Loading activity…
@sewon__min
Assistant professor @Berkeley_EECS @berkeley_ai || Research scientist at @allen_ai || PhD from @uwcse @uwnlp
AI
DR Pixel's researchers report that page-native research outperforms OCR-based baselines without training and requires fewer tool calls.
XAI
In posts describing new research, the authors say some base models recovered much of reinforcement learning’s reasoning gain when prompted with model-specific “token cues,” and they say the work also includes a safety case study on refusal and compliance.
AI
A post says not yet. It describes “high-complexity” tasks whose difficulty grows quadratically with the size of the literature, rather than linearly.
