◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

R. Lapid

15 papers hereh-index 8338 citations25 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • first author4
  • middle author8
  • last author3

Across the 15 of 15 papers where every author was matched, so the position is known.

fields
  • cs.CV7
  • cs.CL4
  • cs.AI2
  • cs.CR1
  • cs.SD1

identity via Semantic Scholar / OpenAlex

activity
20242026
collaborators
Showing cs.CLShow all

4 papers · 1 filter

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.CL2026

Activation Steering for Masked Diffusion Language Models

Adi Shnaidman, Erin Feiglin, Osher Yaari +3

Masked diffusion language models (MDLMs) generate text via iterative masked-token denoising, enabling mask-parallel decoding and distinct controllability and efficiency tradeoffs f…

cs.CL2026

BenchOverflow: Measuring Overflow in Large Language Models via Plain-Text Prompts

Erin Feiglin, Nir Hutnik, Raz Lapid

We investigate a failure mode of large language models (LLMs) in which plain-text prompts elicit excessive outputs, a phenomenon we term Overflow. Unlike jailbreaks or prompt injec…

cs.CL2024

Open Sesame! Universal Black Box Jailbreaking of Large Language Models

Raz Lapid, Ron Langberg, Moshe Sipper

Large language models (LLMs), designed to provide helpful and safe responses, often rely on alignment techniques to align with user intent and social guidelines. Unfortunately, thi…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.