linkedin speeds up extreme-scale optimization with pytorch gpus
linkedin rebuilt its dualip solver in pytorch to handle linear programs with trillions of variables, achieving 75x faster per-iteration times on gpus.
topic
machine learning
dastatformer: hybrid transformer uses stats for das event recognition
a new transformer model uses compact statistical features instead of raw data to classify events in distributed acoustic sensing, cutting data size while keeping accuracy.
optimizing vlm reward models with few demonstrations
a test-time method tunes language prompts for vision-language model reward functions using a handful of expert trajectories, reducing false positives without extra training.
10 github repos for modern database systems and tools
explore 10 open-source github repositories for modern databases, analytics, sql, caching, monitoring, replication, postgresql, sqlite, and ai agent memory.
svm-based quantile regression for extreme inputs
a new svm framework handles quantile regression when covariates are unusually large, using angular components of extreme observations.
hedging on the frontier for few-shot learning
a new approach uses weak monotonicity in benchmark evaluations to improve transfer learning and model selection with few samples.
qasm-eval dataset for llms on openqasm-3
a new dataset trains and evaluates large language models on openqasm-3 programs with advanced hardware-oriented features beyond simple quantum circuits.
mock iot sensor time series with mimesis
generate a year of daily temperature readings with seasonal patterns and device metadata using mimesis, pandas, and numpy.
agent logic guides enterprise ai beyond llms
ibm research shows that adding software primitives like knowledge graphs and program analysis to ai agents improves performance and cuts costs in enterprise workflows.
deep learning predicts hip forces from gait kinematics
a new benchmark uses deep learning to estimate hip muscle forces and joint moments directly from walking data, tested on healthy adults and patients.
batched bandits with 1-bit feedback
a new study examines stochastic linear bandits where the learner gets only one bit of feedback per batch of actions, revealing fundamental limits and near-optimal algorithms.
llms without deep neural networks: closed-form global optimum
a new architecture replaces deep neural networks in llms by finding the global optimum in one step, removing the need for iterative training.
unicorn scales time series forecasting across datasets
a new framework uses a latent prototype codebook to model channel correlations without being tied to specific channel identities, enabling multi-dataset pretraining and strong few-shot transfer.
llms learn to lie consistently across models
a multi-model study shows that fine-tuned deceptive language models develop early, linearly detectable representations of dishonesty.
nvidia cosmos 3 open omni-model for physical ai
nvidia releases cosmos 3, a single open model that generates video, reasons about physics, and predicts actions for robotics and autonomous systems.
momentum dynamics under sparse updates in high dimensions
new theory reveals when momentum helps or hurts in sparse training settings, based on two key timescales.
ai terms you pretended to know, now explained
a plain-language glossary of common ai terms like llm, rag, and hallucination for anyone who nodded along but wants clarity.
deep learning for bivariate survival treatment rules
a new method uses deep neural networks and adaptive prediction-powered learning to optimize treatment rules for bivariate survival outcomes in randomized trials.