ViToS uses dual-stream RL with cross-feedback optimization to prune medical image tokens to 77% length while reporting 108.27% and 104.16% relative performance on two 7B VLMs across seven benchmarks.
arXiv preprint arXiv:2508.02669 , year=
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Staged post-training that first solidifies visual perception before visual and textual reasoning improves VLM accuracy and shortens reasoning traces on visual math and perception benchmarks.
ClinSeekAgent automates active multimodal evidence seeking for clinical reasoning, improving LLM performance on raw EHR and CXR tasks while enabling distillation into smaller models.
VISTA uses prefix resampling and a vision-aware attention score to address data imbalance and language prior bias in self-improvement training of MLLMs, yielding up to 13.66% gains on reasoning tasks.
Complex multimodal architectures do not reliably outperform unimodal baselines or a simple multimodal baseline under standardized evaluation.
E-MRL trains VLMs via RL on a diagnosis-localization-verification MDP with a novel cross-view consistency reward to ground 3D tumor reports in verifiable CT slices.
TIF-GRPO uses integral feedback on pseudo-temporal trajectories to regulate anatomy-aware rewards in RL for clinical faithfulness in volumetric CT analysis.
TeamPath introduces a reinforcement-learning-powered multimodal AI copilot for pathology that generates reasoned diagnoses and integrates image and transcriptomic data.
citing papers explorer
-
Token-Sparse Medical Multimodal Reasoning via Dual-Stream Reinforcement Learning
ViToS uses dual-stream RL with cross-feedback optimization to prune medical image tokens to 77% length while reporting 108.27% and 104.16% relative performance on two 7B VLMs across seven benchmarks.
-
From Seeing to Thinking: Decoupling Perception and Reasoning Improves Post-Training of Vision-Language Models
Staged post-training that first solidifies visual perception before visual and textual reasoning improves VLM accuracy and shortens reasoning traces on visual math and perception benchmarks.
-
ClinSeekAgent: Automating Multimodal Evidence Seeking for Agentic Clinical Reasoning
ClinSeekAgent automates active multimodal evidence seeking for clinical reasoning, improving LLM performance on raw EHR and CXR tasks while enabling distillation into smaller models.
-
Learn to Think: Improving Multimodal Reasoning through Vision-Aware Self-Improvement Training
VISTA uses prefix resampling and a vision-aware attention score to address data imbalance and language prior bias in self-improvement training of MLLMs, yielding up to 13.66% gains on reasoning tasks.
-
Fusion or Confusion? Multimodal Complexity Is Not All You Need
Complex multimodal architectures do not reliably outperform unimodal baselines or a simple multimodal baseline under standardized evaluation.
-
E-MRL: Cross-view Aligned Evidence-driven Multimodal Reinforcement Learning for Reliable 3D Tumor Analysis
E-MRL trains VLMs via RL on a diagnosis-localization-verification MDP with a novel cross-view consistency reward to ground 3D tumor reports in verifiable CT slices.
-
Regulating Anatomy-Aware Rewards via Trajectory-Integral Feedback for Volumetric Computed Tomography Analysis
TIF-GRPO uses integral feedback on pseudo-temporal trajectories to regulate anatomy-aware rewards in RL for clinical faithfulness in volumetric CT analysis.
-
TeamPath: Building MultiModal Pathology Experts with Reasoning AI Copilots
TeamPath introduces a reinforcement-learning-powered multimodal AI copilot for pathology that generates reasoned diagnoses and integrates image and transcriptomic data.