Natural Language Processing

Text understanding and language tasks

This Week's Best | Monthly Best | Guide | Trending

Top This Week

[2603.24326] Boosting Document Parsing Efficiency and Performance with Coarse-to-Fine Visual Processing
Llms

[2603.24326] Boosting Document Parsing Efficiency and Performance with Coarse-to-Fine Visual Processing

Abstract page for arXiv paper 2603.24326: Boosting Document Parsing Efficiency and Performance with Coarse-to-Fine Visual Processing

arXiv - AI · 4 min ·
[2601.13508] Autonomous Computational Catalysis Research via Agentic Systems
Nlp

[2601.13508] Autonomous Computational Catalysis Research via Agentic Systems

Abstract page for arXiv paper 2601.13508: Autonomous Computational Catalysis Research via Agentic Systems

arXiv - AI · 3 min ·
[2510.20847] Integrated representational signatures strengthen specificity in brains and models
Machine Learning

[2510.20847] Integrated representational signatures strengthen specificity in brains and models

Abstract page for arXiv paper 2510.20847: Integrated representational signatures strengthen specificity in brains and models

arXiv - AI · 4 min ·

All Content

[2507.14186] A Disentangled Representation Learning Framework for Low-altitude Network Coverage Prediction
Nlp

[2507.14186] A Disentangled Representation Learning Framework for Low-altitude Network Coverage Prediction

This paper presents a novel framework for predicting low-altitude network coverage using disentangled representation learning, addressing...

arXiv - Machine Learning · 4 min ·
[2602.12247] ExtractBench: A Benchmark and Evaluation Methodology for Complex Structured Extraction
Llms

[2602.12247] ExtractBench: A Benchmark and Evaluation Methodology for Complex Structured Extraction

ExtractBench introduces a benchmark and evaluation framework for extracting structured data from unstructured documents like PDFs, addres...

arXiv - AI · 4 min ·
[2602.10603] dnaHNet: A Scalable and Hierarchical Foundation Model for Genomic Sequence Learning
Llms

[2602.10603] dnaHNet: A Scalable and Hierarchical Foundation Model for Genomic Sequence Learning

The paper presents dnaHNet, a novel tokenizer-free autoregressive model designed for genomic sequence learning, achieving significant eff...

arXiv - Machine Learning · 4 min ·
[2602.04942] Privileged Information Distillation for Language Models
Llms

[2602.04942] Privileged Information Distillation for Language Models

This paper presents methods for distilling privileged information in language models, focusing on improving performance in multi-turn env...

arXiv - AI · 4 min ·
[2602.02201] Cardinality-Preserving Attention Channels for Graph Transformers in Molecular Property Prediction
Machine Learning

[2602.02201] Cardinality-Preserving Attention Channels for Graph Transformers in Molecular Property Prediction

This article presents a novel graph transformer model, incorporating cardinality-preserving attention channels, to enhance molecular prop...

arXiv - Machine Learning · 3 min ·
[2602.00628] From Associations to Activations: Comparing Behavioral and Hidden-State Semantic Geometry in LLMs
Llms

[2602.00628] From Associations to Activations: Comparing Behavioral and Hidden-State Semantic Geometry in LLMs

This paper examines the relationship between behavioral and hidden-state semantic geometry in large language models (LLMs) through psycho...

arXiv - AI · 3 min ·
[2505.07671] Benchmarking Retrieval-Augmented Generation for Chemistry
Llms

[2505.07671] Benchmarking Retrieval-Augmented Generation for Chemistry

This article presents ChemRAG-Bench, a benchmark for evaluating retrieval-augmented generation (RAG) in chemistry, demonstrating signific...

arXiv - AI · 4 min ·
[2601.09495] Parallelizable memory recurrent units
Machine Learning

[2601.09495] Parallelizable memory recurrent units

The paper introduces memory recurrent units (MRUs), a new family of RNNs that combine persistent memory with parallelizable computations,...

arXiv - Machine Learning · 4 min ·
[2512.13228] ModSSC: A Modular Framework for Semi-Supervised Classification on Heterogeneous Data
Nlp

[2512.13228] ModSSC: A Modular Framework for Semi-Supervised Classification on Heterogeneous Data

ModSSC is an open-source Python framework designed for semi-supervised classification, enhancing reproducibility and experimentation acro...

