RouteRAG is a novel approach that trains language models with reinforcement learning to dynamically decide when to reason, which type of retrieval to use (passage, …
Large Language Models (LLMs) have demonstrated exceptional abilities in comprehending and generating text, motivating numerous researchers to utilize them for Information Extraction (IE) purposes, including …
Structured Prediction as Translation between Augmented Natural Languages. It is the official code for TANL paper.
Extracting relation triplets from raw text is a crucial task in Information Extraction, enabling multiple applications such as populating or validating knowledge bases, factchecking, and …
REBEL is a seq2seq model that simplifies Relation Extraction (EMNLP 2021).
We introduce copresheaf topological neural networks (CTNNs), a powerful and unifying framework that encapsulates a wide spectrum of deep learning architectures, designed to operate on …
Large Language Models (LLMs) have shown remarkable generalization capability with exceptional performance in various language modeling tasks. However, they still exhibit inherent limitations in precisely …
i want to run a small jorunal club this weekend
Kayewords: genetics weekendJournal Club du DESS Unisanté centré sur des articles clés en épidémiologie et santé publique.
Kayewords: epidemiology; public healthAutoregressive models (ARMs) are widely regarded as the cornerstone of large language models (LLMs). We challenge this notion by introducing LLaDA, a diffusion model trained …
AlphaEvolve is a generic evolutionary coding agent that combines the generative capabilities of LLMs with automated evaluation in an iterative evolutionary framework that proposes, tests, …
Graph learning has rapidly evolved into a critical subfield of machine learning and artificial intelligence (AI). Its development began with early graph-theoretic methods, gaining significant …
Hosted by the Department of Inorganic and Organic Chemistry (FQM-273) at the University of Jaén, this journal club provides a collaborative forum for postgraduate students, …
Kayewords: Hybrid materials, surface chemistry, nanostructures, …Generating graph-structured data is crucial in applications such as molecular generation, knowledge graphs, and network analysis. However, their discrete, unordered nature makes them difficult for …
The rapid rise of compound AI systems (a.k.a., AI agents) is reshaping the labor market, raising concerns about job displacement, diminished human agency, and overreliance …
We develop new methods to integrate experimental and observational data in causal inference. While randomized controlled trials offer strong internal validity, they are often costly …
In this work, we tested the Triplet Extraction (TE) capabilities of a variety of Large Language Models (LLMs) of different sizes in the Zero- and …
This repository contains the official resources for the paper "On the Theoretical Limitations of Embedding-based Retrieval". This work introduces the LIMIT dataset, designed to stress-test …
A new paper from Google DeepMind challenges the assumption that better data or bigger models alone can overcome the limitations of single vector embeddings for …
Keywords: vector embeddings, information retrieval, large …The expressiveness of flow-based models combined with stochastic variational inference (SVI) has expanded the application of optimization-based Bayesian inference to highly complex problems. However, despite …
The rapid advancement of generative AI enables highly realistic synthetic videos, posing significant challenges for content authentication and raising urgent concerns about misuse. Existing detection …
Large Language Models (LLMs) demonstrate remarkable reasoning capabilities, yet the structural mechanisms underlying these abilities remain under explored. In this work, we introduce GraphGhost, a …
Rectified Flows learn ODE vector fields whose trajectories are straight between source and target distributions, enabling near one-step inference. We show that this straight-path objective …
Agentic AI Reading Group @ ANL
Kayewords: Agent, AIReinforcement learning (RL) has recently become a strong recipe for training reasoning LLMs that produce long chains of thought (LongCoT). Yet the standard RL "thinking …