LIVE · refreshes every 20 min
updated Nov 14, 07:23 UTC
110010.art(ificial intelligence)
AI products, research, and launches — clustered and ranked, not just re-blogged.
110010.art / archive

Research

Oct 19
26d ago Alkhder at AlexandriaX-2026 demonstrates context-aware English-to-dialectal Arabic dialogue translation using QLoRA-fine-tuned NileChat-3B arXiv cs.CL → story
26d ago Alkhder presents constrained selection and rotation-averaged logit scoring for multimodal hallucination detection at ImageEval 2026 Subtask 1b arXiv cs.CL → story
26d ago AuditKIT introduces a unified evaluation spine for benchmarking, judging, and comparing large language models and agentic systems arXiv cs.CL → story
26d ago Binding-specific relearning savings for test-time continual learning arXiv cs.LG → story
26d ago BOLT: bound-guided learning for transport-coupled scheduling uses relaxations to bound makespan in flexible job-shop with time lags and fleet constraints arXiv cs.LG → story
26d ago Broad and efficient PII detection with unified labels arXiv cs.CL → story
26d ago CF-NODE: Counterfactual Spatial Node Intervention for test-time adaptation under domain shift, evaluated across five diabetic retinopathy datasets arXiv cs.LG → story
26d ago CGDT-CESN: correlation-guided and dynamics-trained clustered echo state network for multivariate time-series prediction arXiv cs.LG → story
26d ago Coverage cliffs in off-policy quantile certification arXiv cs.LG → story
26d ago Cultural (in)competence: investigating culture-specific stereotype detection capabilities of LLMs arXiv cs.CL → story
26d ago Deterministic bounds on accuracy and stability of metric-space regression and classification arXiv cs.LG → story
26d ago Diagnosing GNN failure modes with layer-wise probe entropy arXiv cs.LG → story
26d ago Don't Retrain, Remix: Adaptation of Web Agents using Mixture Hypernetworks arXiv cs.LG → story
26d ago Embeddings Are Overpriced? A Frozen 16 MB Vocabulary for Small and Ternary Language Models arXiv cs.CL → story
26d ago Evidence-gated bilingual retrieval-augmented generation for consumer banking search arXiv cs.CL → story
26d ago Federated unlearning in vehicular networks: removing faulty contributions after aggregation spreads symptoms across the fleet arXiv cs.LG → story
26d ago Flat loss, evolving features: grokking in modular addition arXiv cs.LG → story
26d ago From Parallels to divergence: language models' learning of action nominal constructions arXiv cs.CL → story
26d ago Generative adversarial networks with Monte Carlo dropout uncertainty quantification for structural health monitoring using fibre Bragg grating data in Hawk T1A aircraft arXiv cs.LG → story
26d ago Generative Value Classifier arXiv cs.LG → story
26d ago HeRE: a novel benchmark for Hebrew relation extraction via LLM-guided denoising of knowledge graph alignments arXiv cs.CL → story
26d ago Inductive learning of concept embeddings from cross-linguistic colexification patterns with textual attributes arXiv cs.CL → story
26d ago Lean4AgenticRL advances agentic RL with verifiable multi-level process rewards arXiv cs.LG → story
26d ago Learning smooth dynamics via Kinematic Interpolants arXiv cs.LG → story
26d ago Learning user representations to improve simulation fidelity arXiv cs.CL → story
26d ago Literal lock-in: how test language shifts literal attraction in typed decision models on Bengali idioms arXiv cs.CL → story
26d ago LLMs can propose and run ML experiments but struggle to gauge the value within training time constraints. arXiv cs.LG → story
26d ago Measuring mechanistic uncertainty in large language models via causal robustness arXiv cs.CL → story
26d ago Mitigating demographic disparities in explanation-human alignment via rationale regularization arXiv cs.CL → story
26d ago Model Knows Better: defending medical multi-agent systems against prompt injection arXiv cs.CL → story
26d ago Noise-robust forced alignment for spontaneous speech using upsampled WavLM features and explicit non-lexical vocal event modeling arXiv cs.LG → story
26d ago On the SPOT: enhancing speculative decoding for diffusion language models via commit-order prediction arXiv cs.LG → story
26d ago Pearl-Chat: engineering a native Luganda language model from first principles in JAX and Flax NNX arXiv cs.CL → story
26d ago Plausible explanations can mislead multimodal judges in a VQA-style benchmark, study finds arXiv cs.CL → story
26d ago Predicting privileged information effectiveness for on-policy self-distillation arXiv cs.LG → story
26d ago Prefill disruptions in MoE models: using fewer routed experts increases short-answer F1 loss; a small set of prompt tokens carries most of the damage. arXiv cs.CL → story
26d ago Progressive misalignment can emerge from benign recursive self-distillation arXiv cs.LG → story
26d ago Rank measures of fine-tuning updates are only marginally above noise when compared with random matrices and baseline references, the study finds. arXiv cs.LG → story
26d ago RealCLI: a paired benchmark for unified evaluation of task execution and human–agent collaboration on realistic CLI tasks arXiv cs.CL → story
Oct 18
27d ago MIT researchers create AI model that identifies optimal crystalline materials for various applications MIT News (AI) → story

Older items: monthly archive →