Nachrichten
Red-Bandit: Test-Time Adaptation for LLM Red-Teaming via Bandit-Guided LoRA Experts
arXiv:2510.07239v1 Announce Type: new Abstract: Automated red-teaming has emerged as a scalable approach for auditing...
Recognizing Limits: Investigating Infeasibility in Large Language Models
arXiv:2408.05873v3 Announce Type: replace Abstract: Large language models (LLMs) have shown remarkable performance in various...
READoc: A Unified Benchmark for Realistic Document Structured Extraction
arXiv:2409.05137v3 Announce Type: replace Abstract: Document Structured Extraction (DSE) aims to extract structured content from...
Readers Prefer Outputs of AI Trained on Copyrighted Books over Expert Human Writers
arXiv:2510.13939v1 Announce Type: new Abstract: The use of copyrighted books for training AI models has...
Readability Reconsidered: A Cross-Dataset Analysis of Reference-Free Metrics
arXiv:2510.15345v1 Announce Type: new Abstract: Automatic readability assessment plays a key role in ensuring effective...
RAG-based Architectures for Drug Side Effect Retrieval in LLMs
arXiv:2507.13822v1 Announce Type: cross Abstract: Drug side effects are a major global health concern, necessitating...
RaDialog: A Large Vision-Language Model for Radiology Report Generation and Conversational Assistance
arXiv:2311.18681v3 Announce Type: replace-cross Abstract: Conversational AI tools that can generate and discuss clinically correct...
RA3: Mid-Training with Temporal Action Abstractions for Faster Reinforcement Learning (RL) Post-Training in Code LLMs
TL;DR: A new research from Apple, formalizes what “mid-training” should do before reinforcement learning RL...
R-Zero: A Fully Autonomous AI Framework that Generates Its Own Training Data from Scratch
Large Language Models (LLMs) have revolutionized fields from natural language understanding to reasoning and code...
QwenLong-L1 solves long-context reasoning challenge that stumps current LLMs
Alibaba’s QwenLong-L1 helps LLMs deeply understand long documents, unlocking advanced reasoning for practical enterprise applications.Read...
Qwen3-ASR-Toolkit: An Advanced Open Source Python Command-Line Toolkit for Using the Qwen-ASR API Beyond the 3 Minutes/10 MB Limit
Qwen has released Qwen3-ASR-Toolkit, an MIT-licensed Python CLI that programmatically bypasses the Qwen3-ASR-Flash API’s 3-minute/10...
Quiet Feature Learning in Algorithmic Tasks
arXiv:2505.03997v1 Announce Type: cross Abstract: We train Transformer-based language models on ten foundational algorithmic tasks...
