MGPO elicits grounding in LMMs via multi-turn RL with binary rewards, yielding 5.4% and 5.2% gains on MME-Realworld and V* Bench and surpassing GPT-4o on the latter after training on 21K samples.
Visual agents as fast and slow thinkers
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
DeepEyes uses reinforcement learning to teach vision-language models active perception and image-based thinking, yielding gains on perception, reasoning, grounding, and hallucination benchmarks.
OmniDrive-R1 boosts VLM reasoning score from 51.77% to 80.35% and answer accuracy from 37.81% to 73.62% on DriveLMM-o1 via reinforcement-driven interleaved multi-modal chain-of-thought with annotation-free grounding.
DeFacto trains multimodal models with counterfactual image variants and GRPO reinforcement learning to enforce that correct answers are supported by correct visual evidence.
DRS-GUI introduces a dynamic region search method with Focus/Shift/Scatter actions and MCTS-based planning that improves GUI grounding accuracy by 14% on ScreenSpot-Pro for both general and GUI-specific MLLMs without any training.
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.
The survey organizes the shift of LLMs toward deliberate System 2 reasoning, covering model construction techniques, performance on math and coding benchmarks, and future research directions.
citing papers explorer
-
High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement Learning
MGPO elicits grounding in LMMs via multi-turn RL with binary rewards, yielding 5.4% and 5.2% gains on MME-Realworld and V* Bench and surpassing GPT-4o on the latter after training on 21K samples.