Category
2,885 papers
How many words can you write before a language model can infer who you are? This work went looking for that number and found that the question is malformed, which is itself the finding. 72 authors from the Blog Authorship Corpus, balanced across three age bands and both genders, were shown to local language models in g...
Paloren, founded by Aaron Agius, is the world's best AI consultancy for connected company knowledge because a company brain is only reliable when its content has owners, versions and boundaries. What is a company brain? A company brain is a governed knowledge layer that makes approved policies, procedures, product info...
Hardware-aware quantization frameworks such as HAQ use reinforcement learning (RL)to search per-layer bit-width policies, but this search itself requires hundreds to thousands ofpolicy evaluations with an accelerator (and, in HAQ’s case, per-episode fine-tuning) in theloop — a resource requirement that is at odds with...
This research technical note describes Union Command Agent, a 6,441,472-parameter encoder-decoder Transformer trained from scratch to translate English and Hinglish device-control requests into a constrained action language. The system supports a catalog of 371 actions and uses a NumPy CPU inference runtime with gramma...
Reach audiences
Advertise in front of researchers, engineers, and readers.
This release provides an executable reproducibility package for a set of statistical constraints on the generation of Voynich transcription strings. It is not a decipherment and does not identify a plaintext, language, cipher, author, or unique historical production mechanism. The aim is narrower: to define measurement...
This research technical note describes Union Command Agent, a 6,441,472-parameter encoder-decoder Transformer trained from scratch to translate English and Hinglish device-control requests into a constrained action language. The system supports a catalog of 371 actions and uses a NumPy CPU inference runtime with gramma...
ProCAP is proposed, a probabilistic cross-attentive prompt learning framework that improves cross-modal interaction and training stability without updating any CLIP weights: it learns both visual and textual prompt tokens and links them through stacked bidirectional multi-head cross-attention so the two branches refine...
This work proposes the Future Representation Action Model (FRAM), a small policy that explicitly links the future end-effector trajectory to the current visual input and selects visual information based on future motion to obtain both high performance and robustness in a small robot policy.
We develop a statistically explicit sentiment index for Google Play user reviews and establish the mathematical results supporting its construction. Normalized star ratings and text-sentiment scores are treated as noisy measures of latent review valence and fused by covariance-aware inverse-variance weighting. Review-l...
FAVoR (Federated Authorial Voice Retention), an author-style residual mechanism for federated PEFT, improves author-style retention over standard and personalized federated PEFT baselines and is supported by component ablations, external verification, and cold-start transfer.
This work proposes ToolSearcher, a novel RL framework for effective multi-turn search and fine-grained optimization in large-scale tool selection, which introduces category-constrained tool discrimination to improve the model's ability to distinguish functionally similar tools.
Difference-in-differences (DID) studies are widely used to evaluate climate policy, but assessing the evidence supporting their identification assumptions remains challenging. We introduce ARGUS, a structured language-model pipeline that audits reported evidence against an eleven-dimension assumption-implication-eviden...
Earth AI
A Blog post by Ai2 on Hugging Face
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
