Category
3,243 papers
A Neuro-Symbolic framework that closes this gap by tightly coupling a Vision-Language Model for automatic First-Order Logic rule induction with a Dynamic Logic Tensor Network for differentiable rule verification, in a closed iterative feedback loop is proposed.
Testing the ability of common large language models to consider design principles to generate de novo proteins that bind metals and lipophilic small molecules without copying existing sequences highlights the utility of LLMs in making protein design more comprehensible and accessible to users without sophisticated desi...
SpecGuard is introduced, an inference-time backdoor detector that repurposes speculative decoding at zero added model-computation cost and doubles as a free, always-on signal for detecting backdoored LLM behavior.
Generative AI and the practice of"vibe coding"are changing how archaeologists carry out computational research, but their effects on the discipline's range of methods is still understudied. In this paper, we evaluate whether large language models (LLMs) are narrowing the variety of methods archaeologists use. We first...
Reach audiences
Advertise in front of researchers, engineers, and readers.
A language model normally begins training with random word embeddings: whatever'banana'means must be learned from training corpora. I implement St. Augustine's picture of word learning, meaning by ostension, for a small masked language model (DeBERTa) trained on 10M words: before training, visually grounded tokens rece...
Results show that scaling consistently improves performance, while multitask learning acts as a beneficial regularizer primarily for smaller-capacity models.
Distribution-aware Language Neuron selection is proposed, which leverages pairwise relationships between per-language activation distributions over the full activation range, including negative values, to quantify each neuron's language specificity by clustering languages using pairwise overlap coefficients between the...
Learning from limited text requires models to use context, generalize to new inputs, and retain useful capabilities. Qiushi Engine conducted a long-horizon, end-to-end autonomous research program on BabyLM 2026 Strict-Small, within 10 million corpus words and 100 million cumulative word presentations. Three stages conn...
Non-language data can serve as a partial substitute for language data for the training objective of next-token prediction but does not reliably support broader linguistic generalization, and transfer from non-language data is less efficient than additional language data.
Modern VLMs already encode much of what is needed for specialized domains; the challenge is learning how to ask, suggests modern VLMs already encode much of what is needed for specialized domains; the challenge is learning how to ask.
Comparing full-precision and quantized forward passes, and identifying two mechanisms that characterize pretrained quantization robustness, these mechanisms explain why quantization error that passes through numerous layers can still produce only small output changes, and are verified across models and quantization set...
Continuous and discrete flow matching are usually treated as separate constructions. This paper identifies a duality between them: projecting continuous convex-interpolant paths with one-hot targets through a position-wise argmax yields discrete convex-interpolant paths. The result requires source laws with appropriate...
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
A new computational approach reveals how cells communicate to assemble into tissues. This could accelerate stem cell engineering, improve disease models, and inform therapies.
Zero-knowledge proofs can verify computing results without rerunning workloads or exposing sensitive data. Magnetar helps bring them into the mainstream with support for standard programming languages, major speed gains, and quantum-resistant security. The post Proof-based general-purpose computing with Magnetar appeared first on Microsoft Research.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Learn how Google DeepMind and GovTech Singapore uses lightweight on-device Gemma models to intercept conversational scams in private chats with zero cloud data egress.
We’re giving developers, enterprises, scientists, and consumers access to Gemini 4 Argon, our latest frontier model.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
