The Archive

PerturbRx framework learns treatment-conditioned latent transitions from single-cell data for cancer drug-response prediction.

Theoretical proof that exact truthfulness is incompatible with completeness in calibration measures for sequential binary prediction.

Study shows generation, critique, and revision stages in LLM self-refinement have asymmetric computational requirements; smaller models sufficient for some stages.

TurboBias 2.0 framework enables efficient streaming context-biasing for production ASR systems with user-specific phrase lists and low latency.

Analysis of estimation error decomposition in sparse pricing panels shows cross-trajectory variance dominates within-trajectory uncertainty.

Anatomy-Informed Neural Networks embed anatomic constraints via loss penalties and architectural priors to improve plausibility and generalization.

Analysis of frontier LLMs conducting psychotherapy finds models over-use certain moves (reassurance, validation) vs. human clinicians; maps therapeutic behavior with ontology validated by licensed psychologists.

Transformer model for predicting acute COPD exacerbation from home ventilator data with temporal awareness.

Branch-and-bound algorithm for Steiner Traveling Salesman Problem on convex sets with lower-bound relaxations.

Study of LLM-assisted compliance documentation (DPPs, DPIAs) for EU sustainability and privacy regulations.

Analysis of prompt-model interaction fixed-point structure independent of task performance metrics.

LLM CLI tool 0.32.1 fixes dependency breakage from OpenAI library dropping httpx support.

E²-TTT: Closed-form test-time training enabling efficient long-context processing with per-token weight updates.

SPARCL addresses spectral interference in analytic continual learning via spectral partitioning.

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.