LIVE · refreshes every 20 min
updated Nov 14, 08:03 UTC
110010.art(ificial intelligence)
AI products, research, and launches — clustered and ranked, not just re-blogged.
110010.art / archive

Research

Oct 24
21d ago Aggregate scores can hide substantial changes in individual verdicts when LLM judges' instructions vary, study finds. arXiv cs.CL → story
21d ago AQL-Lite: enabling efficient knowledge acquisition for Arabic LLMs via data-centric continual pretraining arXiv cs.CL → story
21d ago Automating data pipelines and reproducing baselines in low-resource settings arXiv cs.CL → story
21d ago baseVultra: compact nonlinear recurrence reallocates capacity to a candidate-generation matrix while using diagonal matrices for gates arXiv cs.CL → story
21d ago CiteAnchor: Source-aware grounding for hallucinated citation detection and resolution arXiv cs.CL → story
21d ago Clinician-led guardrails for mental-health chatbots define, finalize, and adjudicate a four-check safety rule base for LLM deployment. arXiv cs.CL → story
Oct 23
21d ago MIT lecture: Martha Minow discusses sustaining democracy through use and critique of AI MIT News (AI) → story
21d ago MIT panel reinforces the value of human understanding at SHASS 75th Anniversary Symposium MIT News (AI) → story
21d ago Bringing foundational models to the front lines of TB screening Google Research → story
22d ago From single-actor environments to multi-actor event worlds: evaluating whether LLMs can predict future observations from event logs and proposed actions arXiv cs.AI → story
22d ago GANet: a lightweight group attention network for plant disease identification on embedded systems arXiv cs.LG → story
22d ago GAV: a scientific experimentation environment that verifiably generates PDE problems for agents, enabling efficient evaluation of PDE-programs arXiv cs.LG → story
22d ago Generalizing Metropolis-Hastings for DAG sampling arXiv cs.LG → story
22d ago Governed self-evolution for autonomous investing: a multi-agent LLM system with an invariant core arXiv cs.AI → story
22d ago How AI came to model the “messy” human mind: MIT researcher discusses incorporating randomness and irrationality into early AI models of human creativity MIT News (AI) → story
22d ago Large language models fail to consistently incorporate evolving medical knowledge, ChronoEvo shows 709 recommendation-level revisions reveal gaps in updating clinical guidance arXiv cs.AI → story
22d ago Lehmer's problem: breaking the high-degree barrier via a human-AI discovery loop arXiv cs.AI → story
22d ago MCP vs CLI for AI agents: a comparative analysis of tool integration strategies for autonomous systems arXiv cs.AI → story
22d ago Memory-augmented online test-time adaptation for EEG motor imagery via perturbation consistency and confidence calibration arXiv cs.LG → story
22d ago Model organisms of collusion: corrective transfer in untrusted monitors arXiv cs.AI → story
22d ago Muon update polarizes matrix parameters via Orthogonalized Muon update; study analyzes PolarGD on matrix quadratics and compares line-search directions to mitigate learning-rate effects arXiv cs.LG → story
22d ago Neural Networks with Differentiable Belief-Function Layers arXiv cs.AI → story
22d ago Path-based criterion shows stable and preferred semantics agree in abstract argumentation frameworks arXiv cs.AI → story
22d ago Physical-Engineering’s last exam scores above 90% on knowledge benchmarks and assesses real-world professional work by frontier language models across multi-format project data arXiv cs.AI → story
22d ago Prediction is not calibration: item parameter recovery and representation coupling in knowledge tracing arXiv cs.LG → story
22d ago Probing and steering for safety-relevant behaviours in large language models arXiv cs.LG → story
22d ago Prompt style affects AI accuracy and speed in competitive programming benchmarks arXiv cs.LG → story
22d ago RoleFlow: a self-evolving multi-role agentic system that refines collaborative structure via structural adaptation arXiv cs.AI → story
22d ago Route-and-Generate: KL-regularized router improvement for reasoning routing in LLMs arXiv cs.AI → story
22d ago Secure agentic AI and multimodal intelligence in 6G communication systems arXiv cs.AI → story
22d ago Short-to-Long: Detached Features for Long-Horizon Value Learning arXiv cs.LG → story
22d ago Soft ontology priors over latent concept posteriors for weakly supervised neuro-symbolic learning arXiv cs.AI → story
22d ago SpecMAGIC: specification-guided multi-task generalization in multi-agent reinforcement learning arXiv cs.AI → story
22d ago Spectral uncertainty decomposition for sparse Bayesian learning arXiv cs.LG → story
22d ago Spike-Aware gradient-based mixed-precision quantization of spiking neural networks for vision applications arXiv cs.LG → story
22d ago Stability analysis of signed graphs under edge perturbations arXiv cs.LG → story
22d ago SWE-Verifier: selective verification for cost-efficient coding agents arXiv cs.LG → story
22d ago The cost of saying hello: an empirical study of handshake overhead in AI agent communication protocols arXiv cs.AI → story
22d ago Three-Pillar governance framework for safe and trustworthy AI agents arXiv cs.AI → story
22d ago Why Bother Me Again? Benchmarking personal agent memory for interaction preferences arXiv cs.AI → story

Older items: monthly archive →