The Archive

CRS-Triage: ML model for emergency patient acuity prediction with confidence scoring handling incomplete and unreliable EHR data.

SciRet: Empirical study of hybrid BM25+dense retrieval, reranking, and answer generation for scientific RAG across corpus scales on CORD-19.

Source-Conditioned Description-Length Gain detects LLM-generated plagiarism via probabilistic compression, distinguishing source reuse from similarity.

A central challenge in robotics is building policies that generalize beyond the demonstrations they’re trained on. A policy that succeeds in a training scene... A central challenge in robotics is building policies that generalize beyond the demonstrations they’re trained on. A policy that succeeds in a training scene often fails when object shapes, positions, or lighting change. Generalizing to these new conditions requires the policy to understand the tasks underlying physics, not just mimic the demonstrations. This ability comes from the backbone it’s… Source

CheMatE: ModernBERT-based embedding model for joint SMILES-NLP representation learning in chemistry, addressing domain overfitting.

Quantization precision (FP16/INT8/INT4) and prompt design critically affect biomedical LLM classifier calibration on Mistral variants.

FedCritic-MIMO: federated multi-agent RL for 6G RAN resource control via serverless critic sharing.

MAFIA: query-only memory poisoning attacks on audited LLM agents via probing and factual injection.

Spotify says Merlin, which represents more than 30,000 independent labels and distributors, has joined Universal Music Group in backing its upcoming AI-powered remix and covers product. The paid tool will let fans create AI-generated covers and remixes of participating artists’ music while ensuring artists opt in, receive credit, and are compensated.

Layer-wise analysis shows sensitivity, causality, and repair capacity dissociate when LLMs fail on perturbed input; identifies spike-and-suppress vs. late-accumulation regimes.

Oilbird: training-free speculative decoding using verifier-computed keys; improves suffix matching for tool-calling workloads.

LatentGuard: safeguard framework compressing textual reasoning into latent states for efficient, inspectable LLM content moderation.

RESUME CONTRACT: TLA+ specification for checkpoint/interrupt/resume semantics across workflow persistence layers, exposing non-compliant agent frameworks.

Texas Governor Greg Abbott has paused new data center development until an audit has been completed.

Geo-Embed: unified multimodal embedding model for urban/geospatial tasks spanning street-view imagery, remote sensing, text, and temporal change.

Texas announced new a audit on data centers that could slow approval for new facilities seeking to connect to the state energy grid. Governor Greg Abbott (R) on Monday directed the Public Utility Commission of Texas (PUCT) and the Electric Reliability Council of Texas (ERCOT) to verify and audit new data center proposals, writing that the review is needed to "keep the grid stable and reliable." Data centers will need to provide information on state and local incentives they've received, how much they'd rely on the state grid, expected water consumption and sources, and how they plan to track ...

FlowForm: satellite flood image synthesis using SWE-inspired latent regularization and structure-aware conditioning for data augmentation.

An analysis of the last seven years of Tesla earnings calls shows just little attention Musk pays to Tesla's car business.

Autonomous vehicle (AV) development often relies on separate models for trajectory generation, high-level intent prediction, scene understanding, and data... Autonomous vehicle (AV) development often relies on separate models for trajectory generation, high-level intent prediction, scene understanding, and data labeling. This separation makes it hard to compare related outputs, investigate model behavior, and reuse the same representations across the development workflow. NVIDIA Alpamayo 2 Super is an open 34-billion-parameter reasoning vision… Source

Computing actual causes for neural network predictions using Halpern-Pearl causal models and Boolean SCMs to improve explainability under structured input dependencies.

MDLMPE: distribution-aware positional encoding for masked diffusion language models to handle dynamic token-availability patterns during denoising.

GDPevo: benchmark for evaluating agent self-evolution on real business workflows with automated data pipeline to prevent contamination.

Faithfulness-safety tension in Large Reasoning Models: models must be interpretable for monitoring yet robust against unsafe reasoning paths.

Multi-agent clinical committees using Gemini show vulnerability to social shortcut cascades where peer consensus propagates errors across agents.

LLM capability for testing Terminal User Interfaces: benchmark across ratatui/Rust, bubbletea/Go, textual/Python showing 12% coverage in real applications.

Narrative review of AI-based sound effect generation across input modalities: text, visual, audio, and multimodal for digital applications.

MissClick: adversarial attack on GUI grounding models exploiting digit-serialized coordinate generation to induce large spatial click displacement.

AgenticECO: tool-using agent workflow for 3D-IC engineering change orders with minimal-disturbance routing layer on TaiWei open-source flow.

Taxonomy of multilingual multi-agent planning failures: request-to-action grounding degradation strongest in low-resource languages.

Self-augmentation method for MLLMs using model failure signals to generate targeted image augmentations without external supervision.