Adaptive Reinforcement for Open-ended Medical Reasoning via Semantic-Guided Reward Collapse Mitigation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Yizhou, Yang, Dingkang, Chen, Zizhi, Han, Minghao, Zhang, Xukun, Liu, Keliang, Wei, Jingwei, Zhang, Lihua
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Forging a Dynamic Memory: Retrieval-Guided Continual Learning for Generalist Medical Foundation Models
by: Chen, Zizhi, et al.
Published: (2025)

Towards Unified Molecule-Enhanced Pathology Image Representation Learning via Integrating Spatial Transcriptomics
by: Han, Minghao, et al.
Published: (2024)

Beyond Pixel Simulation: Pathology Image Generation via Diagnostic Semantic Tokens and Prototype Control
by: Han, Minghao, et al.
Published: (2025)

VLM-based Prompts as the Optimal Assistant for Unpaired Histopathology Virtual Staining
by: Chen, Zizhi, et al.
Published: (2025)

Resolving Evidence Sparsity: Agentic Context Engineering for Long-Document Understanding
by: Liu, Keliang, et al.
Published: (2025)

FysicsWorld: A Unified Full-Modality Benchmark for Any-to-Any Understanding, Generation, and Reasoning
by: Jiang, Yue, et al.
Published: (2025)

OmniFysics: Towards Physical Intelligence Evolution via Omni-Modal Signal Processing and Network Optimization
by: Han, Minghao, et al.
Published: (2026)

VGAT: A Cancer Survival Analysis Framework Transitioning from Generative Visual Question Answering to Genomic Reconstruction
by: Chen, Zizhi, et al.
Published: (2025)

MSCPT: Few-shot Whole Slide Image Classification with Multi-scale and Context-focused Prompt Tuning
by: Han, Minghao, et al.
Published: (2024)

Multi-Scale Heterogeneity-Aware Hypergraph Representation for Histopathology Whole Slide Images
by: Han, Minghao, et al.
Published: (2024)

Fusing Pixels and Genes: Spatially-Aware Learning in Computational Pathology
by: Han, Minghao, et al.
Published: (2026)

PersonaAnimator: Personalized Motion Transfer from Unconstrained Videos
by: Qian, Ziyun, et al.
Published: (2025)

Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle
by: Liu, Keliang, et al.
Published: (2025)

Improving Multimodal Sentiment Analysis via Modality Optimization and Dynamic Primary Modality Selection
by: Yang, Dingkang, et al.
Published: (2025)

Skip and Skip: Segmenting Medical Images with Prompts
by: Chen, Jiawei, et al.
Published: (2024)

MaskBEV: Towards A Unified Framework for BEV Detection and Map Segmentation
by: Zhao, Xiao, et al.
Published: (2024)

Reward-Guided Semantic Evolution for Test-time Adaptive Object Detection
by: Zhou, Lihua, et al.
Published: (2026)

MedAide: Information Fusion and Anatomy of Medical Intents via LLM-based Agent Collaboration
by: Yang, Dingkang, et al.
Published: (2024)

The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward
by: Li, Long, et al.
Published: (2025)

ProFocus: Proactive Perception and Focused Reasoning in Vision-and-Language Navigation
by: Xue, Wei, et al.
Published: (2026)

Self-Rewarding Rubric-Based Reinforcement Learning for Open-Ended Reasoning
by: Ye, Zhiling, et al.
Published: (2025)

Can LLMs' Tuning Methods Work in Medical Multimodal Domain?
by: Chen, Jiawei, et al.
Published: (2024)

HybridOcc: NeRF Enhanced Transformer-based Multi-Camera 3D Occupancy Prediction
by: Zhao, Xiao, et al.
Published: (2024)

Semantic Reward Collapse and the Preservation of Epistemic Integrity in Adaptive AI Systems
by: Parris, William
Published: (2026)

Evaluating and Mitigating Social Bias for Large Language Models in Open-ended Settings
by: Liu, Zhao, et al.
Published: (2024)

Efficiency in Focus: LayerNorm as a Catalyst for Fine-tuning Medical Visual Language Pre-trained Models
by: Chen, Jiawei, et al.
Published: (2024)

SatireDecoder: Visual Cascaded Decoupling for Enhancing Satirical Image Comprehension
by: Jiang, Yue, et al.
Published: (2025)

Beyond Semantic Priors: Mitigating Optimization Collapse for Generalizable Visual Forensics
by: Liu, Jipeng, et al.
Published: (2026)

Adaptive Test-Time Reasoning via Reward-Guided Dual-Phase Search
by: Cui, Yingqian, et al.
Published: (2025)

CoMT: Chain-of-Medical-Thought Reduces Hallucination in Medical Report Generation
by: Jiang, Yue, et al.
Published: (2024)

From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation
by: Jiang, Yuxin, et al.
Published: (2026)

Reinforced Context Order Recovery for Adaptive Reasoning and Planning
by: Ma, Long, et al.
Published: (2025)

Learn to Reason Efficiently with Adaptive Length-based Reward Shaping
by: Liu, Wei, et al.
Published: (2025)

Adaptive Draft-Verification for Efficient Large Language Model Decoding
by: Liu, Xukun, et al.
Published: (2024)

When Sharpening Becomes Collapse: Sampling Bias and Semantic Coupling in RL with Verifiable Rewards
by: Fan, Mingyuan, et al.
Published: (2026)

MM-Snowball: Evaluating and Mitigating Hallucination Snowballing in Multimodal Multi-Turn Dialogue
by: Jiang, Yue, et al.
Published: (2026)

Beyond Semantic Manipulation: Token-Space Attacks on Reward Models
by: Zhang, Yuheng, et al.
Published: (2026)

Stable Reasoning, Unstable Responses: Mitigating LLM Deception via Stability Asymmetry
by: Zhang, Guoxi, et al.
Published: (2026)

ReCode: Reinforcing Code Generation with Reasoning-Process Rewards
by: Fan, Lishui, et al.
Published: (2025)

Towards Context-Aware Emotion Recognition Debiasing from a Causal Demystification Perspective via De-confounded Training
by: Yang, Dingkang, et al.
Published: (2024)