arXiv AI August 13, 2026 By Parvel Gu

Detecting a Route Flip Is Easier Than Knowing Whether to Fix It: Causal Route-Mediated Damage in Quantized Mixture-of-Experts

arXiv:2608. 11212v1 Announce Type: new Abstract: Top-k Mixture-of-Experts (MoE) routing is discontinuous, so a deployment-motivated numerical disturbance -- simulated 4-bit KV-cache quantization read by a protected BF16 gate -- pushes tokens across decision boundaries and flips which experts fire.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

efficiency

arXiv Statistics ML

3d ago

Raw-Routed Mixture of Adapters: A Causal Intervention for Routing Collapse in Time Series Foundation Models

arXiv:2609.39445v1 Announce Type: cross Abstract: Time series foundation models (TSFMs) commonly adapt to new data by attaching a single trainable head to a frozen backbone, a one-size-fits-all setup...

By Hung Phan, Thuy T. Nguyen, Minh Ngoc Dinh, Nhat-Quang Tran

fine-tuning

arXiv Machine Learning

Aug 17

The Integer Alibi: Localizing Cross-Kernel Divergence in INT8-Quantized LLM Inference

arXiv:2608. 13756v1 Announce Type: new Abstract: Two GPU kernels implementing the same scaled INT8 GEMM interface are usually treated as interchangeable.

By Teng-Ruei Chen

llms efficiency benchmarks

arXiv Machine Learning

Aug 13

Located but Not Releasable: Silent Gate Inversion and Bounded Linear Release

arXiv:2608. 11822v1 Announce Type: cross Abstract: A growing body of work reports that language models represent task-relevant latent structure that they fail to use.

By Xining Xun

llms

arXiv AI

Aug 18

Routing Divergence Is Not Evidence of Behavioral Influence in Same-Weight MoE Self-Distillation

arXiv:2608. 15787v1 Announce Type: cross Abstract: Two Mixture-of-Experts (MoE) forward passes can share every weight yet route the same token through different experts.

By Cedric Caruzzo, Donggeun Yoo, Tae Soo Kim

efficiency

arXiv Machine Learning

Aug 5

Sensitivity, Causality, and Repair Dissociate: A Layer-Wise Analysis of Perturbation Robustness and Its Scaling

arXiv:2608. 03842v1 Announce Type: cross Abstract: When a language model fails on surface-perturbed input (typos, OCR noise, homophones), "which layer is responsible" has three natural operationalizations: where representations diverge most (sensitivity), where restoring clean activations recovers the prediction (causality), and where a small adapter can repair the damage (compensatory capacity) - and we show these three layer maps dissociate.

By Nathan Labiosa, David Buff, Ena Nayak, Erica Donno

llms computer-vision

arXiv Machine Learning

Jun 10

Quality Is Not a Safety Proxy Under Quantization

arXiv:2606. 10154v1 Announce Type: new Abstract: Quantized checkpoints are often screened first with quality metrics and only later, if at all, with direct safety tests.

By Sahil Kadadekar

llms efficiency safety

One email a morning, machine-written

Related stories

Raw-Routed Mixture of Adapters: A Causal Intervention for Routing Collapse in Time Series Foundation Models

The Integer Alibi: Localizing Cross-Kernel Divergence in INT8-Quantized LLM Inference

Located but Not Releasable: Silent Gate Inversion and Bounded Linear Release

Routing Divergence Is Not Evidence of Behavioral Influence in Same-Weight MoE Self-Distillation

Sensitivity, Causality, and Repair Dissociate: A Layer-Wise Analysis of Perturbation Robustness and Its Scaling

Quality Is Not a Safety Proxy Under Quantization