All Updates

Page 1454 of 1462

February 12, 2026

๐Ÿ“„
ArXiv AIโ€ข140d ago

LLMs Accelerate Systematic Mapping

Experience report on using LLMs for systematic mapping studies. Highlights time savings in screening and extraction but notes challenges like hallucinations and prompt engineering. Offers lessons and recommendations for adoption.

#research#llm-mapping#v1
๐Ÿ“„
ArXiv AIโ€ข140d ago

LLM Evolutionary Sampling Speeds Databases

DBPlanBench exposes physical query plans for LLM-proposed localized edits, refined via evolutionary search. LLMs leverage semantic knowledge for optimizations like join orderings. Achieves up to 4.78x speedups, with transfers from small to large databases.

#research#dbplanbench#v1
๐Ÿ“„
ArXiv AIโ€ข140d ago

LLM Agents Auto-Optimize RecSys Models

A self-evolving system uses Google's Gemini LLMs to autonomously generate, train, and deploy recommendation model improvements. It features an Offline Agent for hypothesis generation and an Online Agent for production validation. Deployed successfully at YouTube, surpassing manual workflows.

#research#youtube#v1
๐Ÿ“„
ArXiv AIโ€ข140d ago

LITT: Timing Transformer for EHR Events

LITT introduces a Timing-Transformer architecture that aligns sequential events on a virtual relative timeline for event-timing-focused attention. It enables personalized clinical trajectory interpretations. Validated on EHR data from 3,276 breast cancer patients to predict cardiotoxicity onset.

#research#litt#v1
๐Ÿ“„
ArXiv AIโ€ข140d ago

Latent Flows Model Reaction Trajectories

LatentRxnFlow predicts reactions as continuous latent trajectories via Conditional Flow Matching from reactant-product pairs. Offers SOTA USPTO accuracy with trajectory diagnostics and uncertainty estimation. Enables error mitigation and reliable predictions.

#research#latentrxnflow#v1
๐Ÿ“„
ArXiv AIโ€ข140d ago

Large-Scale AI Social Simulation Launched

AIvilization v0 deploys a resource-constrained artificial society with unified LLM agents. Features hierarchical planning, adaptive profiles, and human steering for long-horizon autonomy. Reproduces real market stylized facts like wealth stratification.

#research#aivilization#v0
๐Ÿ“„
ArXiv AIโ€ข140d ago

LAP Achieves Zero-Shot Robot Embodiment Transfer

Language-Action Pre-training (LAP) represents robot actions in natural language for zero-shot transfer across embodiments without fine-tuning. LAP-3B, a 3B VLA, delivers over 50% success on novel robots and tasks. Enables efficient adaptation and unifies action prediction with VQA.

#research#lap-3b#v1
๐Ÿ“„
ArXiv AIโ€ข140d ago

LakeMLB Benchmarks ML in Data Lakes

LakeMLB is a benchmark for machine learning in data lakes, focusing on multi-table union and join scenarios with real datasets from government, finance, and more. Supports pre-training, augmentation strategies. Evaluates tabular ML methods and releases datasets/code.

#research#lakemlb#data-lakes
๐Ÿ“„
ArXiv AIโ€ข140d ago

KSTER Attacks Reverse LLM Model Edits

KSTER exploits low-rank updates in locate-then-edit methods to recover edited data via spectral keyspace reconstruction and entropy prompt recovery. Achieves high success on multiple LLMs. Defense subspace camouflage uses decoys to hide fingerprints.

#security#kster#v1
๐Ÿ“„
ArXiv AIโ€ข140d ago

KPO Stabilizes LLM Policy Optimization

Online Causal Kalman Filtering models IS ratios as evolving latent states for stable RL in LLMs. Smooths noise while preserving token structure. Superior on math reasoning datasets.

#research#kpo#v1
๐Ÿ“„
ArXiv AIโ€ข140d ago

KG-Guided LLM for SSD Analysis

KORAL integrates LLMs with Data and Literature Knowledge Graphs for SSD diagnostics from fragmented telemetry. Provides descriptive, predictive, prescriptive, what-if analysis with explainable insights. Outperforms expert methods on production traces.

#research#koral#v1
๐Ÿ“„
ArXiv AIโ€ข140d ago

ImprovEvolve Boosts AlphaEvolve Solutions

Enhances LLM-guided evolution by evolving programs that propose, improve, and perturb solutions iteratively. Achieves new SOTA on hexagon packing and autocorrelation inequality benchmarks. Reduces LLM cognitive load via structured parameterization.

#research#improvevolve#v1
๐Ÿ“„
ArXiv AIโ€ข140d ago

HZO Speeds Zeroth-Order Optimization

Hierarchical Zero-Order optimization decomposes network depth for efficient ZO in DNNs. Reduces query complexity from O(ML^2) to O(ML log L). Matches backpropagation accuracy on CIFAR-10 and ImageNet.

#research#hzo#v1
๐Ÿ“„
ArXiv AIโ€ข140d ago

Human Guidance Excels in Vibe Coding

Presents experimental framework comparing human-led, AI-led, and hybrid vibe coding groups. Humans deliver superior iterative instructions, preventing AI-led performance collapse. Hybrids thrive with human direction and AI evaluation.

#research#vibe-coding#v1
๐Ÿ“„
ArXiv AIโ€ข140d ago

Guide Transitions Orgs to Agentic AI

Practical framework shifts organizations to agentic AI via domain-driven tasks and human-in-loop orchestration. Addresses challenges like workflow ownership and scaling. Emphasizes small AI-augmented teams with business alignment.

#research#agentic-framework#v1
๐Ÿ“„
ArXiv AIโ€ข140d ago

GTR Enhances Time Series Forecasting

Global Temporal Retriever (GTR) is a plug-and-play module extending MTSF models' context via global pattern retrieval. Uses adaptive embeddings, dynamic alignment, and 2D convolution fusion. SOTA results on six datasets with low overhead; code on GitHub.

#research#gtr#v1
๐Ÿ“„
ArXiv AIโ€ข140d ago

GRU-Mem Optimizes Long-Context LLM Reasoning

GRU-Mem introduces text-controlled gates to MemAgent for efficient long-context reasoning, preventing memory explosion and unnecessary computation. Update and exit gates manage recurrent memory loops via RL rewards. Achieves up to 400% faster inference on reasoning tasks.

#research#gru-mem#v1
๐Ÿ“„
ArXiv AIโ€ข140d ago

Generative Framework for Brain Infarct Masks

Introduces an anatomy-preserving method using VAE and latent diffusion to generate multi-class brain segmentation masks from NCCT data. It learns anatomical latents from masks only, generating realistic samples with optional lesion control. Avoids artifacts seen in pixel-space models.

#research#latent-diffusion#v1
๐Ÿ“„
ArXiv AIโ€ข140d ago

GenAI Framework for Higher Ed

Surveys reveal divided stakeholder perceptions of GenAI in IT/EE disciplines at University of Oulu. Proposes conceptual framework with high-level requirements for responsible integration. Ensures EU AI Act compliance and addresses privacy, integrity concerns.

#research#genai-framework#v1
๐Ÿ“„
ArXiv AIโ€ข140d ago

GameDevBench Evaluates Game Dev Agents

GameDevBench offers 132 multimodal game development tasks from tutorials. Agents struggle, with top solving 54.5%; tasks demand code and asset handling. Simple image/video feedback improves performance up to 47.7%.

#research#gamedevbench#v1
Page 1454 of 1462