Category
3,243 papers
It is argued that epistemic diversity is a useful evaluation dimension for settings where LLMs are used to support knowledge-intensive tasks, and a preliminary framework for conceptualizing and measuring epistemic diversity in LLMs is proposed, and operationalized in two domains.
This work develops a new reinforcement learning signal named ConsensusPR, which directly reduces the reward sparsity of outcome reward across long reasoning trajectories, and introduces ConsensusBench, a novel dataset designed to provide rule-based process-level signals.
This work presents MedProb, a lightweight probing framework that predicts multiple-choice Med-VQA answers from frozen VLM representations without free-text generation, and shows the probe can be extended to open-ended generation via a rejection-sampling scoring procedure.
This work investigates whether LLMs can learn molecular design strategies from cheaper synthetic tasks that generalize to expensive molecular lead optimization settings and suggests that scaling post-training using synthetic tasks is an effective strategy for adapting LLMs to high-cost experimental scenarios that are t...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Results show that feature recurrence can overstate cross-lingual transfer, while identifying a language-agnostic translation-initiation direction in Gemma 2 and Gemma 3.
This perspective lays down the basic concepts needed to understand MEG foundation models and provides a didactic overview of the field's key design choices, including tokenization, sensor- versus source-space representations, sensor-geometry encoding, backbone architectures, self-supervised objectives, and pretraining...
PLUME (Personalized Low-Rank Adaptation through User Modulation and Shared Subspace), a lightweight framework that achieves efficient and expressive per-user adaptation by leveraging a shared task-specific subspace, is proposed as a scalable and semantically grounded approach to LLM personalization.
Overall, the results challenge the assumption that effective post-training must be token-intensive and point to a new direction for understanding and designing more efficient post-training algorithms.
GSMultiAgent is proposed, a multi-agent collaborative cascade framework built atop Hermes Agent, which transforms natural-language mission requirements into optimized guidance system models through structured agent cooperation with feedback-driven iterative refinement and establishes multi-agent coordination with struc...
A novel empirical study targeting three domain- specific languages for transformation rules, namely Comby, GritQL, and Ast-Grep, which shows great potential for LLMs to generate sound, correct, generalizable, and reusable rules.
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...
While self-assessment against marking criteria is widely advocated, its effects on different components of student work remain unclear. This study evaluates a redesign of a UK foundation-year engineering laboratory module incorporating a structured self-assessment coversheet and a progressive authorship scheme. Across...
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.
