89.8% on V* and outperforming GPT-4o.
VLA-RL applies online RL to pretrained VLAs, yielding a 4.5% gain over strong baselines on 40 LIBERO manipulation tasks and matching commercial models like π₀-FAST.
RSICCLLM introduces a post-training framework with RSICI dataset, difference-aware supervised fine-tuning, and dual-negative preference optimization that claims to outperform much larger models on remote sensing image change captioning.
DyGRO-VLA is a two-stage optimization framework for cross-task scaling of Vision-Language-Action models via dynamic grouped residual optimization in RL.
AutoVQA-G is a self-improving framework that generates VQA-G datasets with higher visual grounding accuracy than leading multimodal LLMs via iterative CoT verification and prompt refinement.
TempR1 applies temporal-aware multi-task RL using GRPO and three types of localization rewards to achieve SOTA temporal understanding in MLLMs with synergistic gains from joint optimization.
RCoT-Seg uses GRPO-reinforced keyframe selection from a CoT-start corpus followed by SAM2 mask propagation to improve video object segmentation under implicit temporal instructions over prior MLLM sampling methods.
XEmbodied is a foundation model that integrates 3D geometric and physical signals into VLMs using a 3D Adapter and Efficient Image-Embodied Adapter, plus progressive curriculum and RL post-training, to improve spatial reasoning and embodied performance on 18 benchmarks.
A staged pipeline using ASR transcription, visual existence verification, Sa2VA coarse segmentation, and agent-guided SAM3 refinement won first place in the PVUW MeViS-Audio track by decomposing audio-conditioned Ref-VOS into sequential verification and refinement steps.
An agent-augmented Sa2VA pipeline for referring video object segmentation placed third in the MeViS-Text track of the 5th PVUW Challenge by adding verification, search, and refinement stages.
citing papers explorer
-
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.
-
Leveraging Latent Visual Reasoning in Silence
Latent visual reasoning improves multimodal models via training effects even without using latent tokens at inference, enabled by an attention-based RL reward that promotes interaction with text tokens.
-
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.
-
Dual-Pathway Circuits of Object Hallucination in Vision-Language Models
Vision-language models contain identifiable grounding and hallucination pathways; suppressing the latter reduces object hallucinations by up to 76% while preserving accuracy.
-
Visual Latents Know More Than They Say: Unsilencing Latent Reasoning in MLLMs
Visual latents in MLLMs are systematically silenced by autoregressive training but can be unsilenced at inference via query-guided contrastive alignment followed by a confidence-progression reward.
-
GRASP: Grounded CoT Reasoning with Dual-Stage Optimization for Multimodal Sarcasm Target Identification
GRASP improves multimodal sarcasm target identification by anchoring visual regions in grounded chain-of-thought reasoning and using dual-stage optimization on a new balanced dataset.
-
AdaTooler-V: Adaptive Tool-Use for Images and Videos
AdaTooler-V trains MLLMs to adaptively use vision tools via AT-GRPO reinforcement learning and new datasets, reaching 89.8% on V* and outperforming GPT-4o.
-
VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning
VLA-RL applies online RL to pretrained VLAs, yielding a 4.5% gain over strong baselines on 40 LIBERO manipulation tasks and matching commercial models like π₀-FAST.
-
RSICCLLM: A Multimodal Large Language Model for Remote Sensing Image Change Captioning
RSICCLLM introduces a post-training framework with RSICI dataset, difference-aware supervised fine-tuning, and dual-negative preference optimization that claims to outperform much larger models on remote sensing image change captioning.
-
DyGRO-VLA: Cross-Task Scaling of Vision-Language-Action Models via Dynamic Grouped Residual Optimization
DyGRO-VLA is a two-stage optimization framework for cross-task scaling of Vision-Language-Action models via dynamic grouped residual optimization in RL.
-
AutoVQA-G: Self-Improving Agentic Framework for Automated Visual Question Answering and Grounding Annotation
AutoVQA-G is a self-improving framework that generates VQA-G datasets with higher visual grounding accuracy than leading multimodal LLMs via iterative CoT verification and prompt refinement.
-
TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning
TempR1 applies temporal-aware multi-task RL using GRPO and three types of localization rewards to achieve SOTA temporal understanding in MLLMs with synergistic gains from joint optimization.
-
RCoT-Seg: Reinforced Chain-of-Thought for Video Reasoning and Segmentation
RCoT-Seg uses GRPO-reinforced keyframe selection from a CoT-start corpus followed by SAM2 mask propagation to improve video object segmentation under implicit temporal instructions over prior MLLM sampling methods.
-
XEmbodied: A Foundation Model with Enhanced Geometric and Physical Cues for Large-Scale Embodied Environments
XEmbodied is a foundation model that integrates 3D geometric and physical signals into VLMs using a 3D Adapter and Efficient Image-Embodied Adapter, plus progressive curriculum and RL post-training, to improve spatial reasoning and embodied performance on 18 benchmarks.
-
APRVOS: 1st Place Winner of 5th PVUW MeViS-Audio Track
A staged pipeline using ASR transcription, visual existence verification, Sa2VA coarse segmentation, and agent-guided SAM3 refinement won first place in the PVUW MeViS-Audio track by decomposing audio-conditioned Ref-VOS into sequential verification and refinement steps.
-
AgentRVOS for MeViS-Text Track of 5th PVUW Challenge: 3rd Method
An agent-augmented Sa2VA pipeline for referring video object segmentation placed third in the MeViS-Text track of the 5th PVUW Challenge by adding verification, search, and refinement stages.