Despite their capabilities, Multimodal Large Language Models (MLLMs) may produce plausible but erroneous outputs, hindering reliable deployment. Accurate uncert...
We present a scalable methodology for evaluating language models in multi-turn interactions, using a suite of collaborative games that require effective communi...
Small language models (SLMs) have emerged as efficient alternatives to large language models for task-specific applications. However, they are often employed in...
Argumentative LLMs (ArgLLMs) are an existing approach leveraging Large Language Models (LLMs) and computational argumentation for decision-making, with the aim ...
Mobile Agents can autonomously execute user instructions, which requires hybrid-capabilities reasoning, including screen summary, subtask planning, action decis...
The expansion of retrieval-augmented generation (RAG) into multimodal domains has intensified the challenge for processing complex visual documents, such as fin...
This paper proposes CIRCLE, a six-stage, lifecycle-based framework to bridge the reality gap between model-centric performance metrics and AI's materialized out...
Large Language Model (LLM) adapters enable low-cost model specialization, but introduce complex caching and scheduling challenges in distributed serving systems...
markdown Image: Google Drive document scanner on Samsung Galaxy S24 Ultra Rita El Khoury / Android Authority The new Galaxy S26https://www.androidauthority.com/...
Serverless computing simplifies cloud deployment but introduces new challenges in managing service latency and carbon emissions. Reducing cold-start latency req...
Software engineering agents (SWE) are improving rapidly, with recent gains largely driven by reinforcement learning (RL). However, RL training is constrained by...
Machine unlearning for large language models often faces a privacy dilemma in which strict constraints prohibit sharing either the server's parameters or the cl...
