Understanding the social intelligence of large language models (LLMs) is increasingly important for applications involving human-AI interaction and multi-agent environments. Social intelligence comprises two aspects: cognitive intelligence, the ability to infer others'mental states, and behavioral intelligence, the abi...
Alieh Zamani, Soroush Esfahanian, Erfan Shahabi et al.· 0 citations
This work introduces ReaDy, the first speculative decoding method, to leverage HLA recurrent states for position-specific context retrieval during drafting, and achieves an average $3.16\times decoding speedup over autoregressive decoding with Qwen3.
Bo Sun, Zun-Hai Su, Xia-Lie Zhuang et al.· 0 citations
Pretrained vision-language-action models (VLAs) often fail midway through unseen long-horizon tasks. Recursive self-improvement (RSI) offers a remedy, but embodied RSI methods either refine the harness around a frozen executor and so cannot add a missing motion, or train the executor on persistent failures without aski...
Pei-Dong Wang, Ying Chang, Zhi-Ming Ma et al.· 4 citations
Cultural attitudes and social norms evolve over time, yet most cultural benchmarks for large language models (LLMs) treat culture as a static attribute of a country or region. We introduce ChronoCulture, a benchmark of 10,360 temporal pairs built from longitudinal survey data across 72 countries. Each pair contains the...
Rusali Saha, Nitya Khurana, Rui-Hong Huang et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
SemCER is introduced, which keeps CER's alignment and denominator and charges each grapheme edit a severity from an LLM judge, with no word segmentation.
Chemical chain-of-thought can contain hallucinated structural and property claims. We thereby introduce MolLean, a process-verifiable language that grounds chemical reasoning in an explicit molecular state. A layered Lean-based kernel checks state transitions and assertions over molecular readouts, from primitive graph...
Co-scientists and agentic scientific claim verifiers are increasingly used to assess claims across the sciences. Natural-language scientific claims, written for human experts, are often underspecified and so admit several defensible interpretations. Such verifiers usually pick one, often tacitly, and benchmarks score t...
Delip Rao, Ahmed Muharram, Chris Callison-Burch· 0 citations
Retrieval-Augmented Generation (RAG) models have become almost a cornerstone of open-domain question answering tasks; in which the quality of answers generated in the process, greatly relies on the effectiveness of retrieval mechanisms. In the realm of LLM, the last two years have seen tremendous progress in RAG archit...
Fazle Mohammed Tasfiq, Sabab Attin, Sheikh Md. Tahmid Hossain et al.· 0 citations
Audits of large language model (LLM) extraction from full-length documents report severe unreliability, leaving two questions open: what the failures actually consist of, and whether confidence signals can turn unreliable output into usable output. We run a preregistered, fully frozen evaluation of two new-generation l...
Hate speech has become increasingly prevalent on social media, raising concerns about its detection, interpretation, and moderation. Persian, a relatively low-resource language, lacks sufficient annotated data and computational resources for fine-grained hate speech analysis. In this study, we introduce a fine-grained,...
Ghazal Kalhor, Sima Kamandloo, Mehrsa Shamsian et al.· 0 citations
This work proposes SCOUT, a cascaded two-track retrieval framework that separates retrieval performance from exhaustive search, and evaluates it on 4 major benchmarks against 6 baselines and observes a significant query-time latency improvement up to 80.7x.
Diana Turmakhan, Aseem Srivastava, Vivek Gupta et al.· 0 citations
AI agent communities sustain lexical persistence, popular terms spread, recur, and achieve broad adoption, but whether they also develop the temporal semantic structure characteristic of human linguistic communities remains open. We compare MoltBook (AI agent community, 8 weeks), PTT (Chinese human BBS, 19 years), and...
Chih-Han Lin, Yu-Yun Chang, Po-Ya Angela Wang 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.
