LePaX enables high-resolution chest X-ray report generation by learning to allocate resolution to diagnostically relevant regions and fusing high-res patches back into global features without increasing token count.
hub
In: Proceedings of the 40th annual meeting of the Association for Computational Linguistics
15 Pith papers cite this work. Polarity classification is still indexing.
15
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Transition-aware best-of-N sampling embeds report sentences as sets, computes directional transition vectors via set-to-set distances, and scores candidates by proximity to ground-truth training transitions.
A new robustness benchmark for medical VLMs and segmentation models shows fine-tuning strategy dominates performance under 40 perturbation types, with medical-specific ones hitting segmentation hardest.
A prompting pipeline and statement-level metrics show that six state-of-the-art text-based explainable recommendation models achieve high semantic similarity but very low factual consistency on Amazon review data.
Ego3DLM jointly predicts past and future 3D body pose and motion descriptions in a single autoregressive pass, conditioned on egocentric video, 3D scene features, and three-point tracking, achieving state-of-the-art on the Nymeria benchmark.
Phi-Nav generates path-level hindsight instructions from on-policy exploration trajectories to supply additional semantic supervision for vision-language navigation agents.
AtomiMed is a new modality-agnostic evaluation framework for medical report generation that decomposes reports into hierarchical atomic clinical facts and applies agentic cross-verification to achieve higher correlation with radiologist judgments than n-gram metrics.
Hi-GaTA is a hierarchical gated temporal aggregation adapter that uses short-to-long temporal pyramids and gated fusion to enable surgical video report generation, backed by a new 214-video benchmark and a surgical ViViT pretrained on 40,000 minutes of video.
CT-SpatialVQA benchmark reveals that eight 3D medical VLMs achieve only 34% average accuracy on semantic-spatial reasoning tasks from CT data, frequently below random performance.
IMU-to-4D uses wearable IMU data and repurposed LLMs to predict coherent 4D human motion plus coarse scene structure, outperforming cascaded state-of-the-art pipelines in temporal stability.
GEST-Engine turns game engines into zero-cost dense ground-truth video generators; GTASA reveals frozen video encoders fail inter-entity spatial relation probes.
View-PNDF detects and selectively fine-tunes view-specific neurons for consistent multi-view chest X-ray report generation, followed by LLM consolidation of reports.
SLAP is a new batch-aware pruning framework that uses distribution-aware stratified sampling and Hessian-approximated gradients to select data, claiming 20-40% less data while matching or exceeding full-dataset performance on LLM instruction tuning tasks.
STAND adds semantic anchoring and dual-granularity disambiguation modules to address viewpoint, scale, and knowledge ambiguities in remote sensing change captioning.
Curr-RLCER applies curriculum reinforcement learning with coherence-driven rewards to align generated explanations with predicted ratings in explainable recommendation systems.
citing papers explorer
-
Seeing What Matters: Lesion-Aware High-Resolution Patch Discovery and Fusion for Chest X-ray Report Generation
LePaX enables high-resolution chest X-ray report generation by learning to allocate resolution to diagnostically relevant regions and fusing high-res patches back into global features without increasing token count.
-
Transition-Aware best-of-N sampling for Longitudinal Chest X-ray Reports
Transition-aware best-of-N sampling embeds report sentences as sets, computes directional transition vectors via set-to-set distances, and scores candidates by proximity to ground-truth training transitions.
-
MedFM-Robust: Benchmarking Robustness of Medical Foundation Models
A new robustness benchmark for medical VLMs and segmentation models shows fine-tuning strategy dominates performance under 40 perturbation types, with medical-specific ones hitting segmentation hardest.
-
On the Factual Consistency of Text-based Explainable Recommendation Models
A prompting pipeline and statement-level metrics show that six state-of-the-art text-based explainable recommendation models achieve high semantic similarity but very low factual consistency on Amazon review data.
-
Ego-Human Motion Prediction with 3D-Aware LLM
Ego3DLM jointly predicts past and future 3D body pose and motion descriptions in a single autoregressive pass, conditioned on egocentric video, 3D scene features, and three-point tracking, achieving state-of-the-art on the Nymeria benchmark.
-
Path-level Hindsight Instructions for Semantic Exploration in Vision-Language Navigation
Phi-Nav generates path-level hindsight instructions from on-policy exploration trajectories to supply additional semantic supervision for vision-language navigation agents.
-
AtomiMed: Hierarchical Atomic Fact-Checking for Universal Clinical-Aware Medical Report Evaluation
AtomiMed is a new modality-agnostic evaluation framework for medical report generation that decomposes reports into hierarchical atomic clinical facts and applies agentic cross-verification to achieve higher correlation with radiologist judgments than n-gram metrics.
-
Hi-GaTA: Hierarchical Gated Temporal Aggregation Adapter for Surgical Video Report Generation
Hi-GaTA is a hierarchical gated temporal aggregation adapter that uses short-to-long temporal pyramids and gated fusion to enable surgical video report generation, backed by a new 214-video benchmark and a surgical ViViT pretrained on 40,000 minutes of video.
-
Lost in Volume: The CT-SpatialVQA Benchmark for Evaluating Semantic-Spatial Understanding of 3D Medical Vision-Language Models
CT-SpatialVQA benchmark reveals that eight 3D medical VLMs achieve only 34% average accuracy on semantic-spatial reasoning tasks from CT data, frequently below random performance.
-
Seeing Without Eyes: 4D Human-Scene Understanding from Wearable IMUs
IMU-to-4D uses wearable IMU data and repurposed LLMs to predict coherent 4D human motion plus coarse scene structure, outperforming cascaded state-of-the-art pipelines in temporal stability.
-
GTASA: Ground Truth Annotations for Spatiotemporal Analysis, Evaluation and Training of Video Models
GEST-Engine turns game engines into zero-cost dense ground-truth video generators; GTASA reveals frozen video encoders fail inter-entity spatial relation probes.
-
Seeing Through Multiple Views: Parameter-Efficient Fine-Tuning via Selective Neurons for Consistent Radiology Report Generation
View-PNDF detects and selectively fine-tunes view-specific neurons for consistent multi-view chest X-ray report generation, followed by LLM consolidation of reports.
-
SLAP: Stratified Loss-based Pruning for On-Policy Data-Efficient Instruction Tuning
SLAP is a new batch-aware pruning framework that uses distribution-aware stratified sampling and Hessian-approximated gradients to select data, claiming 20-40% less data while matching or exceeding full-dataset performance on LLM instruction tuning tasks.
-
STAND: Semantic Anchoring Constraint with Dual-Granularity Disambiguation for Remote Sensing Image Change Captioning
STAND adds semantic anchoring and dual-granularity disambiguation modules to address viewpoint, scale, and knowledge ambiguities in remote sensing change captioning.
-
Curr-RLCER:Curriculum Reinforcement Learning For Coherence Explainable Recommendation
Curr-RLCER applies curriculum reinforcement learning with coherence-driven rewards to align generated explanations with predicted ratings in explainable recommendation systems.