tight minimax bounds for fair bandits
new research provides tight minimax regret bounds for fair multi-armed bandits when fairness is measured by negative p-means, resolving an open problem.
aitag research
summaries filed under research
record-level data provenance for ai training datasets
originblame tracks author identity at record and token level, enabling precise forget sets for machine unlearning and reducing over-deletion.
aioptimal market making in perpetual futures
a theoretical framework for adaptive market making in perpetual futures markets with zero maker fees, deriving optimal bid-ask spreads and hedging strategies.
aiai assistant for india's tinkering labs
google deepmind launches atl saathi, a gemini-powered web app that gives educators in india's atal tinkering labs a 24/7 planning and training assistant.
aiwhy diffusion models create new data
a study shows that diffusion models generate novel outputs because neural networks learn a smoothed score function, causing interpolation between training points.
aivoice ai still struggles in real conversations
a new benchmark with over 1 million human ratings shows voice models often fail at listening, emotion, and real-world noise despite high scores on traditional tests.
aiphase-controlled delta memory with chunk-wy kernels
a new attention method uses fourier phase control and chunk-wise factorization to improve state tracking and long-context memory in linear attention models.
aiviable path entropy measures bounded reflection in ai
mirror theory proposes studying intelligent systems by their capacity for coherent self-reflection, operationalized through viable path entropy, a measure of verified continuation diversity under budget constraints.
aifixing shape-prior shortcuts in single-shot 3d scanning
a new network design prevents depth-from-boundary shortcuts in fringe projection profilometry by using a wrapped-phase representation and calibration layer.
aiontology-amplified distillation for sovereign enterprise models
a study tests ontology-amplified distillation on a small language model for regulated finance, finding similar grounding to a frontier model but with limited statistical power.
aitesting causal graphs with outlier events
a new method uses outlier events to falsify incorrect causal graphs, providing statistical tests with false positive control and power guarantees.
aiin-context rl under non-stationarity survey
a survey on in-context reinforcement learning methods that handle changing environments without test-time parameter updates.
aiusing background knowledge for faster causal discovery
a new framework integrates expert constraints directly into scalable causal discovery algorithms, improving efficiency and accuracy.
aidoomql: a doom-like game running entirely in sqlite
a python terminal game where sqlite handles movement, collision, enemies, combat, and pixel rendering using a recursive cte ray tracer.
aideep learning improves causal mediation estimates
a two-stage method called unit uses deep representation learning to sharpen estimates of structural mediation parameters under a no essential heterogeneity assumption.
aitsconet: two-stage copula model for uncertainty-aware spatio-temporal forecasting
a new model combines a cnn-lstm with a gaussian copula to jointly forecast multiple environmental variables while providing calibrated uncertainty estimates.
aituring's ai assumption may be wrong
computer scientist peter j. denning argues that ai cannot capture tacit human knowledge like common sense and culture, making true human-level intelligence impossible.
aiformat sensitivity index measures prompt wrapper impact on llm scores
a new benchmark metric reveals how small formatting changes in prompts can significantly alter model accuracy and parseability, challenging the reliability of current leaderboard rankings.
aitoulmin model makes ml diagnosis more transparent
researchers use argumentation theory to break down retinal disease predictions into explainable parts, helping doctors trust ai decisions.
aimessage format effects in multi-hop agent relays depend on tier
study finds that structured message formats help or hurt llm agent relays depending on the model's capability tier, with strong models staying accurate and weak models degrading.
ai