PaperPulse logo
FeedTopicsAI Researcher FeedBlogPodcastAccount

Stay Updated

Get the latest research delivered to your inbox

Platform

  • Home
  • About Us
  • Search Papers
  • Research Topics
  • Researcher Feed

Resources

  • Newsletter
  • Blog
  • Podcast
PaperPulse•

AI-powered research discovery platform

© 2024 PaperPulse. All rights reserved.
Live Feed

AI Research Paper Feed

Discover cutting-edge research papers in AI and machine learning. Stay ahead with the latest breakthroughs, insights, and discoveries from top researchers worldwide.

21,679 Research Papers
Multi-Domain Coverage
Real-time Updates
ArXivFeb 3, 2026

Not All Negative Samples Are Equal: LLMs Learn Better from Plausible Reasoning

Zixiang Di, Jinyi Han et al.

TLDR: Plausible Negative Samples (PNS) improve the reasoning capabilities of Large Language Models by generating high-quality incorrect responses for training purposes.

00
ArXivFeb 3, 2026

Live or Lie: Action-Aware Capsule Multiple Instance Learning for Risk Assessment in Live Streaming Platforms

Yiran Qiao, Jing Chen et al.

TLDR: The study introduces AC-MIL, a novel framework for assessing risks in live streaming by analyzing user behaviors and coordination patterns, significantly improving detection accuracy and interpretability over existing methods.

00
ArXivFeb 3, 2026

HySparse: A Hybrid Sparse Attention Architecture with Oracle Token Selection and KV Cache Sharing

Yizhao Gao, Jianyu Wei et al.

TLDR: HySparse is a new hybrid sparse attention model that improves performance and reduces memory usage by using full attention layers as oracles for token selection and sharing KV caches with sparse layers.

00
ArXivFeb 3, 2026

EVE: Efficient Verification of Data Erasure through Customized Perturbation in Approximate Unlearning

Weiqi Wang, Zhiyi Tian et al.

TLDR: EVE introduces an efficient method for verifying machine unlearning by using customized perturbations, eliminating the need for initial model training involvement and improving verification accuracy and speed.

00
ArXivFeb 3, 2026

Persona Generators: Generating Diverse Synthetic Personas at Scale

Davide Paglieri, Logan Cross et al.

TLDR: Persona Generators create diverse synthetic personas using large language models to improve AI system testing across varied user populations.

00
ArXivFeb 3, 2026

D3PIA: A Discrete Denoising Diffusion Model for Piano Accompaniment Generation From Lead sheet

Eunjin Choi, Hounsu Kim et al.

TLDR: D3PIA is a discrete diffusion model that effectively generates piano accompaniments from lead sheets, outperforming other models in preserving chord conditions and musical coherence.

00
ArXivFeb 3, 2026

TodyComm: Task-Oriented Dynamic Communication for Multi-Round LLM-based Multi-Agent System

Wenzhe Fan, Tommaso Tognoli et al.

TLDR: TodyComm is a dynamic communication algorithm for multi-agent systems that adapts to changing conditions, improving task effectiveness and efficiency.

01
ArXivFeb 3, 2026

ContraLog: Log File Anomaly Detection with Contrastive Learning and Masked Language Modeling

Simon Dietz, Kai Klede et al.

TLDR: ContraLog is a parser-free method for log anomaly detection using contrastive learning and masked language modeling to predict message embeddings, showing effectiveness on benchmark datasets.

03
ArXivFeb 3, 2026

Use Graph When It Needs: Efficiently and Adaptively Integrating Retrieval-Augmented Generation with Graphs

Su Dong, Qinggang Zhang et al.

TLDR: EA-GraphRAG efficiently integrates retrieval-augmented generation with graph-based methods, improving accuracy and reducing latency by dynamically adapting to query complexity.

00
ArXivFeb 3, 2026

EHRWorld: A Patient-Centric Medical World Model for Long-Horizon Clinical Trajectories

Linjie Mu, Zhongzhen Huang et al.

TLDR: EHRWorld is a new medical world model that improves long-term clinical simulations by using a large dataset of real-world electronic health records, outperforming models based solely on large language models (LLMs).

00
ArXivFeb 3, 2026

When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs

Bogdan Zagribelnyy, Ivan Ilin et al.

TLDR: This paper introduces a new benchmarking framework for retrosynthesis using large language models (LLMs), emphasizing chemical plausibility over exact matches and presenting a novel dataset, CREED, to improve LLM performance.

00
ArXivFeb 3, 2026

ELIQ: A Label-Free Framework for Quality Assessment of Evolving AI-Generated Images

Xinyue Li, Zhiming Xu et al.

TLDR: ELIQ is a label-free framework designed to assess the quality of AI-generated images, adapting to evolving generative models without the need for human annotations.

00
ArXivFeb 3, 2026

Group Selection as a Safeguard Against AI Substitution

Qiankun Zhong, Thomas F. Eisenmann et al.

TLDR: The paper explores how AI reliance impacts cultural diversity, suggesting that group selection may help preserve cultural variance and innovation against AI substitution in creative work.

00
ArXivFeb 3, 2026

Morphe: High-Fidelity Generative Video Streaming with Vision Foundation Model

Tianyi Gong, Zijian Cao et al.

TLDR: Morphe is a new video streaming method that uses vision foundation models to achieve high visual quality and efficient bandwidth usage even in poor network conditions.

00
ArXivFeb 3, 2026

Anytime Pretraining: Horizon-Free Learning-Rate Schedules with Weight Averaging

Alexandru Meterez, Pranav Ajit Nair et al.

TLDR: This paper introduces anytime pretraining schedules using weight averaging, which provide effective learning rate strategies for language models without needing a fixed training horizon.

01
ArXivFeb 3, 2026

Decision-oriented benchmarking to transform AI weather forecast access: Application to the Indian monsoon

Rajat Masiwal, Colin Aitken et al.

TLDR: This paper introduces a decision-oriented framework for evaluating AI weather prediction models, using Indian monsoon forecasting as a case study to benefit rain-fed agriculture and support millions of farmers with actionable forecasts.

01
ArXivFeb 3, 2026

QuAIL: Quality-Aware Inertial Learning for Robust Training under Data Corruption

Mattia Sabella, Alberto Archetti et al.

TLDR: QuAIL is a new training mechanism that improves machine learning model performance on corrupted tabular data by using feature reliability information to guide learning.

01
ArXivFeb 3, 2026

LLM-Inspired Pretrain-Then-Finetune for Small-Data, Large-Scale Optimization

Zishi Zhang, Jinhui Han et al.

TLDR: This paper proposes a novel pretrain-then-finetune approach using a Transformer model to tackle small-data, large-scale optimization problems by leveraging synthetic data and domain knowledge.

01
ArXivFeb 3, 2026

RAGTurk: Best Practices for Retrieval Augmented Generation in Turkish

Süha Kağan Köse, Mehmet Can Baytekin et al.

TLDR: The study develops a Turkish-specific Retrieval-Augmented Generation (RAG) dataset and benchmarks various methods, finding that complex methods like HyDE significantly improve accuracy over simpler baselines.

02
ArXivFeb 3, 2026

Mitigating Staleness in Asynchronous Pipeline Parallelism via Basis Rotation

Hyunji Jung, Sungbin Shin et al.

TLDR: This study addresses gradient staleness in asynchronous pipeline parallelism by using basis rotation to improve alignment and accelerate convergence, achieving faster training for large models.

00
Showing 1-20 of 21679 papers
per page
…
1 / 1084