LIVE PULSE
3.9 Anthropic CEO Amodei calls for slower AI development and shared safety rules — 11 src2.1 Agility Robotics unveils Digit 5 humanoid for warehouses and factories — 2 src2.0 Apple ships rebuilt Siri with Google Gemini, but not in the EU — 2 src1.7 Siri AI in macOS 27 Golden Gate: FAQ, Germany availability, privacy questions — 2 src1.4 Sam Altman says OpenAI will not go public in 2026, citing AI safety concerns — 5 src1.1 OpenAI contractors review real ChatGPT conversations to rate responses, report says — 2 src1.1 Anthropic data retention policy prompts firms to limit Claude use for sensitive work — 1 src1.1 Study examines issue bias in LLMs used as writing assistants before Swedish 2026 election — 1 src1.1 Study Audits Misalignment in Multi-Modal World Models — 1 src1.1 Retrieval-Grounded Reasoning Approach Proposed for Universal Multimodal Embeddings — 1 src3.9 Anthropic CEO Amodei calls for slower AI development and shared safety rules — 11 src2.1 Agility Robotics unveils Digit 5 humanoid for warehouses and factories — 2 src2.0 Apple ships rebuilt Siri with Google Gemini, but not in the EU — 2 src1.7 Siri AI in macOS 27 Golden Gate: FAQ, Germany availability, privacy questions — 2 src1.4 Sam Altman says OpenAI will not go public in 2026, citing AI safety concerns — 5 src1.1 OpenAI contractors review real ChatGPT conversations to rate responses, report says — 2 src1.1 Anthropic data retention policy prompts firms to limit Claude use for sensitive work — 1 src1.1 Study examines issue bias in LLMs used as writing assistants before Swedish 2026 election — 1 src1.1 Study Audits Misalignment in Multi-Modal World Models — 1 src1.1 Retrieval-Grounded Reasoning Approach Proposed for Universal Multimodal Embeddings — 1 src
HEATPULSEAI MAGAZINES
FLIP · FOLLOW · SAVE
Log inSign up

time-series-foundation-models

topic4 events
papersTODAY 04:00 UTC

FlowTSFM: Turning Encoder Depth into Quantile Transport

A new arXiv preprint introduces FlowTSFM, an approach for encoder-based time series foundation models that assigns a predictive role to intermediate Transformer layers instead of supervising only the final forecast. The method recasts encoder depth as a form of quantile transport, according to the abstract. The announcement provides only the opening portion of the paper's abstract, so full details of the architecture and evaluation are not yet available in this report.

time-series/foundation-models/quantile/research
papersTODAY 04:00 UTC

Tabby: Open Pretraining Recipe Released for Time Series Foundation Models

Researchers introduce Tabby, a long-context probabilistic foundation model designed for time series data, built on an encoder-only patch Transformer architecture. The release includes a fully open account of the pretraining process, covering the decisions and components behind the model's construction. The work aims to make time series foundation model development more reproducible and accessible.

time-series/foundation-models/open-source/pretraining
papersSEP 10 04:00 UTC

Paper examines distilling synthetic data for time series foundation models

A new arXiv preprint looks at how time series foundation models are pretrained on artificially generated trajectories where the underlying data-generating process is known. The work focuses on distillation methods rather than the conventional loss-based pretraining objectives that compare model outputs against targets. It aims to improve how these models learn from synthetic time series data.

time-series/foundation-models/synthetic-data/distillation
papersSEP 10 04:00 UTC

Time-Series Foundation Model Benchmarks Still Reflect Pretraining Familiarity on Later Hold-Outs

A new study questions whether time-series foundation models can be fairly evaluated using test data collected after their pretraining cutoff. It finds that even a temporally later, contamination-free hold-out does not fully isolate genuine generalization, as familiarity with the underlying data distribution absorbed during pretraining persists. The result suggests the field needs evaluation practices that go beyond simply withholding recent data.

benchmarks/evaluation/time-series/foundation-models