Mixture-of-Experts (MoE) models reduce computation by routing each token to a small set of experts, but each selected expert is still used at a fixed precision. We present DPA-MoE, a runtime precision control framework that makes routed experts any-precision. DPA-MoE encodes expert feed-forward weights as prefix-decoda...
Jaeyun Kim, Hoonki Lee, Su-Mi Shin et al.· Conference on Empirical Meth...· 0 citations
Residential design aims to transform existing homes into functional living spaces while satisfying diverse design preferences and physical constraints. However, existing floorplan generation methods typically assume empty building boundaries as input, whereas renovation requires reasoning over existing floorplans. Furt...
Jingguo Liu, Yuanqing Liu, Chong Zhang et al.· 0 citations
Large Language Models (LLMs) increasingly operate in multi-turn interactions that require maintaining latent conversational states, not only explicit facts. We study affective state as an implicit state inferred from sparse contextual cues that remain relevant after topic shifts, and ask whether LLMs expose internal at...
Wenqiu Tang, Zhen Wan, Yihui Wang et al.· 0 citations
Agentic knowledge graph question answering(KGQA) relies on sequences of executable operations, but trajectory-level rewards obscure their individual contributions. Successful trajectories may contain ineffective operations, while failed trajectories may contain useful ones. To assess individual operations, we propose O...
Yucheng Li, Mingyuan Li, Xiaxia Wang et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Natural language messages often contain quasi-identifiers that are weak in isolation but can jointly reveal an individual's private attributes. We call such a jointly revealing set of cues a quasi-evidence group. Existing privacy benchmarks focus on explicit identifiers, attribute inference, or task-driven disclosures,...
Yu-Fan Zhu, Yang-Fan Jiang, Yang Fei et al.· 0 citations
Attribute-value extraction is important for building high-quality product catalogs in e-commerce. Existing systems either rely on generative or tagging strategies for extracting the attribute names and their corresponding values. Tagging models directly label spans in the source, making them fast and grounded, but they...
Keshav Kolluru, Manas Gupta, Maroof Ahmad et al.· 0 citations
Current value alignment evaluations for large language models (LLMs) heavily rely on output compliance, overlooking whether LLMs maintain value consistency when alternating between generator and evaluator roles. Such consistency is increasingly important because modern LLM agents and alignment pipelines often rely on t...
Jun-Ru Wu, Jing-Ting Zheng, Yu-Qi Ren et al.· 0 citations
A pipeline built to be deterministic at every stage -- text extraction and optical character recognition (OCR), chunking, embedding, embedding, indexing, retrieval and inference -- returned byte-identical output at each stage across reruns, interruptions, edits, machines of one graphics processing unit (GPU) model and...
Cyber threat intelligence (CTI) relies on the timely identification of emerging threats, enabling organizations and security analysts to support situational awareness and decision-making. Social media platforms such as X (formerly Twitter) have become valuable CTI sources because vulnerabilities and attack activities a...
Ferry Afit Kurniawan, Kazushi Okamoto, Koki Karube et al.· 0 citations
Large language model (LLM)-guided Bayesian optimization (BO) uses past observations to guide search, but proposed directions and their revision can remain implicit. We propose Feedback-Guided Search State (FGSS), a structured hypothesis-management interface connecting language-based guidance to observed evidence, execu...
Hao Chen, Ziyang Ling, Ronald X. Xu et al.· 0 citations
We present a Korean Benchmark Suite (KBS) comprising Ko-ARC, Ko-GSM8K, Ko-EQ-Bench, Ko-WinoGrande, Ko-LAMBADA, and Ko-IFEval, covering six capabilities across 9,396 items. The suite combines review, localization, direct Korean construction, and redesign for Korean, avoiding a translation-only approach to benchmark adap...
Yeonkyoung So, Jongmin Kim, Sungmok Jung et al.· 0 citations
Multi-hop retrieval-augmented generation (RAG) requires an agent to retrieve evidence for a sequence of dependent sub-questions. When a wrong answer lacks a required passage, the passage may be inaccessible to the retriever, or the agent may have failed to issue a query that would retrieve it. Standard retrieval evalua...
Jia-Qi Wei, Wen-Xuan Huang, Cheng-Dong Xu 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.
