Event cameras offer microsecond temporal resolution, high dynamic range and no motion blur, but referring video object segmentation (RVOS) lacks event-stream datasets and models. We introduce Event-SAMA-239K, a synthetic-event conversion of the SAMA-239K grounded video-chat corpus and all additional SAMA training data:...
Sergei Fedorchenko, Max Zehnder, Nikola Zubi\'c et al.· 0 citations
As large language models (LLMs) become more widespread in Africa, their safety in low-resource languages remains largely untested since most red-teaming work focuses on English. This study evaluates six state-of-the-art LLMs using 400 explicit adversarial prompts in Yoruba and Nigerian Pidgin, categorised into four har...
Paula Chikaodinaka Anyanwu, Valdini Douglace Lemofouet, Blessing Ngozi Uzor et al.· 0 citations
Multi-turn conversations with multimodal large language models (MLLMs) reuse input context, but long multimodal inputs increase time to first token (TTFT). Query-aware hard pruning reduces prefill tokens but permanently excludes information that later questions may require. We propose Raincheck, a framework for deferre...
Wenjie Huang, Jun Zhang, Hongyaoxing Gu et al.· 0 citations
View- and target-specific echocardiography AI models capture useful but complementary information and may not achieve sufficient predictive performance in isolation. A learned ensemble is a natural way to combine these outputs, but heterogeneous models typically require each output to be converted into a binary decisio...
Ryo Takizawa, Tempei Kabayama, Chiemi Yamazaki et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
ExLabel is proposed, an LLM-based, self-evolving, experience-guided assistant for task clarity and test coverage assessment in SWE datasets that maintains an evolving experience bank that distills cross-instance knowledge into stable yet adaptive judgment criteria and reuses relevant experience to guide the assessment...
Zhong-Hao Jiang, Xu-Yang Zheng, Yan-Fu Yan et al.· 0 citations
Research on medical item difficulty has largely focused on prediction rather than on identifying interpretable patterns associated with empirical difficulty. This study used empirical difficulty labels to guide large language models (LLMs) in inducing difficulty rubrics and examined how rubric guidance affected LLM dif...
Xiaomeng Xiong, Marcus Walker, Yanlin Jiang· 0 citations
The decoding order of masked diffusion language models (dLLMs) can substantially affect generation quality, yet common decoders typically apply the same reveal rule throughout generation. Confidence provides a strong default, but it measures how decisively a position can be predicted now, not how useful revealing that...
Chengwei Zhou, Zhaoyan Jia, Massoud Pedram et al.· 0 citations
On-policy distillation (OPD) is increasingly adopted in the post-training of large language models. However, a stronger teacher may fail to improve the student. Prior work attributes this to a lack of new knowledge, but what that knowledge is remains unclear. We show that OPD learns not only \textit{how to branch}, i.e...
Shiping Yang, Chuanqi Tang, Hossein Hajimirsadeghi et al.· 0 citations
Compositional generalization remains a persistent limitation of transformer language models: even when a model learns to combine known facts correctly in-distribution (ID), the same compositional mechanism may fail when applied to out-of-distribution (OOD) knowledge. We investigate this compositionality gap in a contro...
Introspection, the ability of a system to access and reason about its internal signals, is crucial for language model (LM) self-consistency and scalable interpretability. Prior work argues that LMs possess introspective capabilities, and that training (SFT) could enhance such behavior. However, most setups leave open t...
Zilu Tang, Jongin Kim, Kerem Sahin et al.· 0 citations
Looped Transformers increase computational capacity through the repeated application of shared blocks, but their recurrent depth makes conventional full-depth decoding expensive. While existing speculative pipelines accelerate generation by processing consecutive token positions at varying depths, they are typically li...
AtomTree is presented, a hierarchical framework for state-aware task planning with LLMs that incrementally builds a tree of subgoals and actions, where the LLM decides at each step, from the current symbolic state, whether to further decompose or to output a grounded low-level action.
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.
