Low-rank adaptation (LoRA) enables efficient specialization and distribution of large language models through compact adapters. However, untrusted adapters introduce a supply-chain threat: a backdoored adapter can cause a model to generate harmful content, malicious code, political propaganda, or covert advertisements...
Doniyorkhon Obidov, Honggang Yu, Xiaolong Guo et al.· 0 citations
Large Language Models (LLMs) have accelerated drug discovery, particularly in the automated design of antimicrobial peptides (AMPs). However, current validation pipelines for peptide generation models overlook historical precedents showing that certain drugs carry health risks predominantly for individuals with specifi...
Doniyorkhon Obidov, Xiaolong Guo, Yonghui Li et al.· 0 citations
In a dual-use field, hazardous knowledge and the benign expertise around it share vocabulary, concepts, and causal structure. That overlap makes selective refusal hard, and existing methods such as unlearning and refusal training overgeneralize their suppression into the benign side. We argue for conditioning, not supp...
In Large Language Model (LLM) training, data mixing plays a pivotal role in determining model performance. Recent methods optimize mixture weights via proxy models, but they rely on the assumption of static data distributions. As a result, when the underlying data pool shifts, these methods require costly retraining fr...
Zinan Tang, Yukun Zhang, Shaomian Zheng et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
As AI agents become increasingly capable of complex, long-horizon reasoning, rigorous evaluation is essential for measuring progress toward real-world healthcare applications. However, existing healthcare benchmarks are often static or narrow in clinical scope, motivating broader evaluation of agents acting on raw pati...
Qianchu Liu, Sheng Zhang, Guanghui Qin et al.· 0 citations
Interactive LLM agents increasingly work with users across tasks, yet remembering a previous correction does not ensure that the agent changes its behavior in the future. In a diagnostic constructed from anonymized real-world agent interactions, agents using Mem0 still violate 57.5% of applicable preference checks. We...
Yujun Zhou, Kehan Guo, Haomin Zhuang et al.· 0 citations
Backdoor attacks pose a serious threat to the safety and reliability of Large Language Models (LLMs), as they cause models to behave normally on clean inputs while producing attacker-specified responses when hidden triggers are present. Removing such unknown backdoors is particularly challenging when the defender does...
Kazuki Iwahana, Masaru Matsubayashi, Takuma Koyama et al.· 0 citations
Transformers have become the dominant architecture for large language models, largely due to the scalability and flexibility of attention, feed-forward layers, residual connections, and normalization. This paper introduces dynamic short convolutions as an additional neural network primitive for improving Transformers....
Oliver Sieberling, Bharat Runwal, Rameswar Panda et al.· 0 citations
Deceptive web content, widely instantiated across the internet and commonly known as \textit{social-engineering attacks}, manipulates autonomous web agents into submitting users' personally identifiable information (PII) to attacker-controlled endpoints. In this paper, we show that social-engineering attacks are highly...
Soham Roy, Sarthakbrata Halder, Arya Bharaty et al.· 0 citations
Training tool-calling agents requires large-scale trajectory data with verifiable labels, yet existing approaches either synthesize environments that diverge from real API behavior or generate tasks without ground-truth outcomes for verification. We present FireFly, a pipeline for generating verified tool-call data fro...
Yuxuan Lu, Ziyi Wang, Yingzhou Lu et al.· 0 citations
Reinforcement learning with verifiable rewards (RLVR) is widely used to improve the reasoning capability of language models, since model-generated answers can be easily verified by a rule-based verifier. In contrast, reinforcement learning from human feedback (RLHF) is mainly used to optimize open-ended conversation wi...
Shangjian Yin, Yu Fu, Yue Dong et al.· 0 citations
This work identifies the main barrier to adopting compile-and-execute on the web: For it to work well, tools must map cleanly to semantic actions, with effects known before execution, so a compiler has enough information to emit a program.
Julien Piet, Ann T. Chow, Yi Hou et al.· 7 citations· ⚡2
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.
