Technology & AI
Paired sampling cuts variance in domain adaptation training
An arXiv preprint proposes pairing data into quadruplets to cut gradient variance in unsupervised domain adaptation, improving target accuracy on three
Marcello Babbili
AI and technology, explained through what they actually mean. An AI-assisted newsroom under human editorial rules — every story cites its primary sources so you can check them yourself.
499 stories
Technology & AI
Ex-Fuzzy library adds regression with 15 readable rules
New preprint extends Ex-Fuzzy with interpretable regression, hitting R² of 0.86 across 10 benchmarks using 10 to 15 human-readable rules.
Technology & AI
Adversarial Frontiers paper rethinks AI robustness testing
Adversarial Frontiers, a new arXiv preprint, argues single-budget AI robustness rankings are unstable and proposes a frontier-based evaluation framework.
Technology & AI
Language models overgeneralise and break on nested rules, study finds
Language models build shared rules instead of storing individual facts, KAIST AI finds, and the overgeneralisation affects teams fine-tuning on nested
Technology & AI
HyGRL targets multi-entity RAG with hybrid graph reasoning
HyGRL, a new arXiv paper from Beijing Institute of Technology, blends text with knowledge graphs to answer multi-entity questions that defeat standard RAG.
Technology & AI
CARGO beats trained LLM routers without training data
A new arXiv preprint from Purdue and Princeton shows LLM query routing can work without training data, using model self-agreement as a signal.
Technology & AI
LLM agents pass 100% JSON schema checks, still fail 1 in 5 orders
New OrderBench benchmark runs 2,400 calls across four open models and finds schema validity alone doesn't guarantee semantic correctness.
Technology & AI
AI agents turn robot videos into physics simulations
Agentic Real2Sim uses vision-language agents to convert real robot recordings into simulatable twins, aiming to cut the labor cost of training robots in
Technology & AI
JAXBench: curated TPU docs lift AI kernel correctness 5.8% to 37%
JAXBench, the first TPU benchmark for AI kernel generation, shows curated docs lift correctness from 5.8% to 37.3% and reach 1.6x speedup over XLA.
Technology & AI
LLM confidence scores fail basic coherence test
New arXiv paper finds calibration, the standard test for AI confidence, misses deeper incoherence in how models estimate their own certainty.
Technology & AI
Small AI models outperform LLM prompt guardrails, Fence says
A new arXiv preprint claims small language models trained on synthetic data outperform prompt-based LLM safety checks for hallucination and topic drift.
Technology & AI
LLM steering vectors get probabilistic fix in new paper
New arXiv preprint proposes Probabilistic Concept-Aware Steering, fixing incoherent behaviour in LLM steering vectors for open-weight model teams.