pycc.id brings hypothesis-driven equation discovery with identifiability checks
a new python package helps scientists find governing equations from data by using structural skeletons and checking if parameters can be uniquely determined.
aitag machine learning
summaries filed under machine learning
calibrating language model confidence with three methods
a look at temperature scaling, platt scaling, and isotonic regression for fixing overconfident llms.
aideterministic envelopes fix bias in tamed sgmcmc
new framework decouples taming denominator from stochastic gradient noise to eliminate stationary bias in langevin algorithms.
ainew clustering index uses description length for validation
a new clustering validation index called central description length uses probabilistic bounds on description length to evaluate clusters without labels, handling non-convex and irregular shapes better than traditional methods.
aistaged factorial screening for budget-constrained micro-pretraining
a study tests whether staged fractional-factorial experiments can identify stable early effects in micro-pretraining under tight compute budgets.
aillm benchmarks miss huge capability gaps
a stereological theory shows that standard llm benchmarks have a large structural blind spot, making rankings unreliable.
aimaster time series analysis with python in 7 steps
a practical guide to learning time series analysis with python, covering data structures, cleaning, exploration, classical and ml models, and deployment.
ainemotron 3.5 unifies multimodal safety with custom policies
nvidia releases nemotron 3.5 content safety, a 4b model that combines multimodal input, multilingual support, custom policy enforcement, and auditable reasoning in one inference call.
aieva-bench grows to three enterprise voice agent domains
eva-bench data 2.0 adds itsm and healthcare hrsd domains, totaling 213 scenarios across 121 tools to test voice agents on realistic, domain-specific tasks.
aiagentic ai reshapes data science workflows
ai agents automate routine data tasks, shifting data scientists toward system design and evaluation.
aihf cli rebuilt for coding agents
hugging face redesigned its hf command-line tool to serve both humans and ai coding agents, cutting token usage by up to 6x on complex tasks.
aifine-tune nemotron 3.5 asr for your language or accent
a guide to fine-tuning nvidia's multilingual streaming speech recognition model on custom data for better accuracy in under-resourced languages and domains.
aifinite-iteration theory for tensor power iteration
new analysis of alternating power iteration for spiked tensor models gives finite-iteration error bounds and explains warm-start behavior without relying on specific initializations.
aiieee p3109 arithmetic formats for machine learning
the ieee p3109 draft standard defines parameterized binary floating-point formats and operations to support efficient, consistent machine learning computations.
aijetbrains releases mellum2, a 12b mixture-of-experts model
jetbrains launches mellum2, an open 12b-parameter mixture-of-experts model optimized for low-latency text and code tasks, activating only 2.5b parameters per token.
aieeg region contributions to cognitive workload prediction
a large-scale analysis across four eeg datasets examines how different scalp regions contribute to predicting cognitive workload, revealing consistent patterns and practical implications for sensor selection.
aifive papers that explain llms clearly
a guide to five foundational papers covering transformer architecture, few-shot learning, scaling laws, instruction tuning, and retrieval-augmented generation for understanding large language models.
aireachy mini gets remote mcp tools from hugging face spaces
reachy mini robot can now use remote tools like weather and web search hosted on hugging face spaces via mcp, without downloading code locally.
aideepspeed adds muon optimizer support
deepspeed now integrates muon optimizer, reducing memory and improving convergence for large model training.
aidpo cuts text degeneration in ocr models
direct preference optimization reduced text degeneration by an average of 59.4% across five ocr model families by using the model's own failure outputs as rejection pairs.
ai