The Archive

Pythia multi-agent system for autonomous clinical symptom extraction using open-weights LLMs without fine-tuning.

Study showing LLM judges exhibit bias and over-generosity in no-reference evaluation settings across multiple languages.

Benchmark evaluating LLM capability to identify and correct patient misconceptions across multi-turn medical conversations.

Deep4ge: public dataset of 14,227 DNN training runs with fault annotations for detection and diagnosis from training trajectories.

New York has become the first state to temporarily halt approval of large data centers, as Gov. Kathy Hochul argues the AI-driven building boom shouldn’t come at the expense of higher electricity costs, water supplies, or local control.

ROBIN method localizes and repairs bias in transformer attention heads via inference-time intervention without retraining.

EEC explainer reveals mechanisms of emergent collective behaviors in multi-agent RL for robot swarms despite black-box neural policies.

ChartGenEval introduces corruption-tested benchmark for rhythm-game chart generation evaluation beyond reference-note agreement.

Open-weight reasoning models fine-tuned via RLVR for thermal energy storage control, achieving building-scale load shifting with 30 prompts.

New York’s data center moratorium may become the blueprint for anti-AI movement.

Anthropic launches Claude for Teachers, an educational product tier for classroom use with curriculum resources and safety guardrails.

Superparamagnetic nanodot reservoir computing substrate demonstrates temperature robustness for unconventional ultra-low energy computing.

Meta-evaluation of LLM-generated rubrics for paper reproduction tasks; first systematic study on checklist-based evaluation reliability.

ANGLE framework applies generative learning for non-parametric distributional regression on circular/angular data in computer vision and biology.

KLLMs pretraining paradigm suppresses parametric recall via entity anonymization, forcing evidence-grounded reasoning over memorized knowledge.

Survey of efficient inference techniques for diffusion-based LLMs, covering algorithms and systems beyond theoretical parallel generation claims.

Philosophical analysis of Hempel's statistical ambiguity problem via maximally specific laws; applications to causal AI.

Reflection AI has signed a $1 billion deal to access Nebius's compute. Reflection was founded in 2024 and is developing open source AI technology.

Study examines how iterative AI agent interaction creates neuroplastic conditioning loops, reshaping human cognitive patterns through high-frequency feedback cycles.

Causal intervention analysis reveals Vision-Language Models' Chain-of-Thought reasoning relies on early visual token access, not continuous image grounding during generation.

Hugging Face CEO Clem Delangue says enterprises increasingly want open models, due to cost, accessibility, and ownership. Do frontier models still matter if most production AI ends up running on open models?

PixelLoop introduces pixel-space loop closures for topological navigation, extending SLAM-style corrections to dense relative geometry representations.

Fixed-wing UAV control framework integrates YOLO vision, Kalman filtering, and NMPC for autonomous target tracking and terminal guidance.

Benchmark across 44 language models reveals 41% convergence on 'serendipity' when asked to name any word, exposing hidden conformity in model outputs.

JADR protocol uses Jacobian space analysis to measure models' internal danger-recognition representations, bypassing LLM-judge evaluation artifacts in jailbreak robustness testing.

Spotify is rolling out a new AI-powered conversational feature that lets Premium subscribers chat with the app to discover music, podcasts, and audiobooks, and more.

Framework evolves evaluation metrics alongside agent skills using evolutionary search over drawback detectors, enabling self-improving systems without pre-defined oracles.

Adaptive Vector-Quantized Attention allocates codebook capacity proportionally to attention importance, reducing transformer complexity from O(N²) to O(MN) with precision targeting.

Study questions whether multimodal emotion recognition requires >1B parameters, testing compression of 7B+ models for real-time deployment on edge devices.

OpenAI has spent the better part of the year involved in lawsuit after lawsuit, including one from the world's richest man. But last Friday, the company was hit with one of the highest-profile legal actions yet - from Apple. OpenAI's expensive hardware bet is what's on the line. Apple's lawsuit against OpenAI, filed in Northern California federal court, accused former Apple employees of "stealing Apple's trade secrets for the benefit of OpenAI." The 41-page complaint states that Apple keeps its "product development, manufacturing, supply chain, technology research, and other innovations confi...