VIDRAFT’s AX-Ray diagnostic framework evaluates AI models for deployment safety beyond standard capability benchmarks, using 117 structured diagnostic items across…
Researchers discovered a security vulnerability in proprietary LLM APIs that allowed encrypted chain-of-thought reasoning traces to be extracted and read.…
Simon Willison describes Doug Turnbull’s technique for tagging blog content without constraining a model to a fixed vocabulary. Rather than…
Researchers from UIUC, the University of Maryland, Nanyang Technological University, Purdue, and the University of Illinois Chicago introduce LLMRouter, a…
DarwinX proposes evolving the harness around a frozen LLM — its prompts, tools, memory, and control flow — using a…
AutoDesign targets systems that turn multimodal content into structured design outputs, arguing that most such pipelines stay static rather than…
This paper proposes the Spatial Memory Agent (SMA), a framework that improves spatial reasoning in frozen vision-language models without any…
This research examines internal activation patterns in hybrid linear-attention language models and identifies two distinct phenomena: sharp pre-attention spikes that…
The paper identifies a bottleneck in autoregressive transformers where only sampled output tokens are fed back into the model, discarding…
This paper targets inefficient test-time compute scaling in large reasoning models, where independent sampling wastes resources and naive pruning fails…
SKILLER addresses the model-mismatch problem, where reusable skills designed around powerful frontier models fail when deployed on smaller, cheaper language…
Maglev proposes a way for transformers to maintain persistent, token-wise memory while keeping both inference cost bounded and training parallelizable.…
