The Archive

Meta releases Muse Spark 1.1 with API access and improved agentic tool calling and computer use capabilities.

Marketplace simulation with DeepSeek-V3 agents tests formal mechanisms for maintaining trade stability against adversarial defection.

gspDAG-FL proposes decentralized federated learning via gossip consensus without global coordination, replacing central servers.

Multi-modal inverse RL framework for training robust reward functions across diverse environments and feedback modalities.

UltraX uses adaptive programmatic editing to refine pre-training data quality at scale, addressing efficiency and reliability limits of rule/LLM-based approaches as scaling laws diminish.

BiSCo-LLM introduces binary spherical coding for extreme low-bit LLM compression without explicit codebooks, enabling sub-2-bit weight quantization for memory-constrained deployment.

DominoTree combines tree-structured drafting with Domino's GRU-based causal correction for faster LLM speculative decoding via path-dependent token distributions.

Method steers neural network training via interpretable constraints based on partial dependence to enforce explanations faithful to prior domain knowledge.

llm-meta-ai 0.1 released, enabling CLI access to Meta's muse-spark-1.1 model via Simon Willison's llm tool.

llm 0.31.1 patches tool call JSON error in OpenAI Chat Completion endpoints with empty arguments.

Ben Bernanke joins Anthropic's Long-Term Benefit Trust, signaling governance structure for AI safety oversight.

Anthropic launches public Q&A initiative to address community concerns about AI safety and development practices.

Analysis of 2,053 real patient-chatbot conversations reveals wide variation in communication patterns; proposes patient simulator modeling clinical content, emotion, strategy, and style separately.

S²AE (Structured Sparse AutoEncoder) enforces semantic and spatial consistency in sparse autoencoders for vision-language models to learn modality-consistent mechanistic interpretability concepts.

HCC-STAR, a clinically-aligned LLM, reads EMR narratives to output risk-based staging, ranked treatments with rationales, and survival estimates for hepatocellular carcinoma.

MAESTRO prunes Mixture-of-Experts models using Markov-chain approximation of routing transitions, addressing deployment bottlenecks while maintaining inference efficiency.

Federated deep learning framework for cardiovascular disease risk prediction across institutions without sharing patient data, addressing heterogeneous dataset sizes and population characteristics.

Framework for sequential decision-aware experimental design under adversarial uncertainty, handling hidden/weakly-modeled effects that can alter decision optimality.

Spectral analysis of Extreme Learning Machines' numerical stability via pseudoinverse computation and singular value conditioning.

ImputeViz dashboard for interactive missing data diagnosis and imputation method comparison across MICE, Random Forest, XGBoost, kNN.

TreeSHAP-weighted multimodal fusion for emotion/sentiment recognition balances early/late fusion tradeoffs via sample-level expert weighting.

SMetric proposes session-centric LLM scheduling for agentic workloads with 80%+ KV-cache reuse, shifting optimization from latency to tokens-per-second.

Contravariance theory shows minimal DNN solutions to hard tasks exhibit strong alignment of privileged axes via affine mappings.

Claude’s new Reflect dashboard doesn’t just visualize how you use AI. It also subtly reinforces how much of your daily work now depends on Anthropic’s chatbot.

Three big AI IPOs are set to generate more value than all the U.S. VC backed exits since 2000.

CAAD framework detects multivariate time-series anomalies by monitoring Granger causality consistency in industrial systems.

CommuniWave ML model quantifies informal resident behavior in urban communities via behavior capture networks for city planning.

Study shows state-of-the-art end-to-end audio models have structural bottlenecks preventing direct access to time-frequency-localized interpretable features.

VocaDet sample-driven open-vocabulary detection/segmentation via visual tokenization and vector database retrieval scales to large object repositories.

Model merging approach for conversational information retrieval preserves ad-hoc retrieval performance while handling topic shifts and coreference.