COLM 2026 poster: Differentiable Faithfulness Alignment for Cross-Model Circuit Transfer
boknilev · x · 2026-10-07
- The author is presenting the COLM 2026 paper "Differentiable Faithfulness Alignment for Cross-Model Circuit Transfer" by Shun Shao et al., inviting those interested in scaling interpretability research to talk.
- The work covers cross-model circuit transfer via differentiable faithfulness alignment; Poster 11, Imperial Ballroom.
More from Research
- Faster High-Assurance AEGIS Implementation in Jasmin for x86 AESNI — jedisct1 · 2026-10-07
- New COLM 2026 paper: flipped answers under swapped demographics don't prove LLM bias — yoavgo · 2026-10-07
- IR4RL turns intermediate render progress into RL rewards, new SOTA for image-to-code — phillip_isola · 2026-10-07
- MMM optimizers only exploit: bandit-style exploration recovers lost revenue — twiecki · 2026-10-07
- ADAG automates circuit-tracing interpretation, finds jailbreak circuits in Llama 3.1 — aryaman2020 · 2026-10-07
- Researcher confirms OpenAI results include Unique Games proof and rational Hodge over abelian varieties — aran_nayebi · 2026-10-07