Search the full wire by company, model, lab, or keyword. Every story we have ever aggregated.
Study shows Qwen-VL achieves 87.3% accuracy on vehicle damage classification but fails spatial grounding for fine-grained defects; proposes dedicated segmentation layer.
Microsecond-cost anomaly detection for LLM agent failures using one-class echo-state networks trained only on healthy runs; tested across Qwen, Llama, and Gemini agents.
Cross-modal analysis of scientific formulae shows weak correspondence between syntactic and semantic representations despite joint modeling improving retrieval.
Aggregate-then-Calibrate framework combines heterogeneous human judgments with model scores to assess human-centered tasks lacking ground truth with theoretical guarantees.
LTL-to-LTLf+ translation reduces computational complexity of temporal logic specifications for RL and planning tasks.
Pinterest deploys vision-language models for automated relevance evaluation in search, reducing human annotation cost at scale.
ParEvalLayer detects biased partial evaluations of LLM agents, preventing premature benchmark conclusions from incomplete task runs.
Solution Hacking identifies shortcuts where LLMs achieve correct answers without valid reasoning on frontier science benchmarks.
Agentic Commerce World environment enables multi-agent evaluation with independent buyer/merchant objectives via Vibe Commerce Protocol.
POMDP framework using active inference separates opponent intent from execution noise in noisy multi-agent social dilemmas.
xPress improves speculative decoding by refining block-diffusion drafters through parallel refinement of conditionally dependent tokens.
David Crawshaw proposes using LLM-based automation for nightly software rebasing and testing via cron jobs.
Tutorial bridging control theory and RL via adaptive control and actor-critic methods on classical locomotion benchmarks.
Wasserstein distance bounds for unadjusted Langevin algorithm mixing time improved by √d/ε factor over prior work.
Digital Twin-Enhanced Multiscale Planning automates incident response via decision-theoretic agents, bridging abstract models to operational systems.
Running a dedicated Kubernetes cluster per team often results in more isolation than an organization requires. While one cluster can be successfully shared... Running a dedicated Kubernetes cluster per team often results in more isolation than an organization requires. While one cluster can be successfully shared across many teams, the coordination costs increase as the number of teams grows. Challenges include conflicting CRD versions, overlapping RBAC, and no clean way to carve GPU capacity into team-level budgets. At a certain scale… Source
Storage is an active part of every agentic AI workflow. As agents retrieve enterprise knowledge, access persistent memory, reuse key-value (KV) cache data,... Storage is an active part of every agentic AI workflow. As agents retrieve enterprise knowledge, access persistent memory, reuse key-value (KV) cache data, execute tools, and generate new results, storage systems must continuously supply and preserve the data that moves the agent reasoning loop. Each agent step can trigger multiple storage operations, and those operations can repeat across… Source
Systematic comparison of training-free vs training-based intent classification methods for LLM prompt routing and domain specialization.
Empirical analysis of why frontier LLMs fail at tabular prediction without fine-tuning, foundational insight for tabular models.
Mixed-methods study of caregiver perspectives on four categories of care robots across US, Mexico, and Chile (n=298).
MonitrLLM: open-source evaluation infrastructure linking LLM conversation transcripts to user-defined task intent and outcomes.
Deep learning approach to estimate ground reaction forces from minimal IMU data for Parkinson's disease gait analysis.
Antares: compact LLMs (350M–3B) for agentic vulnerability localization via SFT and RL on cybersecurity reasoning over code.
Physics-calibrated mixture-of-experts framework learns from fragmented experimental data on plastic thermochemical upcycling.
Domain-level news reliability detection via network structure from Telegram URL-sharing patterns, accounting for generative AI mimicry.
Benchmark of 11 audio-language models and classifiers on closed-set sound source identification (2,242 clips, 23 classes).
GROVE: training-free wearable video-memory framework supporting both question-answering and proactive recall from streaming visual input.
Simon Willison argues LLMs make open-source dev tools more practical by lowering code-reading barriers through AI-assisted comprehension.
Google and Kaggle launched a free 353,000-person course on AI agents using Gemma, focused on building and deploying agent systems.
Import AI newsletter curates self-sustaining AI viruses concept, AI progress pacing debate, and creativity attribution confusion.