collaborators

11 papers

cs.AI2026

Unsupervised Features Mining via Activation Geometry

Amit LeVi, Elad David, Max Fomin

Interpretability methods aim to reveal the features represented inside large language models (LLMs). Many existing methods begin with labeled examples of a human-defined concept th…

cs.AI2026

Linguistic Firewall: Geometry as Defense in Multi-Agent Systems Routing

Dvir Alsheich, Adar Peleg, Ben Hagag +3

The rapid integration of Large Language Models (LLMs) has driven the evolution of Multi-Agent Systems (MAS), where specialized agents collaborate to execute complex workflows. Effe…

cs.LG2026

Internal-State Probes Read the Situation, Not the Action: Three Negative Results for Pre-Action Misalignment Monitoring

Max Fomin, Elad David, Amit LeVi

Probes on model internals could help monitor agentic systems if they identify harmful text or tool actions before those actions are generated. We ask when an internal readout suppo…

cs.CL2026

You Had One Job: Per-Task Quantization Using LLMs' Hidden Representations

Amit LeVi, Raz Lapid, Rom Himelstein +3

Many LLM applications require only narrow capabilities, yet standard post-training quantization (PTQ) methods allocate precision without considering the target task. This can waste…

cs.CV2026

Mirage Probes: How Vision Models Fake Visual Understanding

Daniel Ben-Levi, Judah Goldfeder, Weiliang Zhao +5

Vision-language models (VLMs) can answer image-based questions confidently, and often correctly, even when no image is provided. This mirage behavior inflates benchmark scores with…

cs.CR2026

Extracting Recurring Vulnerabilities from Black-Box LLM-Generated Software

Tomer Kordonsky, Amit LeVi, Maayan Yamin +2

LLMs are increasingly used for code generation, but their outputs often follow recurring templates that can induce predictable vulnerabilities. We study vulnerability persistence i…