Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Fazl BarezSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works12 from public data
- Towards Interpreting Visual Information Processing in Vision-Language Models129
This work studies the processing of visual tokens in the language model component of LLaVA, a prominent VLM, and finds that the model extracts object information from these refined representations at the last token position for prediction, mirroring the process in text-only language models for factual association tasks.
- Benchmark Inflation: Revealing LLM Performance Gaps Using Retro-Holdouts15
A systematic methodology for retrospectively constructing a holdout dataset for a target dataset, demonstrating the statistical indistinguishability of this retro-holdout dataset, and comparing LLMs on the two datasets to quantify the performance gap due to the dataset's public availability is introduced.
- Interpreting Learned Feedback Patterns in Large Language Models5
It is hypothesize that LLMs with LFPs accurately aligned to the fine-tuning feedback exhibit consistent activation patterns for outputs that would have received similar feedback during RLHF.
- The Anatomy of Alignment: Decomposing Preference Optimization by Steering Sparse Features4
This work introduces Feature Steering with Reinforcement Learning (FSRL), a framework that trains a lightweight adapter to steer model behavior by modulating interpretable sparse features and theoretically demonstrates that this mechanism is expressive enough to approximate the behavioral shifts of post-training processes.
- 3
- Beyond Monoliths: Expert Orchestration for More Capable, Democratic, and Safe Language Models2
This position paper argues that the prevailing trajectory toward ever larger, more expensive generalist foundation models controlled by a handful of big companies limits innovation and constrains progress, and advocates for an “Expert Orchestration” framework as a superior alternative that democratizes LLM advancement.
- 1
- –
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-11. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it. You will be asked to sign in.