We have 5 of 78 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Whether AI agents can act as scientists utilizing SAE tools for autonomous mechanistic discovery is evaluated to establish experimental model understanding as a measurable capability for closed-loop autonomous AI R&D.
SWE-Touch is introduced, a framework that stress-tests this setting through validated Counter-Edits: plausible edits to task-relevant code that conflict with task completion, and point to detecting workspace changes, reconciling conflicting edits with the task, and verifying the affected behavior as key capabilities fo...
Hetero-Designer is proposed, a novel pipeline that efficiently encodes intricate dependencies among queries, LLMs and roles through a novel Binary-Star Transformer and constructs Hetero-MAS in an autoregressive graph generation process.
Continual Learning (CL) for Large Language Models (LLMs) faces a fundamental Stability-Plasticity Dilemma : balancing the plasticity to acquire new capabilities with the stability to preserve prior knowledge. While Parameter-Efficient Fine-Tuning methods, such as LoRA, enable efficient adaptation, we identify a critica...
Post-training alignment is often shallow, eroding under fine-tuning. It remains untested as to whether constitutional midtraining interventions can produce durable alignment when cleanly isolated from post-training. We build a 394M-token constitutional corpus from Anthropic's Constitution and apply constitutional midtr...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
