academic-research

Tag

Cards List
#academic-research

@julien_c: Thank you

X AI KOLs Timeline · 12h ago Cached

arXiv has received a 17.2 million investment from Simons Foundation International, Siegel Family Endowment, and XTX Markets to support its operations.

0 favorites 0 likes
#academic-research

@rohanpaul_ai: Disclosed AI use in math rose from 1.39% to 14.09% in under 6 months. The authors scanned 32,944 math-related arXiv pap…

X AI KOLs Following · yesterday Cached

A study found that disclosed AI use in mathematics-related arXiv papers increased significantly from 1.39% to 14.09% in a six-month period.

0 favorites 0 likes
#academic-research

Continuous Optimization for p-adic Models

arXiv cs.LG · yesterday Cached

This paper introduces the first method for continuous gradient descent optimization in machine learning models with p-adic parameters, using the Berkovich affine line to enable effective learning on tasks like modular arithmetic.

0 favorites 0 likes
#academic-research

Are Human-Aligned Models Models of Humans? A Turing-Test Gap in Preference Alignment

arXiv cs.AI · yesterday Cached

This paper distinguishes between aligning AI with human preferences versus human behavior, showing that preference alignment can reduce human-likeness and establishing a Turing-test gap in current alignment methods.

0 favorites 0 likes
#academic-research

Self-Organizing Agent Teams Learn to Reason Together

arXiv cs.AI · yesterday Cached

The paper introduces Self-Organizing Agent Teams (SAT), a method where AI agents learn reusable strategies to collaborate and reason together, achieving higher accuracy on mathematics and physics benchmarks compared to individual agents and baseline methods.

0 favorites 0 likes
#academic-research

MoM: Memory of Memory

arXiv cs.CL · yesterday Cached

This paper introduces Memory of Memory (MoM), a framework for LLM agent memory that commits current values on arrival while retaining displaced values as provenance, improving accuracy and reducing stale answers.

0 favorites 0 likes
#academic-research

FrontierMath Erd\H{o}s

arXiv cs.CL · yesterday Cached

The paper introduces FrontierMath Erdős, a benchmark of 68 open Erdős problems for evaluating AI models in mathematics using Lean proof assistant, aiming to address shortcomings in current AI research demonstrations.

0 favorites 0 likes
#academic-research

Agreement Overstates Evidence: Error Dependence in LLM Judge Consensus

arXiv cs.AI · yesterday Cached

This paper examines how error correlation among LLM judges reduces the statistical independence of consensus, showing that shared mistakes can make agreement appear stronger than it is, leading to incorrect conclusions in up to 28% of cases, and proposes using trusted examples to estimate and account for these dependencies.

0 favorites 0 likes
#academic-research

Social Influence and the Allocation of Scientific Attention in AI Populations

arXiv cs.AI · yesterday Cached

This paper adapts the Music Lab experiment to study how social influence affects AI agents' selection of scientific papers, showing that social information reduces attention volume and breadth while increasing between-community variation.

0 favorites 0 likes
#academic-research

A New Chatbot Wants to Unlock the Secrets in Tattered Ancient Greek Records

Wired · yesterday Cached

The Austrian Academy of Science, partnering with Mistral and Sail Reply, releases Apollo, the first advanced large language model for Ancient Greek to help scholars restore tattered papyrus fragments by predicting missing words.

0 favorites 0 likes
#academic-research

PAGE: Partition-Aware Gated KV-Cache Eviction

arXiv cs.LG · 2d ago Cached

The paper introduces PAGE, a partition-aware gated KV-cache eviction method that uses a scalar metric to predict input classes and apply eviction only when safe, reducing accuracy degradation in large language models.

0 favorites 0 likes
#academic-research

ZoAQ: Adaptive Zeroth-Order Querying via Query-Reuse Coupling

arXiv cs.LG · 2d ago Cached

ZoAQ presents an adaptive zeroth-order optimization method that reuses past queries to reduce evaluation counts, saving 43–48% of queries in synthetic tasks and achieving high success in black-box attacks.

0 favorites 0 likes
#academic-research

Lifestreams: a storage model for personal data (1996)

Lobsters Hottest · 2d ago Cached

This 1996 paper introduces Lifestreams, a storage model for organizing personal digital data into a continuous, searchable stream.

0 favorites 0 likes
#academic-research

OpenMAS-GCom. A Diagnostic Benchmark for Graph-enhanced Multi-Agent Systems

arXiv cs.LG · 3d ago Cached

OpenMAS-GCom introduces a diagnostic benchmark for evaluating graph-enhanced multi-agent systems by using controlled interventions to attribute performance differences to specific organizational components.

0 favorites 0 likes
#academic-research

AutoRecLab: Describe the Experiment, Get the Code!

arXiv cs.AI · 3d ago Cached

AutoRecLab is an autonomous Python-based system that automates recommender systems experiments from natural-language prompts, using retrieval-augmented generation (RAG), static verification, and tree search to generate and validate executable code.

0 favorites 0 likes
#academic-research

LLM-Generated Feature Pools for Time Series Anomaly Detection

arXiv cs.AI · 3d ago Cached

This paper explores using a multimodal LLM to generate domain-specific feature pools for time series anomaly detection, showing that a simple statistical pipeline can match the performance of advanced pretrained models on benchmark datasets.

0 favorites 0 likes
#academic-research

An Introduction to Compression-Based Machine Learning

arXiv cs.LG · 3d ago Cached

This article surveys the connection between lossless compression algorithms and machine learning, introducing a design framework that makes compression-based methods competitive with conventional baselines and particularly effective for malware classification.

0 favorites 0 likes
#academic-research

DENSE: Distilling Agent Trajectories into Evidence-Grounded Shortcut Trees for Self-Refinement

arXiv cs.AI · 3d ago Cached

The paper introduces DENSE, a method for distilling AI agent execution traces into evidence-grounded shortcut trees for self-refinement, achieving improved performance on Terminal-Bench without post-hoc outcome labels.

0 favorites 0 likes
#academic-research

SAGE: Schema-Guided LLMs for Grant Review

arXiv cs.CL · 3d ago Cached

SAGE is a schema-guided system that uses large language models to automate grant review by structuring rubrics and linking evidence, with human-in-the-loop validation to improve accuracy.

0 favorites 0 likes
#academic-research

All-in-One Multilingual Scene Text Recognition with Script-aware Mixture-of-Experts

Hugging Face Daily Papers · 3d ago Cached

The paper introduces ScriptMoE, a script-aware mixture-of-experts architecture for all-in-one multilingual scene text recognition, along with the TextMuSS-10M synthetic dataset, achieving state-of-the-art accuracy on benchmarks.

0 favorites 0 likes
Next →
← Back to home

Submit Feedback