policy regret for embedding model routing
a new algorithm tackles dynamic routing of queries to multiple embedding models under adversarial conditions and bandit feedback.
aitag machine learning
summaries filed under machine learning
gpu workflow for hypersonic flow emulators
a fully gpu-based method speeds up building neural emulators for hypersonic flows with physics-aware refinement and uncertainty quantification.
aimobile npu framework speeds up diffusion llm inference
llada.cpp is the first npu-aware framework for accelerating diffusion large language models on smartphones, using multi-block speculative decoding and other techniques.
aiolmo-eval: a workbench for iterative llm evaluation
olmo-eval is an open evaluation workbench for comparing model checkpoints during development with per-question analysis and flexible runtime policies.
ai7 ways to fund your startup idea
seven funding options for startups, from bootstrapping to venture capital, with pros and cons for each.
aipytorch meetup singapore draws apac ai builders
eighty engineers gathered for the first pytorch meetup singapore, covering inference, distributed training, and community governance.
airun claude code with local models
how to connect claude code to ollama, lm studio, or llama.cpp for zero-cost, rate-limit-free coding sessions using local models.
ai3 numpy tricks for faster numerical code
learn vectorization, in-place operations, and memory views to speed up numpy code and reduce memory use.
aiopen source community backs openenv for agentic rl
openenv becomes a community-governed interoperability layer for reinforcement learning environments, backed by major ai organizations.
aiepistemic uncertainty is not always reducible
new research shows that the standard definition of epistemic uncertainty as reducible by more data is inconsistent with its common mutual-information measure, and proposes a three-part taxonomy.
aibuild a minimal feature store from scratch
a hands-on guide to building a feature store with duckdb, parquet, redis, and fastapi, covering offline and online stores, materialization, and retrieval for both predictive ml and llm context.
aipytorch profiling: from linear to fused mlp
a deep dive into pytorch profiling shows how nn.linear fuses bias into gemm kernels and how torch.compile removes cpu overhead in mlps.
aisteering away from sycophancy also cuts factual agreement
activation steering meant to reduce sycophancy in language models also lowers agreement with true statements, showing a structural overlap that current methods cannot separate.
aitopological features as survival data for testing and learning
a new method treats persistence diagrams as survival data, enabling hypothesis testing, effect sizes, and stable feature vectors for machine learning.
aiprohiflo: hierarchical flow matching for protein generation
a new hierarchical flow matching framework generates proteins with functional guidance and fewer sampling steps.
aiboltzmann margin gives knn near-exponential convergence
a new margin condition bridges the gap between polynomial and exponential rates for knn classifiers.
aipython scripts to automate pdf tasks
five python scripts that merge, split, extract, stamp, redact, and inventory pdfs from the command line.
ailocal agentic coding with claude code, ollama, and gemma 4
a guide to building a local agentic programming stack using ollama, gemma 4, and claude code, with setup steps and verification.
aihelion kernels speed up vllm fp8 inference
helion, a pytorch-native kernel dsl, improves vllm inference throughput for qwen3 models with fp8 quantization on nvidia gpus.
aisynib: training objective for multimodal synergy
a new training objective called synergistic information bottleneck targets task-relevant information that only emerges from combining multiple modalities.
ai