SIMA
DeepMind's Scalable Instructable Multiworld Agent (SIMA) is a generalist AI agent that follows natural-language instructions across nine commercial 3D video games like No Man's Sky, Teardown, Valheim, and Space Engineers.
Retrieval Augmented Thoughts (RAT)
RAT augments chain-of-thought by iteratively rewriting each reasoning step using retrieved context, sharply reducing hallucination on long-horizon generation tasks.
Quiet-STaR
Quiet-STaR generalizes the Self-Taught Reasoner (STaR) so that a language model learns to generate internal rationales between every token, not just for explicit QA problems.
Knowledge Conflicts for LLMs
A survey that maps the landscape of knowledge conflicts in LLMs, covering how they arise, how models behave under them, and how to mitigate them.
Stealing Part of a Production Language Model
The paper demonstrates the first practical attack that extracts the embedding-projection layer of production LLMs through their ordinary logit APIs.
Branch-Train-MiX (BTX)
Meta's BTX produces a single Mixture-of-Experts LLM by first training specialized experts in parallel and then mixing them, sidestepping the high cost of training one big generalist.
LLMs Predict Neuroscience Results (BrainBench)
BrainBench asks both LLMs and human experts to predict the outcomes of neuroscience experiments from their abstracts, and finds LLMs outperform experts.
C4AI Command-R
Cohere for AI releases Command-R, a 35B open-weight LLM tuned specifically for retrieval-augmented generation, tool use, and multilingual workflows.
Is Cosine-Similarity Really About Similarity?
This paper argues that cosine similarity between learned embeddings does not always measure semantic similarity, and gives analytical examples where it produces arbitrary or non-unique values.
MM1: Multimodal LLM Pre-training
Apple's MM1 paper runs extensive ablations on multimodal LLM pretraining choices and releases a family of models up to 30B parameters that set competitive MLLM pretraining benchmarks.
Get next week’s papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack