Skip to main content
Search

Polytechnique Montréal

4 related articles

Subscribe to updates
  1. A honeybee swarm's hive mind behaves like one reinforcement learning agent, with each scout a parallel bandit sample

    When honeybees choose a nest site, individuals blindly switch to the option advertised most strongly by neighbors, and this local imitation is shown to be equivalent, at the group level, to a single online reinforcement-learning agent solving a multi-armed bandit. That macro-agent updates nest-site probabilities by a rule named Maynard-Cross Learning, with each scout acting as one parallel action-reward sample. The derivation covers the weighted voter model, a simplified description, and simulations indicate roughly 500 scouts suffice to track the macro-dynamics and converge on the best site.

  2. arXiv

    Time-series foundation models can skip whole Transformer blocks: A100 latency drops 11% to 13% at moderate sparsity, with dataset-level variation

    Two pretrained time-series foundation models skip whole Transformer blocks at inference, leaving mean forecasting quality nearly unchanged across 1,088 held-out windows while cutting median A100 batch-1 latency by 11.2% and 13.4% at moderate sparsity.

  3. arXiv

    MLCommons releases Jailbreak Benchmark v1.0: unsafe-response rate across eight open-weight models rises from 11.08% to 18.65% under jailbreak conditions, with an average Resilience Gap of 7.57%

    MLCommons Jailbreak Benchmark v1.0 introduces an end-to-end methodology that evaluates eight open-weight large language models with paired baseline and adversarial conditions using 264 seed prompts spanning eleven hazard categories and representative attacks drawn from the MLCommons Jailbreak Taxonomy, judging responses with the AILuminate Assessment Standard v1.4 and measuring robustness through the Resilience Gap; the unsafe-response rate rose from 11.08% at baseline to 18.65% under jailbreak conditions, yielding an average Resilience Gap of 7.57%, with accessible systems showing a larger mean gap and attack effectiveness varying substantially across attack categories and hazards.

  4. arXiv

    GrayShield overwrites Transformer weight mantissa LSBs with a Gray-code-guided low-transition sequence, cutting attacker recovery by about 50 percentage points across four model presets and two real-world malware payloads while keeping accuracy impact under 1%

    The work proposes GrayShield, a lightweight, post-training, zero-data sanitization method that completely overwrites the declared mantissa least-significant-bit channel of 32-bit floating-point Transformer weights with a Gray-code-guided low-transition sequence, giving that channel zero capacity; across four Transformer model presets, two real-world malware payloads, and five attacker variants, it maintains sub-1% accuracy impact and achieves a 49.96±0.66 percentage-point Recovery Reduction against seven post-training defenses, with substantially smaller weight-distribution shift than PatternMask and Post-Training Quantization.

You’re all caught up