Model merging is a scalable alternative to multi-task training that combines the capabilities of multiple specialised models into a single model. This is particularly attractive for large speech foundation models, which are typically adapted through domain-specific fine-tuning, resulting in multiple customised checkpoi...
Carlos Carvalho, Francisco Teixeira, Thomas Rolland et al.· 0 citations
Ctrl-G is proposed, to the best of the authors' knowledge the first KG-RAG framework to jointly control structural and interaction exposure to a remote LLM while supporting accurate multi-hop reasoning.
Xingyu Tan, Xiao-Yang Wang, Qing Liu et al.· 15 citations· ⚡1
This paper presents a comparative analysis of community unionism (CU) in two distinct historical and organizational contexts: the National Boot and Shoe Union (B\&S) in the 1920s and Unite Community in the 2010s--2020s. Using BERTopic for thematic modeling and cTF-IDF weighting, alongside word frequency analysis, the s...
Quantitative Discourse Analysis has seen growing adoption with the rise of Large Language Models and computational tools. However, reliance on black box software such as MAXQDA and NVivo risks undermining methodological transparency and alignment with research goals. This paper presents a hybrid, transparent framework...
Thomas Compton· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Large Language Model (LLM)-based agents have recently demonstrated remarkable capabilities in deep research tasks, yet their application to the medical domain remains challenging. The leading proprietary systems achieve only modest results on complex medical benchmarks. This exposes two key bottlenecks: (i) limited cli...
Ailing Yu, HaoYang Hong, Lan Yao et al.· 0 citations
An agent that must call several tools to fulfill a request fails when the tool retriever omits any one of them, yet tool retrievers are mostly built and evaluated on queries requiring a single tool. We compare representatives of six retrieval structures (flat lexical and dense retrieval, LLM query decomposition, LLM-na...
It is demonstrated that MCP tool-call traces can act as effective behavioral side channels for user profiling, motivating the development of privacy-aware mechanisms for agent-tool interactions.
Dong-Hang Duan, Qing-Yu Liu, Yi-Fei Liu et al.· 0 citations
Understanding how code changes affect program semantics is a core aspect of code reasoning in language models. It is commonly evaluated by asking whether two programs are semantically equivalent, but a yes/no answer does not reveal whether a model knows which code change caused a semantic difference, or which sequence...
Omid Saghatchian, Ali Mahzoun, Khashayar Etemadi et al.· 0 citations
Computer-use agents increasingly tackle tasks ranging from everyday desktop activities to long-horizon professional workflows. Yet interfaces centered on screenshots and mouse-and-keyboard actions can impose a human-interaction prior, requiring repeated screen interpretation while leaving the computer's semantic and pr...
Hao-Qing Wang, Xiao-Yi Zhang, Si-Cheng Fan et al.· 0 citations
Aligned RAG Evaluation is introduced, a matched-query protocol that jointly examines clean and poisoned responses, with and without defense, and exposes critical blind spots in ASR-based evaluation and motivates a more comprehensive assessment of RAG poisoning defenses.
Calibrating a cosmological simulation is an expensive, high-dimensional parameter optimization task. Previous works employ Bayesian optimization for automation, which treats the simulator as a black box and precludes the incorporation of human domain knowledge or workflow into the selection policy. We propose AgenticTu...
Decision models such as Jev have emerged as a highly promising paradigm for LLM agent systems, providing lightweight and reliable categorical reasoning for rapid System One execution. However, existing generation-oriented inference engines fail to support these workloads effectively, suffering from severe prefix recomp...
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.
