27 Jun 2026
We introduce 5ting, our system for the SemEval2026 Task 8 (MTRAGEval), which evaluates multi-turn Retrieval Augmented Generation (RAG) systems. Multi turn RAG involves context drift, under specification, and hallucination risk.
Trending research and the full catalog - each paper linked to the benchmarks, methods, and models it introduces.
Filtering here covers the 2,000 most recent papers, as much as one page can hold in memory. See the full index of 23,020 papers.
27 Jun 2026
We introduce 5ting, our system for the SemEval2026 Task 8 (MTRAGEval), which evaluates multi-turn Retrieval Augmented Generation (RAG) systems. Multi turn RAG involves context drift, under specification, and hallucination risk.
27 Jun 2026
Predicting the aerodynamic performance (e.g. lift, drag, and moment coefficients) of an aircraft is challenging -- computational models are biased and direct simulations are prohibitive.
27 Jun 2026
Text encoders are known for their utility in natural language processing, as they are able to efficiently compress inputs into dense vectors while preserving semantics. These models have been applied to affective computing, in particular to help with solving sentiment analysis…
27 Jun 2026
Neurological disorders involve diverse pathologies of the brain and nervous system, making early and accurate detection essential. While many deep CNNs have been developed for MRI-based classification of neurological disorders, most are optimized for binary tasks and often fail…
27 Jun 2026
The main objective of this paper is to propose a general framework for prediction based on different sources of multimodal data in the healthcare domain. We evaluated whether frozen medical large language model (LLM) representations can serve as a shared embedding space for…
27 Jun 2026
In general, an ensemble classifier is more accurate than a single classifier. In this study, we propose an ensemble classifier called the kernel Fisher discriminant analysis forest (KFDA Forest), which is a tree-based ensemble method that applies KFDA.
27 Jun 2026
Causally linking disease-related factors to image-derived biomarkers provides a powerful pathway to understanding disease mechanisms. Despite growing interest in applying causal artificial intelligence (AI) approaches for this task, these methods still need to be adapted for…
27 Jun 2026
Deep learning, which in general relies on voluminous amounts of training data, is vulnerable to data poisoning attacks, including error-generic attacks and backdoors (Trojans). In this work, we propose a new data poisoning attack we dub a latent class attack.
27 Jun 2026
We propose a path-space formulation of prediction in AI world models. Rather than sequences of one-step conditional distributions, we argue that a world model implicitly defines a probability measure over future trajectories.
27 Jun 2026
Synthetic aperture radar (SAR) data augmentation is important for improving the generalization of data-driven SAR interpretation models, yet practical augmentation workflows are often hindered by heterogeneous dataset formats, task-dependent metadata requirements, diverse…
27 Jun 2026
In-context learning (ICL) is an emerging paradigm that employs the semantic information inherent in large language models (LLMs) for generating answers to user queries. While the remarkable performance of ICL has been widely known, a general modeling and a rigorous theoretical…
26 Jun 2026
Recent advances in Human Activity Recognition (HAR) from wearable sensors have shown that multi-modal deep learning models consistently outperform their uni-modal counterparts. Modalities can include IMUs, RGB cameras, audio signals, and others.
26 Jun 2026
The clinical and communication skills of medical students are commonly assessed through Objective Structured Clinical Examinations (OSCEs), which consist of brief scenario-driven simulations of doctor-patient interactions.
26 Jun 2026
Automatically generated videos from scientific papers are increasingly used for education and research dissemination. However, existing evaluation metrics mainly measure visual quality or whether key points from the paper appear in the video without assessing whether the video…
26 Jun 2026
Safety alignment in large language models can degrade during post-training even when neither the data nor the objective is intentionally adversarial. Alignment rebound and reverse dynamics suggest that this degradation may reactivate behavior suppressed during safety alignment.
26 Jun 2026
Synthetic data is increasingly used to enable the development and evaluation of AI systems in domains where access to real-world data is restricted. In healthcare, clinical documentation presents particular challenges due to its sensitivity.
26 Jun 2026
Temporal variation poses a unique challenge for named entity recognition (NER) in historical texts, where entities drift in surface form and salience across time. While language models (LMs) have made progress in various NLP tasks, their ability to reason about temporality,…
26 Jun 2026
Training operator-learning models for large-scale problems governed by partial differential equations (PDEs) is challenging due to the curse of dimensionality, memory constraints, and limited training data.
26 Jun 2026
In recent times, Large Language Models (LLMs) are increasingly being used for legal case judgement summarization. Most prior works have tried traditional extractive and abstractive summarization of case judgements.
25 Jun 2026
Polynomial Stein discrepancies (PSD) provide a scalable alternative to kernel Stein methods for measuring sample quality and goodness-of-fit testing, but their statistical properties remain poorly understood.
25 Jun 2026
Spatial pattern matching is the process of matching query entities and constraints with database entities and relations. It has many applications, including similar region search, housing market search, landmark search, and road network matching.
25 Jun 2026
We introduce TabPFN-CFM, a causal foundation model that can handle multiple causal problems. TabPFN-CFM predicts both causal structure and outcomes from observational data, supports queries on all three levels of Pearl's Causal Hierarchy and uses known graph structure when…
25 Jun 2026
LLM coding harnesses grant agents broad file and shell access, yet the configuration layer that steers them -- rules files, agent definitions, IDE-specific markdown -- is largely unmanaged.
25 Jun 2026
Joint Embedding Predictive Architectures (JEPAs) have recently emerged as a promising paradigm for world modeling by learning predictive dynamics in a latent space rather than generating future observations at the input level.