We adapted Nemotron-3-Nano-30B-A3B for eight Indian languages without changing its backbone architecture. We expanded the vocabulary in place from 131,072 to 163,072 entries using continued byte-pair encoding and AdaptMix rebalancing, reducing tokens per word by 38.6%. We initialized new input and output rows by averag...
Gnani-Evon-v3.3-30B-A3B is a long-context hybrid Mamba-Transformer mixture-of-experts model for reasoning, instruction following, and tool use in English and eight Indian languages. Starting from NVIDIA's Nemotron-3-Nano-30B-A3B checkpoint, it retains the 52-layer backbone and changes the vocabulary, training data, and...
Large Language Models (LLMs) have made substantial progress in multilingual question answering, yet their ability to understand low-resource sociolinguistic contexts remains under-explored. We study North Korea as a unique testbed where decades of division have produced distinct differences from South Korea in vocabula...
Kiwoong Park, Seyoung Song, Donghyun Woo et al.· 0 citations
We introduce Sequent-Prover, a family of verifier-using language-model agents, and the post-training framework that produces them. Agents reason in an executable SMT-LIB scratchpad: they write complete SMT-LIB programs, query Z3 across turns, inspect solver feedback, repair formalizations, and terminate with an explici...
Debargha Ganguly, Wei-Cong Chen, Mohsen Hariri et al.· 4 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Deep research requires connecting multiple steps of search, reasoning, and computation, with intermediate findings guiding what to investigate next. As investigations grow, agents must maintain research state across model calls and check findings before errors propagate into subsequent work. We introduce PANINI-DR, a m...
M. Yigit Turali, Shreyas Rajesh, M. Efe Lorasdagi et al.· 0 citations
This paper makes the following key observations: Shallow exits are consistently more robust to jailbreak attacks than deeper ones; Exit depth affects how easily the adversarial suffix can be optimized, with deeper exits reaching lower attack loss; and adversarial suffixes affect utility uniformly across exit depths.
Large language models are increasingly deployed in contexts requiring adherence to ethical and legal norms, yet their alignment with internationally recognized human rights standards remains underexplored. We introduce UDHRBench, a large-scale benchmark for operationalising the evaluation of large language model compli...
Alak Raad, Noreldin Morssy, Zeerak Suhail et al.· 0 citations
Argument structures represent how individual arguments interact within a discourse. However, leveraging these structures to infer meaningful knowledge remains challenging, as it requires a formal representation of how argumentative influence propagates across the structure. We propose Neuro-symbolic Argumentation Reaso...
Siddharth Bhargava, Sara Tonelli, Patricia Mart\'in-Rodilla· Lecture notes in computer sc...· 0 citations
Large language models can post-edit ASR by using linguistic context to compare N-best hypotheses and rewrite the transcript when needed, often improving WER without retraining the recognizer. However, prompt-only correction is brittle: it may over-edit when top-1 is correct and hallucinate when the reference is absent,...
Shi-Ran Liu, Gao-Hui Xu, Sergio Burdisso et al.· 0 citations
Automated disease classification from patient-reported symptoms requires balancing the speed of lightweight discriminative models against the contextual understanding and latency costs of autoregressive large language models (LLMs). Decision foundation models offer an alternative by mapping representations directly to...
Recent bidirectional encoders have been modernized with innovations from causal large language models (LLMs). However, the pretraining recipe itself remains inherited from small-scale conventions, leaving encoders underoptimized, with no single model performing competitively across both classification and retrieval tas...
Jungwoo Park, Taewhoo Lee, Jaewoo Kang· 0 citations
Large language models are increasingly deployed in applications that act on users'long-term behavior histories, from personal assistants to recommendation and advertising systems. These applications demand the user dimension of LLM intelligence: inferring a person's preferences, intent, and likely future actions from w...
Yang Xiao, Yu-Song Sun, Haoyi Wu et al.· 0 citations
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
A new computational approach reveals how cells communicate to assemble into tissues. This could accelerate stem cell engineering, improve disease models, and inform therapies.
Microsoft Research Blog· microsoft.comOct 15, 2026
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 use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
