RL post-training on hallucination-forced multimodal data improves reasoning performance and can outperform standard training.
Internvl: Scaling up vision foundation mod- els and aligning for generic visual-linguistic tasks
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 7roles
background 2polarities
background 2representative citing papers
LongVideo-R1 trains a reasoning agent on 33K trajectories to intelligently select informative video clips via iterative refinement and RL, achieving better accuracy-efficiency tradeoffs on long video QA benchmarks.
A vision-language framework generates text-based rigid-body scene configurations from videos using motion reasoning and optical flow, reporting 0.30 IoU on CLEVRER (7x over baselines) and transfer to 235 real videos.
HERA is a select-regularize-calibrate framework adapting frozen vision foundation models for cross-domain few-shot semantic segmentation via hierarchical layer selection with ETR, prior-guided regularization, and pixelwise adaptive calibration, reporting over 4.1 mIoU gains.
Chart-FR1 uses Focus-CoT for linking reasoning to visual cues and Focus-GRPO reinforcement learning with efficiency rewards to outperform prior MLLMs on dense chart reasoning tasks.
ViSurf unifies SFT and RLVR for LVLMs in one training stage by injecting ground-truth labels into rollouts and applying novel reward controls, outperforming standalone and two-stage baselines on diverse benchmarks.
A two-stage RL method with information gaps and grounding loss trains MLLMs to focus on and precisely crop relevant image regions, yielding SOTA results on high-resolution VQA benchmarks.
citing papers explorer
-
Understanding the Role of Hallucination in Reinforcement Post-Training of Multimodal Reasoning Models
RL post-training on hallucination-forced multimodal data improves reasoning performance and can outperform standard training.
-
LongVideo-R1: Smart Navigation for Low-cost Long Video Understanding
LongVideo-R1 trains a reasoning agent on 33K trajectories to intelligently select informative video clips via iterative refinement and RL, achieving better accuracy-efficiency tradeoffs on long video QA benchmarks.
-
$\Delta$ynamics: Language-Based Representation for Inferring Rigid-Body Dynamics From Videos
A vision-language framework generates text-based rigid-body scene configurations from videos using motion reasoning and optical flow, reporting 0.30 IoU on CLEVRER (7x over baselines) and transfer to 235 real videos.
-
Selective, Regularized, and Calibrated: Harnessing Vision Foundation Models for Cross-Domain Few-Shot Semantic Segmentation
HERA is a select-regularize-calibrate framework adapting frozen vision foundation models for cross-domain few-shot semantic segmentation via hierarchical layer selection with ETR, prior-guided regularization, and pixelwise adaptive calibration, reporting over 4.1 mIoU gains.
-
Chart-FR1: Visual Focus-Driven Fine-Grained Reasoning on Dense Charts
Chart-FR1 uses Focus-CoT for linking reasoning to visual cues and Focus-GRPO reinforcement learning with efficiency rewards to outperform prior MLLMs on dense chart reasoning tasks.
-
ViSurf: Visual Supervised-and-Reinforcement Fine-Tuning for Large Vision-and-Language Models
ViSurf unifies SFT and RLVR for LVLMs in one training stage by injecting ground-truth labels into rollouts and applying novel reward controls, outperforming standalone and two-stage baselines on diverse benchmarks.
-
Learning to Focus and Precise Cropping: A Reinforcement Learning Framework with Information Gaps and Grounding Loss for MLLMs
A two-stage RL method with information gaps and grounding loss trains MLLMs to focus on and precisely crop relevant image regions, yielding SOTA results on high-resolution VQA benchmarks.