VLMs formulate differentiable rewards from task-specific rules to enable test-time online LoRA optimization of VGMs, delivering 16.7-point gains on symbolic and general video reasoning benchmarks over VLM-as-solver and Best-of-N baselines.
Grpo- care: Consistency-aware reinforcement learning for multimodal reasoning
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
years
2026 8verdicts
UNVERDICTED 8representative citing papers
Touch-R1 applies GRPO reinforcement learning on a new 1M tactile dataset and benchmark to train a Qwen2.5-VL-7B model that outperforms baselines on tactile perception and visual-tactile conflict tasks.
RDPO applies magnitude-aware quantile normalization and Mahalanobis whitening to decorrelate heterogeneous rewards in multi-objective RL, improving instruction following and writing quality on LongCat-Flash post-training while staying competitive on reasoning and coding.
PRP introduces proactive routing via Draft Rating Learning and Joint Rating Learning to route queries early between draft and target models for efficient multimodal reasoning.
ThinkDeception introduces MLLMs, a multimodal CoT dataset, and VAC-GRPO progressive RL to convert deception detection into interpretable reasoning and claims new SOTA accuracy plus rationale quality.
DynFrame introduces tokenized learnable span-density retrieval and Segment-Decoupled GRPO in video MLLMs, achieving competitive or SOTA results on six benchmarks with 4B and 8B models.
MHPR is a multidimensional benchmark for LVLM human-centric perception-reasoning with C-RD, SFT-D, RL-D, T-D data tiers and ACVG pipeline, showing training gains on Qwen2.5-VL-7B to near-parity with larger models.
Identifies two gaps in entropy-based uncertainty for LLM post-training and proposes GCPO to align geometry-aware disagreement measures with reward-based calibration for better gradient regulation.
citing papers explorer
-
VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization
VLMs formulate differentiable rewards from task-specific rules to enable test-time online LoRA optimization of VGMs, delivering 16.7-point gains on symbolic and general video reasoning benchmarks over VLM-as-solver and Best-of-N baselines.
-
Touch-R1: Reinforcing Touch Reasoning in MLLMs
Touch-R1 applies GRPO reinforcement learning on a new 1M tactile dataset and benchmark to train a Qwen2.5-VL-7B model that outperforms baselines on tactile perception and visual-tactile conflict tasks.
-
Multi-Objective and Mixed-Reward Reinforcement Learning via Reward-Decorrelated Policy Optimization
RDPO applies magnitude-aware quantile normalization and Mahalanobis whitening to decorrelate heterogeneous rewards in multi-objective RL, improving instruction following and writing quality on LongCat-Flash post-training while staying competitive on reasoning and coding.
-
Before Thinking, Learn to Decide: Proactive Routing for Efficient Visual Reasoning
PRP introduces proactive routing via Draft Rating Learning and Joint Rating Learning to route queries early between draft and target models for efficient multimodal reasoning.
-
ThinkDeception: A Progressive Reinforcement Learning Framework for Interpretable Multimodal Deception Detection
ThinkDeception introduces MLLMs, a multimodal CoT dataset, and VAC-GRPO progressive RL to convert deception detection into interpretable reasoning and claims new SOTA accuracy plus rationale quality.
-
DynFrame: Adaptive Reasoning-Driven Multimodal Framework with Dynamic Frame Augmentation for Complex Video Understanding
DynFrame introduces tokenized learnable span-density retrieval and Segment-Decoupled GRPO in video MLLMs, achieving competitive or SOTA results on six benchmarks with 4B and 8B models.
-
MHPR: Multidimensional Human Perception and Reasoning Benchmark for Large Vision-Languate Models
MHPR is a multidimensional benchmark for LVLM human-centric perception-reasoning with C-RD, SFT-D, RL-D, T-D data tiers and ACVG pipeline, showing training gains on Qwen2.5-VL-7B to near-parity with larger models.
-
Why Semantic Entropy Fails: Geometry-Aware and Calibrated Uncertainty for Policy Optimization
Identifies two gaps in entropy-based uncertainty for LLM post-training and proposes GCPO to align geometry-aware disagreement measures with reward-based calibration for better gradient regulation.