These cross-lingual transfer experiments show that linguistic proximity has no consistent predictive power for transfer performance, whereas structural similarity in rhetorical organization shows a weak but consistent positive correlation across models, and a set of three methods that explicitly leverage structural inf...
Kazuhiro Yamauchi, Marie Katsurai· Proceedings of the 26th ACM/...· 0 citations
This paper identifies a gap in both speech initiation and response content that requires genuine content understanding and intervention decisions grounded in it and constructs context-matched English monologues in which only the trigger utterance varies within a topic.
Linkai Peng, Baorian Nuchged, Kaiqi Fu et al.· 1 citation· ⚡1
Model fusion integrates the capabilities from source models into a single target model. As of June 2026, Hugging Face hosts more than 2M models. This growing pool provides a rich base for model reuse and capability integration. Yet existing surveys often cover only separate parts of this space, and they do not provide...
Shuo Cai, Yanggan Gu, Zihao Wang et al.· 0 citations
Graph-based retrieval-augmented generation (RAG) is widely used for multimodal, cross-document question answering. However, building corpus-level graphs is expensive, slow to query, and difficult to maintain. We present TrioRAG, a graph-free multimodal framework that integrates evidence from three complementary signals...
Tithi Rakshit, Hongkuan Zhou, Lavdim Halilaj et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
The findings show that even a direction orthogonal to a concept at one layer can contribute to the concept's downstream amplification, and demonstrate that more fine-grained category residuals should also be considered beyond shared general harmfulness representation to fully understand LLM safety.
Soyeon Park, Seogyeong Jeong, Sunwoo Kim et al.· 0 citations
Backend delegation is an effective and modular approach for combining natural duplex speech interaction with strong agentic tool-call capabilities and significantly outperforms GPT-realtime-mini and Qwen3-Omni-30B-A3B-Instruct on EVA-Bench.
Ke Hu, Slyne Deng, Chen Chen et al.· 3 citations· ⚡2
ReaLMem is introduced, the first benchmark built from authentic multi-year personal visual archives, paired with first-person subjective annotations, and ChronoProfiler is proposed, a temporal-weighting profiling module that computes temporal stability scores for user attributes and applies them as a salience prior, re...
Wen-Qi Zhou, Zhuo-Rui Yu, Kai-Ao Wen et al.· 0 citations
Reflective Recovery is proposed, a simple yet effective self-supervised approach that transforms failed reasoning attempts into recovery training data and enables models to develop emergent self-correction behaviors, representing a paradigm shift from outcome-oriented memorization to process-oriented reflective reasoni...
Qi-Rui Chen, Ren-Jie Pi, Jia-Hui Gao et al.· 0 citations
In Human-LLM dialogue, follow-up user utterances may implicitly conflict with earlier intents, leading the LLM to misinterpret user needs and generate inappropriate responses. A reliable dialogue system should proactively detect user-side conflicts before generating a response and seek clarification when necessary. How...
Jinqiang Wang, Tao Zhu, Huansheng Ning· 0 citations
While Large Language Models (LLMs) achieve high accuracy on established Classical Chinese Poetry benchmarks, it remains challenging to distinguish transferable Linguistic-Aesthetic Reasoning from reliance on familiar pre-training patterns. To address this issue, we introduce Neo-Classic, an evaluation benchmark that co...
Han Zhang, Zihan Gu, Zhiyuan Wang et al.· Annual Meeting of the Associ...· 0 citations
FakeSpotter is presented, a content- and strategy-agnostic tool designed to estimate the viral misinformation risk of textual content by measuring structural fingerprints of misinformation rather than directly adjudicating truthfulness.
Generative AI (GenAI) applications have achieved rapid consumer adoption, yet little large-scale research examines user-perceived quality, trust, and adoption barriers. We present one of the first cross-application analyses of app store reviews for six major GenAI applications (ChatGPT, Gemini, Microsoft Copilot, Claud...
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.
