Oshiwambo -- a cluster of mutually intelligible Bantu languages spoken by over a million people across northern Namibia and southern Angola, and the home language of roughly half of Namibian households -- has, to our knowledge, no published machine-translation evaluation benchmark. Major commercial services (Google Tra...
In verifiable domains such as math and coding, finding one correct solution among many attempts can matter more than the pass rate of each attempt. Post-training can concentrate large language model outputs around a few modes, while increasing sampling temperature has limited effectiveness. We introduce Don't Repeat Yo...
This paper presents an approach to use LLMs in a limited setting to generate a small, human-certifiable ACSL contract from the function's documentation, combined with a deterministic toolchain that supports a restricted ACSL profile and generates a driver that uses the CIVL verifier to check the implementation against...
H. Suh, J. Hückelheim, Stephen F. Siegel· 0 citations
Ontology-driven knowledge graph construction from industrial text remains challenging due to the domain specificity of documents, the scarcity of annotated resources, and the complexity of ontology engineering workflows. This paper presents and investigates the applicability of an ontology learning pipeline that combin...
Abdelhadi Belfadel, Maxence Gagnant, Joseph Kattan et al.· 0 citations
A literature-guided descriptor-based filtering framework for reducing composition search spaces and shows that literature-derived embeddings can support intuitive and reproducible filters for narrowing candidate composition spaces while preserving high-performing compositions.
In passage reranking, response ranking and multi-document question answering, LLMs can score several candidate documents or responses together in one prompt, each still receiving its own score. Such scorers are selected on ranking quality, but their scores determine a decision: what a score threshold retains, a reader...
Markus Frohmann, Mahdiyar Ali Akbar Alavi, Elizabeth Lingg et al.· 0 citations
ACache is presented, a cross-request cache reuse mechanism for shared spans, or affixes, at any position: prefix, infix, or suffix, and co-designs it with a modern inference engine, whose attention reads each request's recomputed Anchor KV states alongside one affix cache shared across concurrent requests.
Kai-Huan Liang, An Zhong, Xin Tan et al.· 0 citations
The introduction of WhiteMatter, which allows every layer to draw on past-token representations from any depth, and cyclic iteration, which updates interleaved groups of tokens in turn while processing the tokens within each group in parallel.
We use training-data attribution as an interpretable tool for capability discovery, mapping which regions of the pretraining corpus support social reasoning versus STEM reasoning in OLMo3-7B. Training-data attribution measures how strongly each training document influences a model's predictions on a benchmark, but docu...
Glenn Scott Matlin, Chandreyi Chakraborty, Saehee Eom et al.· 0 citations
Experiments show that Reflective On-policy Self-Distillation (ROSD), which distills transferable reasoning insights rather than complete reference trajectories, consistently outperforms standard OPSD and reinforcement learning baselines, better preserves reasoning diversity, stabilizes training, and mitigates late-stag...
Zi-Qi Zhao, Xin-Yu Ma, Liu Yang et al.· 16 citations
This work revisits classical sentence classification models from a margin enlargement perspective, aggregating token-level features via max pooling and directly estimating sentence scores using a lightweight MLP, and achieves substantial efficiency improvements while maintaining competitive performance with state-of-th...
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.
MIT News · Artificial Intelligence· news.mit.eduSep 24, 2026
A new method, called CW-Net, translates the reasoning process of an autonomous vehicle’s AI system into understandable concepts that explain its behavior.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
