Category
3,244 papers
FAIRLENS shows that fair high-stakes VLM behavior requires similar treatment across groups and refusal to infer high-stakes attributes from appearance, and its question suite transfers to any face corpus with demographic annotations.
This work studies why pretrained language models often fail to preserve mixtures of many components and shows that exact preservation generally requires context-dependent correction, whose required dimensionality can grow with the number of components.
Declarative Attention is introduced, a protocol that elicits the model to declare where it needs to attend within its chain-of-thought, partitioning generation into three modes:(full context),(a specific region), and(recent output only).
DeepAffinity is proposed, which leverages Small Language Models with structured prompts and specialized prediction heads fine-tuned for this task, and shows DeepAffinity outperforms standard generative fine-tuning methods, while general-purpose open-source LLMs perform poorly without task-specific tuning.
Reach audiences
Advertise in front of researchers, engineers, and readers.
Mixture-of-Experts (MoE) is a scaling architecture for large language models that activates only a small subset of expert modules per token, enabling massive parameter growth with nearly constant computation. Recent Hybrid MoE architecture adds \textit{shared experts} to capture consistently useful representations, fur...
Results show that small grayscale patches can inject chosen target semantics across IR-VLM families under a controlled digital threat model, motivating stronger robustness evaluation for infrared multimodal systems.
Does the door-in-the-face technique work on language models? In humans, a large request that is refused makes a smaller follow-up request more likely to be granted. We test this on nine production models from three providers: each model refuses a large request, then receives a smaller version of the same request, and w...
A cornea-specialized large language model enhanced with RAG improved diagnostic accuracy in complex corneal cases, particularly among clinicians with lower baseline performance.
A systematic review and meta-analysis of studies evaluating the diagnostic accuracy of parent-report instruments for identifying speech and/or language disorders in children aged 0-6 years shows that several validated parent-report instruments demonstrate good accuracy for identifying children at risk, supporting their...
Evaluating the quality of Machine Translation (MT) for low-resource languages is a challenging cross-lingual problem in Natural Language Processing. Quality Estimation (QE) aims to predict MT quality in the absence of reference translations. This thesis investigates QE through multilingual modelling, architectural adap...
An independent, clean-room reimplementation of a self-model loop architecture for language-model agents (the "AC1 loop" described in Lark Laflamme's 2026 AC1-LLM / Laflamme-3T essays). The architecture wraps an LLM with a Bayesian belief over the agent's own interaction stance, re-injected into generation each turn alo...
Fil-C showed that C can be made memory-safe at run time by giving every pointer acapability and checking it on every access. We take its diagnostic ambitions and put themsomewhere else: in a compiler small enough for a person, or a language model, to hold inview at once, and with a different goal. Crust’s --mem-safe is...
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.