arXiv - Machine Learning · 3 min ·
[2502.16730] RapidPen: Fully Automated IP-to-Shell Penetration Testing with LLM-based Agents
Llms

[2502.16730] RapidPen: Fully Automated IP-to-Shell Penetration Testing with LLM-based Agents

RapidPen is a novel automated penetration testing framework that utilizes large language models to autonomously exploit vulnerabilities, ...

arXiv - AI · 4 min ·
[2511.02077] Beyond Static Cutoffs: One-Shot Dynamic Thresholding for Diffusion Language Models
Llms

[2511.02077] Beyond Static Cutoffs: One-Shot Dynamic Thresholding for Diffusion Language Models

This article presents One-Shot Dynamic Thresholding (OSDT) for diffusion language models, enhancing decoding efficiency and accuracy by c...

arXiv - Machine Learning · 3 min ·
[2510.15987] Algorithmic Primitives and Compositional Geometry of Reasoning in Language Models
Llms

[2510.15987] Algorithmic Primitives and Compositional Geometry of Reasoning in Language Models

The paper explores how algorithmic primitives and compositional geometry can enhance reasoning capabilities in large language models (LLM...

arXiv - AI · 4 min ·
[2510.04008] RACE Attention: A Strictly Linear-Time Attention for Long-Sequence Training
Machine Learning

[2510.04008] RACE Attention: A Strictly Linear-Time Attention for Long-Sequence Training

The paper presents RACE Attention, a novel linear-time attention mechanism designed for long-sequence training, significantly improving e...

arXiv - Machine Learning · 4 min ·
[2510.03272] Where to Add PDE Diffusion in Transformers
Machine Learning

[2510.03272] Where to Add PDE Diffusion in Transformers

This paper investigates the optimal placement of PDE diffusion layers in transformer architectures, revealing that their insertion order ...

arXiv - AI · 4 min ·
[2510.02410] OpenTSLM: Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series Data
Llms

[2510.02410] OpenTSLM: Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series Data

OpenTSLM introduces a new family of Time Series Language Models designed to enhance reasoning over multivariate medical data, outperformi...

arXiv - Machine Learning · 4 min ·
[2601.21654] ScholarGym: Benchmarking Large Language Model Capabilities in the Information-Gathering Stage of Deep Research
Llms

[2601.21654] ScholarGym: Benchmarking Large Language Model Capabilities in the Information-Gathering Stage of Deep Research

The paper introduces ScholarGym, an evaluation environment designed to benchmark large language models in the information-gathering phase...

arXiv - AI · 3 min ·
[2601.15311] Aeon: High-Performance Neuro-Symbolic Memory Management for Long-Horizon LLM Agents
Llms

[2601.15311] Aeon: High-Performance Neuro-Symbolic Memory Management for Long-Horizon LLM Agents

The paper presents Aeon, a Neuro-Symbolic Cognitive Operating System designed to enhance memory management in Long-Horizon LLM agents, ad...

arXiv - AI · 4 min ·
[2508.19228] Predicting the Order of Upcoming Tokens Improves Language Modeling
Llms

[2508.19228] Predicting the Order of Upcoming Tokens Improves Language Modeling

The paper presents a novel approach to language modeling by introducing token order prediction (TOP) as an improvement over traditional n...

arXiv - Machine Learning · 4 min ·
[2508.11025] Zono-Conformal Prediction: Zonotope-Based Uncertainty Quantification for Regression and Classification Tasks
Machine Learning

[2508.11025] Zono-Conformal Prediction: Zonotope-Based Uncertainty Quantification for Regression and Classification Tasks

The paper introduces Zono-Conformal Prediction, a method for uncertainty quantification in regression and classification tasks that impro...

arXiv - AI · 4 min ·
[2510.20102] Human-Centered LLM-Agent System for Detecting Anomalous Digital Asset Transactions
Llms

[2510.20102] Human-Centered LLM-Agent System for Detecting Anomalous Digital Asset Transactions

The paper presents HCLA, a human-centered multi-agent system designed for detecting anomalies in digital asset transactions, enhancing in...

arXiv - AI · 4 min ·
Previous Page 119 Next

Related Topics

Machine Learning Large Language Models Generative AI Computer Vision Robotics & Embodied AI AI Safety & Ethics

Stay updated with AI News

Get the latest news, tools, and insights delivered to your inbox.

Subscribe to Newsletter

Daily or weekly digest • Unsubscribe anytime