Answering questions over heterogeneous data means combining evidence from files, databases, documents and the web. Data agents automate this, but their success depends on context. Three context-engineering techniques (CETs) help by shaping it: semantic layers describe the data, orchestration splits work among agents, a...
Zhivar Sourati, Marianne Menglin Liu, Zheng Wang et al.· 0 citations
Reinforcement learning with self-generated labels, such as majority vote over a model's own samples, often recovers most of the gain of training with verifiable rewards. This is puzzling from the usual prompt-level view, in which majority vote only returns a model's modal answer and cannot add information about correct...
Dylan P. Wilson, Chengsong Huang, Jiaxin Huang· 0 citations
Negation is a fundamental aspect of language understanding and it is important vision-language models (VLMs) are able to process it effectively. We investigate how VLMs process negation by analysing attention patterns of different models. We draw comparisons between human gaze and attention in models when processing af...
Beth Pearson, Michael Wray, Martha Lewis· 0 citations
Reasoning distillation requires chain-of-thought (CoT) data with correct answers, but obtaining such data efficiently remains challenging. Forward CoT generation (FCG) followed by rejection sampling (RS) produces verified, question-only responses, yet may require many teacher calls for difficult problems. Reverse CoT g...
Zinan Tang, Zhuoshi Pan, Kairui Chen et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Wolof is spoken by 23M people, mostly in Senegal, but remains weakly supported by open-weight language models, while API models raise cost, governance, and sovereignty constraints for local deployments. In this paper, we present 0.6B-14B open-weight models adapted to Wolof through instruction tuning, preference alignme...
Gw\'enol\'e Lecorv\'e, Delphine Charlet, Pierre Adam et al.· 0 citations
Automating organizational work means answering many small typed questions about one piece of state (does this email need a reply, how urgent is it, who owns it) with probabilities good enough to act on without a human. The open typed-decision model we compare against, like a standard cross-encoder, answers each questio...
A single late-layer residual-stream direction is identified: a single late-layer residual-stream direction, the initiative vector, extracted from the model's own conversations without training or annotation, which transfers a speaker's turn-taking style to the model.
Chen Yuxuan, Xiao Yang, Jack Sun et al.· 0 citations
Competitive Token Selection (CoTS), a training-free framework that reframes latent intervention from binary mode selection into continuous allocation at the token level, and demonstrates that CoTS consistently outperforms standard CoT and state-of-the-art training-free latent reasoning methods.
Permutation generation with language models requires both text-conditioned ranking and a global one-to-one assignment between candidates and output positions. We study this problem through three diffusion-LLM parameterizations: hard-assignment prediction over shuffled candidate-index sequences, soft-assignment predicti...
Zhe Xu, Mingfu Liang, Kavosh Asadi et al.· 0 citations
Romance scam has become a serious problem via social media, and the improvement of artificial intelligence enable to fake identify easily. In the study, a chatbot has developed to detect romance scam in real-time through Line Messaging API. Using the seven stage theories in the social science field, the stages of roman...
Yi-cheng Liu, Guan-ru Lai, Yi-cheng Lai et al.· 0 citations
In recent advancements within speech processing, converting read speech to conversational speech has gained significant attention. The primary challenge in this domain is maintaining naturalness and intelligibility while minimizing computational overhead for real-time applications. Traditional read speech often lacks t...
Parshav Singla, Agnik Banerjee, Aaditya Arora et al.· 0 citations
Large language models have exhibited significant enhancements in performance across various tasks. However, the complexity of their evaluation increases as these models generate more fluent and coherent content. Current multilingual benchmarks often use translated English versions, which may incorporate Western cultura...
Xiaonan Wang, Jinyoung Yeo, Joon-Ho Lim 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.
