IOI
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Certified Circuits: Stability Guarantees for Mechanistic Circuits
Announce Type: replace Abstract: Understanding how neural networks arrive at their predictions is essential for debugging, auditing, and deployment. Mechanistic interpretability pursues this goal by identifying circuits--minimal subnetworks responsible for specific behaviors. However, existing circuit discovery methods are brittle: circuits depend strongly on the chosen concept dataset and often fail to transfer out-of-distribution, raising doubts whether they capture the concept or merely...
Pattern Selectivity is Not Task-Causal Structure: A Cross-Architecture Mechanistic Study of Composed-Task Circuits in 1B-Class Language Models
arXiv:2606.05378v1 Announce Type: new Abstract: We test whether a single screen-and-ablate recipe -- identify attention-head circuits by task-pattern selectivity, then verify by causal ablation against a matched-random null -- produces consistent mechanistic claims across model families. The recipe ports across pipelines; the specific circuit it identifies does not. Across four composed tasks (indirect-object identification, greater-than, successor sequences, variable binding) and three...
FrontierCode
Introducing FrontierCode Raising the bar from correctness to quality Today’s coding benchmarks have established that models can write correct code. But as AI-generated code becomes the dominant path to production, correctness is now table stakes. The question that we should be asking is: can models actually write good code?
Query Circuits: Explaining How Language Models Answer User Prompts
arXiv:2509.24808v2 Announce Type: replace Abstract: Explaining why a language model produces a particular output requires local, input-level explanations. Existing methods uncover global capability circuits (e.g., indirect object identification), but not why the model answers a specific input query in a particular way. We introduce query circuits, which directly trace the information flow inside a model that maps a specific input to the output.
When the Scaffold Stays On: AI, Practice Style, and Screening in Elite Skill Formation
arXiv:2606.06253v1 Announce Type: cross Abstract: Generative AI raises short-term productivity by completing tasks that learners would otherwise practice on their own. Whether this substitution erodes frontier skill, the skill behind top-tail non-AI-aided performance, is an open question of rising stakes. The sharper question is whether selection mechanisms can screen apart two coexisting types: substitute-users, who use AI in place of deliberate practice, and complement-users, who use it to...