arXiv Machine Learning August 13, 2026 By Sang Su Lee, Vineeth Loganathan, Shishir Dash, Vijay Raghavan

Certifying What Helps Customer-Return Timing: A Screen-and-Confirm Test for Conditioning Signals, and Why Decay Is Nearly Enough

Read the original on arXiv Machine Learning →

arXiv:2608. 11555v1 Announce Type: new Abstract: Practitioners enrich customer-return models with ever more signals (lifetime value, category, recency/frequency, calendar, geography), and the temporal-point-process (TPP) literature follows suit with covariate- and external-covariate-conditioned intensities.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

benchmarks

arXiv Machine Learning

5d ago

Excess Separability: Nuisance-Controlled Residual-Stream Probing for Benchmark Contamination Detection

arXiv:2608. 12652v1 Announce Type: cross Abstract: Benchmark contamination is diagnosed today with n-gram overlap, with likelihood-based membership inference, or with canary strings, and each needs something usually unavailable: the training corpus, a well-chosen test statistic, or foresight at dataset release.

By Florian Braun

llms benchmarks

arXiv AI

Jul 23

CUSUM-Shaped Inference-Time Monitoring and Targeted Re-Decoding for Quantized Small Language Model Reasoning

arXiv:2607. 20129v1 Announce Type: new Abstract: Quantized small autoregressive reasoning models can enter long, repetitive, or unproductive trajectories, yet inference-time compute is usually allocated without observing how a trajectory develops.

By El Hassane Ettifouri, Ayoub Belfatmi, Mahaman Sanoussi Yahaya Alassan, Walid Dahhane

llms efficiency

arXiv Machine Learning

Jun 2

Benchmarking Recursive-Collapse Warning Claims Under Matched False-Positive Control

arXiv:2606. 00329v1 Announce Type: cross Abstract: Recursive systems can enter collapse-like regimes -- self-reinforcing amplification, persistent recursion, and narrowing diversity that mask accelerating internal degradation -- before overt failure becomes visible.

By David Mullett

llms benchmarks safety

arXiv AI

Jul 7

Metronome: Bound the Cache, Keep the Beat for Real-Time Interaction Model Serving

arXiv:2607. 02640v1 Announce Type: cross Abstract: Real-time interaction models -- Moshi, MiniCPM-o, Qwen-Omni -- turn serving into a periodic real-time task: on every frame a session ingests streaming audio and must respond by a recurring wall-clock deadline, while its KV cache grows monotonically and stays pinned for the whole conversation.

By Jiaying Meng, Bojie Li

efficiency benchmarks

arXiv Machine Learning

Jul 3

Certified World Models as Sensing Clocks: Drift-Aware Deadlines for Active Perception

arXiv:2607. 01537v1 Announce Type: new Abstract: Certified world models estimate how long their predictions remain valid.

By Hongbo Wang

agents

arXiv AI

Jul 29

Entangled by Design: Spurious Intra-Variable Signal Routing in Tabular In-Context Learners

arXiv:2607. 25532v1 Announce Type: new Abstract: Consider a model trained at a single hospital to predict patient recovery, where the measured feature $X$ bundles the patient's true health signal ($C$) with a systematic artefact from that hospital's equipment ($S$).

By Athanasios Vlontzos, Giorgos Papanastasiou, Bernhard Kainz, Sotirios Tsaftaris

benchmarks

Related stories

Excess Separability: Nuisance-Controlled Residual-Stream Probing for Benchmark Contamination Detection

CUSUM-Shaped Inference-Time Monitoring and Targeted Re-Decoding for Quantized Small Language Model Reasoning

Benchmarking Recursive-Collapse Warning Claims Under Matched False-Positive Control

Metronome: Bound the Cache, Keep the Beat for Real-Time Interaction Model Serving

Certified World Models as Sensing Clocks: Drift-Aware Deadlines for Active Perception

Entangled by Design: Spurious Intra-Variable Signal Routing in Tabular In-Context Learners