Recent advances in Large Language Models (LLMs) have revolutionized artificial intelligence and how human interact with AIs. Despite impressive advancements, LLMs struggle with complex mathematical, scientific, and logical tasks. Inspired by human cognitive flexibility - our ability to dynamically switch mental perspec...
Gender bias remains a persistent concern in machine translation (MT), affecting both generated translations and their automatic evaluation. When a source text leaves a person's gender unspecified, translations may realize that person using masculine or feminine forms, and both MT systems and evaluation metrics may exhi...
Orfeas Menis-Mastromichalakis, Giorgos Filandrianos, Wafaa Mohammed et al.· 0 citations
Omni Demand Understanding is established as a distinct multimodal contextual inference problem: given an interaction stream, a model must detect whether a user demand is present and infer intent from multimodal and conversational context, and ODU is evaluated along five dimensions, covering both single-turn and multi-t...
Qi Chen, Yun-Fei Chu, Haolin He et al.· 1 citation· ⚡1
This work proposes ArenaFlow, a hierarchical credit propagation framework for open-ended agent reinforcement learning that leverages tournament-based relative ranking to derive trajectory-level reward signals and propagates trajectory-level advantages to high-confidence pivotal steps according to tournament survival de...
Qiang Zhang, Rui-Xue Ding, Fan-Rui Zhang et al.· 1 citation
Reach audiences
Advertise in front of researchers, engineers, and readers.
A linguistically motivated tokenizer for Vietnamese and Chinese that converts each syllable into IPA and factorizes it into three phonological components: onset, rime, and tone is introduced.
Nghia Hieu Nguyen, Thai Bao Huynh, Binh-An Dinh-Le et al.· 0 citations
HMS is introduced, a scalable framework that induces coarse- and fine-grained reasoning structures without predefined taxonomies and reveals a shared organization--understanding/planning, translating/drafting, and refining/verifying--alongside domain-specific variation.
Yu-Xiang Liu, Jiaming Luo, Eleftheria Briakou et al.· 0 citations
RM-EVAL is introduced, a reward model trained on human preference data from SEEDA, as a reference-free meta-evaluator that predicts human-like quality judgments at both full-sequence and partial-sequence levels and can be used as a learning signal to improve GEC generation via Reward-Guided Text Generation (RGTG), whic...
Ruo-Tian Wu, Bill Johnson, G. Saunders et al.· 0 citations
It is found that SFT consistently improves text-turn success, and that overall next-turn success increases for every model under gold-history evaluation, but these improvements do not transfer to autonomous workflow execution.
Neural morphological generation systems often achieve high aggregate accuracy on benchmark datasets, yet such performance can conceal systematic errors clustered in rare morphological subclasses. We present an orthography-aware diagnosis of Japanese past-tense verb inflection, treating hiragana not merely as a transcri...
Good tutoring adapts to the individual: it tracks what a learner knows, notices why they go wrong, and asks the next question that will help most. Most deployed tutoring tools instead serve fixed item banks and treat a wrong answer as a single bit of signal. We present CoLearn, an interactive, agentic tutor that suppor...
Kai-Lai He, Zhi-Hao Wu, Lin-Hai Zhang et al.· Proceedings of the 2026 Conf...· 0 citations
The Hirschberg algorithm is applied to perform the alignment between speech and text as a constrained random walk, allowing the Viterbi algorithm to prune the search space with arbitrary confidence while accounting for transcription errors.
Lawry Sorenson, Michael Crandall, Eric K. Ringger et al.· 0 citations
Undesired information such as harmful content and private data propagates through Multilingual Large Language Models (LLMs) via direct training and indirect cross-linguistic spread. Multilingual Machine Unlearning (MMU) aims to remove such information, yet its evaluation remains underexplored, leaving unclear whether u...
Kyomin Hwang, Hyeonjin Kim, Hyunho Lee 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.
