LIVE · refreshes every 20 min
updated Oct 18, 09:03 UTC
110010.art(ificial intelligence)
AI products, research, and launches — clustered and ranked, not just re-blogged.
110010.art / archive

Research

Oct 14
4d ago Agentic data engineering for LLMs: system design and a controlled empirical study arXiv cs.CL → story
4d ago AphaVoice: a text-to-speech model for aphasia patient simulation arXiv cs.CL → story
4d ago ASSET: Adaptive speech segmentation via reinforcement learning arXiv cs.CL → story
4d ago Barycentric anchored search improves fine-tuned vision models under distribution shift without additional training or inference cost, via post-hoc weight-space optimization using barycentric candidates arXiv cs.LG → story
4d ago Bias measurement in Chinese language models varies by task and register; irony classification risks skewing results arXiv cs.CL → story
4d ago Calibrated typed-decision models evaluated on Indonesian regional languages using NusaX and NusaTranslation sentiment datasets arXiv cs.CL → story
4d ago Coding LLMs can be harnessed to learn interpretable models from data arXiv cs.LG → story
4d ago CoEvoke: evoking multi-agent collaboration for trajectory collection arXiv cs.LG → story
4d ago DoSA: Dots Sparse Attention uses a seed set to condition sparse attention with a lower-bound threshold for Top-K selection arXiv cs.LG → story
4d ago DShuttleNet: a badminton doubles dataset for evaluating team coordination arXiv cs.LG → story
4d ago EdgeLLM-Nano: auditing polar-guided key-cache compression and consistency-anchored pruning on a 33.6 MB on-device language model arXiv cs.CL → story
4d ago Evaluating LLMs as agentic workflow executors in real-world customer support arXiv cs.CL → story
4d ago Evaluating semantic relation knowledge through bidirectional relation prediction from gloss pairs arXiv cs.CL → story
4d ago Fin_Agent at FinEval 2026: task-aware methods for multilingual financial NLP arXiv cs.CL → story
4d ago GameSmith scales zero-sum self-play with synthesised games arXiv cs.LG → story
Oct 13
4d ago Artificial neural networks build their own learning machinery, researchers show MIT News (AI) → story
4d ago MIT Lincoln Laboratory hosts National Security Commission on Emerging Biotechnology discussions with defense technologists, academics, and business leaders across Massachusetts MIT News (AI) → story
5d ago Q&A: Building accountability behind our words—and AI’s—in civic conversations MIT News (AI) → story
Oct 12
5d ago Simulating student learning for better AI tutoring Microsoft Research → story
6d ago Representation alignment from a few paired data via distilled optimal transport arXiv cs.AI → story
6d ago Reward hacking can propagate as a transmissible strategy in multi-agent coding systems arXiv cs.AI → story
6d ago Sample-Adaptive zeroth-order post-training; SAZO learns sample importance online to allocate queries adaptively for faster fine-tuning of large language models. arXiv cs.LG → story
6d ago SeedS: Preview-guided evidence admission for search agents arXiv cs.CL → story
6d ago Self-preservation in language models; a model-generated replay approach aims to help choose preservation strategies arXiv cs.CL → story
6d ago Speculative decoding with optimized layer selection: analyzing information and geometry of LLM hidden states across layers to improve decoding efficiency arXiv cs.CL → story
6d ago SpireBench evaluates long-horizon strategic play of agentic models with Slay the Spire arXiv cs.AI → story
6d ago STAPLE: static sparse upcycling of pretrained checkpoints via embedding modules arXiv cs.LG → story
6d ago Structure-disjoint splits drift with the libraries they are built on, study shows for molecular machine learning and MCES clustering in mass-spectrometry structure prediction arXiv cs.LG → story
6d ago SWE-Duel: a self-scaling arena for coding agents arXiv cs.CL → story
6d ago SynAct: synergistic active feedback learning for LLM agents arXiv cs.LG → story
6d ago Teaching neural decoders with language as supervision for brain-computer interfaces arXiv cs.AI → story
6d ago Temporal evidence forests for long-horizon multi-party conversational memory arXiv cs.CL → story
6d ago Time Delay System for Sequence Modeling proposes explicit content-aware temporal recall to address memory limitations in LSTMs, Transformers, and state-space models. arXiv cs.CL → story
6d ago Towards defining, measuring, and leveraging creativity in AI applications arXiv cs.AI → story
6d ago Transformer-based masked diffusion models provably learn distributions with latent structure arXiv cs.LG → story
6d ago U4RASD submits encoder and LLM approaches for Arabic relation extraction at KnowledgeGraphEval-2026 Subtask 2 arXiv cs.CL → story
6d ago Unreliable narrator framing as a cost-effective mechanism for satire explanation of Australian and American satirical news arXiv cs.CL → story
6d ago Unsupervised multimodal reward modeling uses a linear head on a frozen Qwen3-VL backbone to score captions without human preference labels; layer choice determines the reward. arXiv cs.CL → story
6d ago VEPA: Verified evolving formal policy for lifelong LLM agent guardrails arXiv cs.AI → story
6d ago When charts deceive web agents: a paired benchmark for misleading visualization-grounded tasks arXiv cs.CL → story

Older items: monthly archive →