Copertina

Weighting What Matters: Boosting Sample Efficiency in Medical Report Generation via Token Reweighting

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Weers, Alexander, Rueckert, Daniel, Menten, Martin J.
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Pitfalls of topology-aware image segmentation
di: Berger, Alexander H., et al.
Pubblicazione: (2024)

Not All Tokens Matter Equally: Dynamic In-context Vector Distillation with Decisive-Token Supervision for Long-form Medical Report Generation
di: Wu, Ning, et al.
Pubblicazione: (2026)

DoGE: Domain Reweighting with Generalization Estimation
di: Fan, Simin, et al.
Pubblicazione: (2023)

Semantic Token Reweighting for Interpretable and Controllable Text Embeddings in CLIP
di: Kim, Eunji, et al.
Pubblicazione: (2024)

Filter-then-Weight: Online Data Selection and Reweighting for LLM Fine-Tuning
di: Wang, Fangxin, et al.
Pubblicazione: (2026)

Taming Extreme Tokens: Covariance-Aware GRPO with Gaussian-Kernel Advantage Reweighting
di: Wang, Cheng, et al.
Pubblicazione: (2026)

Not All Tokens Matter: Towards Efficient LLM Reasoning via Token Significance in Reinforcement Learning
di: Liu, Hanbing, et al.
Pubblicazione: (2025)

REAL Sampling: Boosting Factuality and Diversity of Open-Ended Generation via Asymptotic Entropy
di: Chang, Haw-Shiuan, et al.
Pubblicazione: (2024)

Forget What Matters, Keep the Rest: Selective Unlearning of Informative Tokens
di: Koh, Seunghee, et al.
Pubblicazione: (2026)

Logit Reweighting for Topic-Focused Summarization
di: Braun, Joschka, et al.
Pubblicazione: (2025)

How Much Is One Recurrence Worth? Iso-Depth Scaling Laws for Looped Language Models
di: Schwethelm, Kristian, et al.
Pubblicazione: (2026)

A Tale of Two Classes: Adapting Supervised Contrastive Learning to Binary Imbalanced Datasets
di: Mildenberger, David, et al.
Pubblicazione: (2025)

Controlling Summarization Length Through EOS Token Weighting
di: Belligoli, Zeno, et al.
Pubblicazione: (2025)

Boosting Lossless Speculative Decoding via Feature Sampling and Partial Alignment Distillation
di: Gui, Lujun, et al.
Pubblicazione: (2024)

What is Hiding in Medicine's Dark Matter? Learning with Missing Data in Medical Practices
di: Suzen, Neslihan, et al.
Pubblicazione: (2024)

Towards Generalisable Time Series Understanding Across Domains
di: Turgut, Özgün, et al.
Pubblicazione: (2024)

Out-of-Vocabulary Sampling Boosts Speculative Decoding
di: Timor, Nadav, et al.
Pubblicazione: (2025)

Fast Controlled Generation from Language Models with Adaptive Weighted Rejection Sampling
di: Lipkin, Benjamin, et al.
Pubblicazione: (2025)

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning
di: Lin, Zihan, et al.
Pubblicazione: (2026)

Product of Experts with LLMs: Boosting Performance on ARC Is a Matter of Perspective
di: Franzen, Daniel, et al.
Pubblicazione: (2025)

Multimodal Medical Code Tokenizer
di: Su, Xiaorui, et al.
Pubblicazione: (2025)

GEAR: Granularity-Adaptive Advantage Reweighting for LLM Agents via Self-Distillation
di: Li, Sijia, et al.
Pubblicazione: (2026)

Ignore the KL Penalty! Boosting Exploration on Critical Tokens to Enhance RL Fine-Tuning
di: Vassoyan, Jean, et al.
Pubblicazione: (2025)

Improving Next Tokens via Second-to-Last Predictions with Generate and Refine
di: Schneider, Johannes
Pubblicazione: (2024)

ChEX: Interactive Localization and Region Description in Chest X-rays
di: Müller, Philip, et al.
Pubblicazione: (2024)

Tokenization Matters: Navigating Data-Scarce Tokenization for Gender Inclusive Language Technologies
di: Ovalle, Anaelia, et al.
Pubblicazione: (2023)

$μ^2$Tokenizer: Differentiable Multi-Scale Multi-Modal Tokenizer for Radiology Report Generation
di: Li, Siyou, et al.
Pubblicazione: (2025)

Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety
di: Guan, Zihan, et al.
Pubblicazione: (2025)

Reducing and Exploiting Data Augmentation Noise through Meta Reweighting Contrastive Learning for Text Classification
di: Mou, Guanyi, et al.
Pubblicazione: (2024)

Distillation Scaling Laws
di: Busbridge, Dan, et al.
Pubblicazione: (2025)

Mixture of Weight-shared Heterogeneous Group Attention Experts for Dynamic Token-wise KV Optimization
di: Song, Guanghui, et al.
Pubblicazione: (2025)

Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability
di: Lin, Zicheng, et al.
Pubblicazione: (2024)

Clinical Context-aware Radiology Report Generation from Medical Images using Transformers
di: Singh, Sonit
Pubblicazione: (2024)

Lossless Compression of Large Language Model-Generated Text via Next-Token Prediction
di: Mao, Yu, et al.
Pubblicazione: (2025)

Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data?
di: Hayase, Jonathan, et al.
Pubblicazione: (2024)

PIER: A Novel Metric for Evaluating What Matters in Code-Switching
di: Ugan, Enes Yavuz, et al.
Pubblicazione: (2025)

Topograph: An efficient Graph-Based Framework for Strictly Topology Preserving Image Segmentation
di: Lux, Laurin, et al.
Pubblicazione: (2024)

DenseFormer: Enhancing Information Flow in Transformers via Depth Weighted Averaging
di: Pagliardini, Matteo, et al.
Pubblicazione: (2024)

What Matters for Model Merging at Scale?
di: Yadav, Prateek, et al.
Pubblicazione: (2024)

The Truth Lies Somewhere in the Middle (of the Generated Tokens)
di: Wang, Sophie L., et al.
Pubblicazione: (2026)