The Archive

Re³Cap uses multimodal retrieval and RL to refine image captioning in large vision-language models.

Stratechery weekly digest covering Apple EU compliance, Truth Social, and sports entertainment—no AI content.

llm-openrouter plugin 0.7 adds server-side tools (Shell, WebFetch, WebSearch) and OpenRouter Responses API support.

AUSO optimizes skill lifecycle in agent learning from internalization through action-level utilization.

CLEAR: Continuous latent adapter routing preserves LLM utility while reducing harmful outputs via conditional safety tuning.

ConceptTS: LLM-guided concept bottlenecks provide interpretable multivariate time-series forecasting with human-readable explanations.

Training-free framework reduces CoT inference overhead via reusable reasoning memories, formalizing context-generation trade-off.

Use AdaptGrow, a GPU-accelerated matrix factorization algorithm, to turn rolling correlation and tail-dependence matrices into hard clusters, soft factor... Use AdaptGrow, a GPU-accelerated matrix factorization algorithm, to turn rolling correlation and tail-dependence matrices into hard clusters, soft factor loadings, and structural-break signals at single-GPU and multi-node scale Quant strategies routinely group instruments for portfolio construction, risk aggregation, statistical arbitrage, and trade surveillance. Incorrect groupings can make… Source

Statistical analysis of clustered calibration data breaks independence assumptions in threshold-based ML safety filters and conformal predictors.

Thomas Ptacek argues AI-powered coding agents make building native GUIs cost-effective enough to replace terminal UIs for personal tools.

Study on generalization of UAV-based weed detection models across crops and fields, identifying distribution shift failure modes.

Entity-structure-indexed RAG framework improves long-document QA by indexing entity relationships and supporting multi-hop reasoning.

Rank-calibrated multi-stream anomaly detector for operational telemetry using copula dependence and AR(1) innovations.

Dis2Pat dataset and benchmark for LLM-based patent drafting from informal inventor disclosures, closing real-workflow gap.

Knowledge-graph-based denoising method for sequential recommendation removes unreliable user interactions via explicit item relations.

Empirical study across 7 LLMs shows affective context significantly amplifies sycophancy in subjective evaluations, relevant to alignment.

RARE framework enables representation engineering steering for MoE LLMs by decoupling routing from behavior-directed latent modifications.

Master-level lecture notes on numerical linear algebra foundations for PDEs, ML, and data assimilation.

GPU-optimized genetic algorithm for TSP with irregular memory access patterns; domain-specific optimization unrelated to frontier AI.

Agent memory poisoning via false statements reduces accuracy 0.85→0.30; content screening fails to detect 360 poisoned memories.

Ontology framework for tracking and managing AI models/datasets across organizations; metadata and governance infrastructure.

Zeroth-order optimization for spiking neural networks on in-memory computing accelerators; hardware-specific fine-tuning technique.

LLM augmentation with semi-structured data for predictive political QA; actor stance and vote prediction from external resources.

P3Bench: benchmark for personalized privacy control in LLMs via attention head intervention; user-specific disclosure preferences.

Cross-agent specification portability: Claude, Gemini, Copilot on Oracle-to-PostgreSQL migration; 380/1006 successful executions.

Curriculum-aware time-series imputation for clinical physiological data; addresses realistic gap patterns in medical records.

PUN protocol: plausible unknown names for LLM evaluation; controls for memorization vs. factuality in person-name benchmarks.

Q-Planning: off-policy Q-function enables self-improving robot policies beyond behavior cloning; scales to multi-billion-parameter visuomotor models.

SENTRY applies XGBoost and RAG to replace questionnaires in IT change risk assessment for financial institutions.

Tydra hybrid Transformer-SSM architecture reduces TabPFN inference time 30% on tabular data while maintaining accuracy.