The Archive

Controlled study compares LLM (ChatGPT-4o, Gemini) vs. human literature review performance across physics, astrophysics, cosmology.

OmniDelta allocates token budgets by skill across modalities in OmniLLMs, compressing audio-video sequences for inference efficiency.

Physics-informed neural operator for thermal ranking of low-cost wall materials in hot-dry climates using finite difference methods.

MyMentorLLM: multimodal LLM simulation environment for psychotherapy training with voice/text patients, trainees, and expert supervisors.

Contextual Deconvolution method for demand forecasting in retail using kernel-modulated operators to separate promotional shocks from baseline trends.

Controlled benchmark analyzing how LoRA adaptation site affects learning geometry across lexical, factual, causal, and procedural objectives in Transformers.

CoRT: token-level credit weighting for rubric-guided policy optimization in language models, enabling fine-grained attribution across generated spans.

OrchBench: simulation-based benchmark for evaluating multi-agent orchestration plans in isolation without conflating with worker/tool/environmental noise.

Analysis of outcome skew in Stockfish-evaluated equal chess positions vs. human play on Lichess, showing position-specific bias independent of ratings.

Policy analysis: general-purpose AI governance frameworks for public services risk failure due to GPAI properties (generality, accessibility, low cost) undermining safety preconditions.

KQFuzz: LLM-based knowledge-guided fuzzer for quantum libraries using codebase context to improve test generation efficiency and flexibility.

Perplexity has expanded its agentic Personal Computer tool to Windows, allowing computers running the world's most popular OS to be used as a locally run AI system. Like the Mac version that Perplexity launched in April, Personal Computer for Windows operates like a "general-purpose digital worker" that can access local files and apps to perform actions on your behalf, such as creating documents and updating spreadsheets. This launch builds on Personal Computer integrations that Perplexity launched for Microsoft's 365 workspace apps and Teams virtual meeting software in May. Personal Computer...

Survey of instruction-based image editing spanning task taxonomy, training data methods, and architectural evolution from GAN to diffusion/autoregressive models.

OmniPhys benchmark (1,551 samples) diagnoses physical commonsense violations in text-to-image models via knowledge graphs and addresses gradient hallucination in prompt optimization.

F(AI)2R extends AI provenance tracking to executable agent skills via aiprov (PROV-O extension), enabling auditable AI contributions in research artifacts.

Study uses spectral dataset properties (entropy, rank, autocorrelation) as empirical priors to guide 1D-CNN architecture design for NIR chemometrics across 25 regression tasks.

AIriskEval-edu audits pedagogical risks in AI-generated explanations across five dimensions (factual accuracy, depth, bias, relevance, student-appropriateness) with evidence spans.

Construction-Driven Injection embeds linguistically-grounded code-mixing fingerprints in LLMs to create verifiable ownership signals resistant to accidental activation and perplexity filtering.

Human-in-the-loop corpus simplifies scientific paper summaries via GPT-4o-mini with iterative refinement by non-specialist STEM readers for cross-disciplinary accessibility.

Joint text-audio alignment method decodes Chinese speech from EEG into text, addressing high-dimensional output space and low SNR for non-invasive neural interfaces.

Theoretical analysis of positive quadratic networks studies quotient structure effects on training dynamics and implicit bias via Riemannian geometry on PSD manifolds.

Over the last few months, I've spent a lot of time talking to my computer. One underrated feature of the LLM revolution has been a remarkable leap in all kinds of dictation technology - even the fastest, cheapest models are getting very good at understanding and processing speech. I've tested lots of these apps, from WisprFlow to Monologue to Spokenly to Handy to so many others, and have found them all to be useful ways to quickly write emails, Slack messages, and more. They sometimes default to giving everything a too-formal style of formatting and love ending a text message with a period (l...

Philosophical critique of epistemic risks in LLM outputs challenges the 'Epistemia' framework by invoking semiotic and situated-knowledge perspectives.

MemSFT mitigates alignment tax by decoupling domain specialization via plug-and-play parametric memory that imitates retriever behavior, preserving general-task performance.

ReDAM and Unified-weather-edit methods align multi-sensor weather simulations for autonomous vehicle perception in adverse conditions.

Contrastive GNN framework learns disease trajectory embeddings from temporal clinical graphs using structure-aware random walks.

Physics-informed broad learning system (PI-BLS) solves PDEs via backpropagation-free broad RdNNs with embedded differential operators.

Set-theoretic algorithm formalizes al-Sabr wa al-Taqsim method for extracting legal causes in Islamic jurisprudence from truth tables.

BeyondUncertainty uses LLM confidence estimates to route retrieval for knowledge-intensive QA, reducing irrelevant evidence and computation.

Density-matrix framework analyzes electronic structure in lithium-metal electrolytes; ML models proposed to reduce quantum-chemical computation.