While Large Language Models (LLMs) rely on highly non-linear components, in this work we demonstrate that they exhibit fundamental linearity: when inputs from distinct text streams are linearly combined, the model outputs a superposition of the individual next-token distributions. We term this the \textit{Superposition...
Pavel Tikhonov, Anton Korznikov, Matvey Mikhalchuk et al.· 0 citations
An end-to-end study of automatic speech recognition (ASR) for adolescent health communication in three Ghanaian languages, validated through KasaHealth, a live voice-first ASRH application deployed in all three languages, complemented by Senti-Check, a technical evaluation harness.
Stephen E. Moore, Akwasi Asare, Mich-Seth Owusu et al.· 0 citations
TimeBraid, a series of unified time-series and language models that align pretrained language models and pretrained time-series foundation models through interleaved global residual attention layers, remains competitive with far larger general-purpose models and task-specific counterparts.
Xin-Yue Wang, Jia-Cheng Pang, Kun Zhou et al.· 0 citations
PPTBench establishes a measurable testbed for studying visual coding and advancing agents toward more reliable visual creation, and shows that agents can generally produce valid slide files, but struggle to produce high-quality reconstructions that faithfully recover the semantics and visual structure of the target.
Xiao-Qiu Wang, Yi-Zhe Chi, Wen-Yi Li et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Verified search, in which a language model proposes programs, a hard evaluator scores them, and selection keeps the best, has recently moved mathematical records; controlled ablations of the proposer-side components remain rare. We instrument a minimal FunSearch-style loop at office scale (a 30B local model on a laptop...
While TTLab's system localizes error spans effectively, classification of rare error types remains challenging, highlighting the need for data augmentation for tail categories.
Ali Abusaleh, Bhuvanesh Verma, Alexander Mehler· 1 citation
An exploratory, single-seed ablation of TALH (Adaptive Latent Hybrid), a decoder-only language model with parallel Multi-head Latent Attention (MLA) and a custom recurrent state-space (SSM) branch supports implementation-specific hypotheses rather than general conclusions about MLA, SSMs, or mixture-of-experts models.
This work introduces PROOF, a profile-oriented benchmark for factual coverage in instruction-tuned language models, and measures factual coverage as a structured, intervention-aware profile rather than a single claim about what a model believes.
A. Chetvergov, Mikhail Solovev, Timofei Sivoraksha et al.· 0 citations
This paper examines Pythia and OLMo 2 across 66 pretraining checkpoints, three of the post-training stages of OLMo 2 that have been released, about 90,000 continuations, and four training corpora, and traces the provenance from end to end to show exactly where such descriptions came from.
Deep search requires LLM agents to decompose complex queries, search for evidence, and synthesize grounded answers, yet existing ReAct-style agents suffer from two limitations: role coupling, where one policy must handle planning, evidence use, and synthesis; and context accumulation, where growing search histories int...
Xing-Yu Wu, Yuchen Yan, Zhengxi Lu et al.· 0 citations
This work proposes Agentic-GER, an LLM-based agent for terminology correction in long-form speech, which uses global context from the full transcript to identify suspicious terms and resolve ambiguous hypotheses.
Yan-Qiao Zhu, Wu-Peng Wang, Zhifu Gao et al.· 0 citations
The main findings are that diverse, high-quality SFT establishes a strong capability floor and difficulty filtering keeps RL prompts within a productive learning range, and reward reliability provides a practical principle for ordering stages.
Chia-yuan Chang, Ren-Yuan Cheng, Rui Feng 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.
