research note
This work addresses the critical challenge of enabling robust multimodal medical reasoning in low-resource Indic languages, a setting where most existing multimodal large language models (MLLMs) un…
research note
This paper addresses the challenge of scaling reproducibility assessments in the social and behavioral sciences, where conventional approaches rely on independent human reanalysts to manually recon…
research note
This paper addresses inefficiencies in large language model (LLM) architectures applied to time series (TS) data, particularly the uniform treatment of TS tokens and prompt tokens despite their dif…
research note
This paper addresses the computational challenge of accurately and efficiently predicting thermal conductivities of metal-organic frameworks (MOFs), which are porous materials with complex hybrid o…
research note
This paper addresses the challenge of evaluating Search Agents (SAs) that leverage large language models for complex, open-ended daily information-seeking tasks
research note
EconCSLib introduces a novel AI-assisted human-in-the-loop formalization system and Lean 4 library specialized for Economics and Computation research papers
research note
This paper addresses the challenge of autonomous scientific discovery by shifting focus from prescribing rigid agent workflows to engineering rich, reliable environments in which large language mod…
research note
This paper addresses a significant gap in the evaluation and deployment of large language model (LLM) agents, which traditionally assume static environments, whereas real-world settings are dynamic…
research note
This paper addresses the problem of benchmarking search agents—large language models (LLMs) integrated with search tools—on evolving, contamination-free knowledge
research note
This paper addresses a critical limitation in time series forecasting for highly incomplete and irregular real-world data — the common but unrealistic assumption that future valid observation timest…
research note
This paper addresses the challenge of managing fine-grained, dynamic data dependencies in parallel workloads, focusing on the limitations of traditional futures due to their value immutability
research note
This paper addresses a significant accessibility gap in conjoint analysis, a widely used method for measuring preferences across multiple disciplines including marketing, political science, healthc…
