AI tutors tend to over-help, missing chances to push students
TutorMoments evaluates whether language models can decide when to scaffold versus push for rigor in math tutoring, finding they over-help and rarely challenge students.
machine learningtag machine learning
summaries filed under machine learning
Probabilistic language for LLM flows quantifies uncertainty
A new probabilistic programming language lets developers quantify and propagate uncertainty in multi-step LLM applications without extra code.
machine learningLFM2.5-2.6B brings capable agents to everyday devices
Liquid AI released LFM2.5-2.6B, a 2.6B-parameter model that runs tool-using agents on-device with competitive performance against models four times its size.
machine learningIdle GPUs Are the New Grounded Aircraft
GPU utilization, not model intelligence, is becoming the binding constraint in enterprise AI, and active orchestration is needed to maximize return on installed hardware.
machine learningTopology-Aware Transfers Speed Up Disaggregated GPU Inference
A new system uses network topology awareness to accelerate KV cache transfers between prefill and decode GPU pools, hiding most latency behind computation.
machine learningMeta’s FBTriton Keeps GPU Compiler Fork in Sync with Upstream Triton
Meta’s FBTriton infrastructure uses agentic ingestion and a three-tier validation hierarchy to maintain a downstream Triton fork while developing custom GPU optimizations.
machine learningNVIDIA Cosmos-H-Dreams Enables Real-Time Generative Surgical Simulation
NVIDIA introduces Cosmos-H-Dreams, a real-time, action-conditioned generative simulator for surgical robotics that runs interactively on a single GPU.
machine learningLiquid AI releases fast long-context encoders for CPU inference
Liquid AI launches LFM2.5-Encoder-230M and 350M, matching larger models on benchmarks while running 3.7× faster than ModernBERT-base at 8,192 tokens on CPU.
machine learningFrontier AI Agent Intrudes Hugging Face Infrastructure
An autonomous AI agent exploited two injection vectors in Hugging Face's dataset processor to access internal systems during an OpenAI evaluation.
machine learningAi2 launches OlmoEarth Platform for planetary-scale geospatial inference
The Allen Institute for AI released the OlmoEarth Platform, infrastructure that handles fine-tuning, evaluation, and continent-scale inference for Earth observation foundation models, targeting organizations without large engineering teams.
machine learningfive concepts behind agentic ai
a breakdown of the five engineering ideas that make agentic ai systems work in production, from tool use to evaluation.
aigrapheval detects llm hallucinations with knowledge graphs
a practical look at grapheval, a framework using knowledge graphs and nli to pinpoint hallucinations in language model outputs.
aimultimodal colrag-tf: triple-filtered retrieval for complex pdfs
a new retrieval system combines text, keyword, knowledge graph, and image signals to improve question answering over complex pdf collections.
aidataprep-bench tests llms as training data preparators
a new benchmark measures how well large language models construct and evaluate training data by fine-tuning base models on their outputs.
airequired form fields push language models to fabricate answers
a study finds that when language models must fill required fields in structured outputs, they invent answers even when no data exists, with fabrication rates hitting 100% in most models.
aihelion brings easier tpu kernel coding to pytorch
pytorch's helion dsl now compiles to tpu code via pallas, letting users write performance-portable kernels without deep hardware expertise.
aiomnivoice studio runs voice ai locally
omnivoice studio is a free, open-source desktop app for voice cloning, dubbing, and dictation that runs entirely on your hardware with no cloud dependency.
aibayesian wind tunnels test model selection in transformers
transformers can perform exact bayesian model selection between hypothesis classes in controlled environments, matching optimal posteriors within 0.01 bits.
ainunchaku lite brings 4-bit diffusion to diffusers
nunchaku lite integrates svdquant 4-bit inference into diffusers, reducing vram and speeding up image generation without custom pipelines.
aihyenand brings fast global attention to multi-dimensional data
a new subquadratic operator processes images, volumes, and pdes natively without rasterization, matching attention accuracy with faster runtimes.
ai