research note
This paper investigates the limits of reinforcement learning with verifiable rewards (RLVR) for teaching large language models (LLMs) to use knowledge graph (KG) navigation tools under a deliberate…
research note
RePlan-Bot addresses key challenges in embodied instruction following (EIF) within interactive 3D environments, such as long-horizon planning, handling irreversible state changes, and recovering fr…
research note
This paper addresses a key gap in user profiling research where prior work largely evaluates models on static snapshots of user-generated content (UGC), ignoring the dynamic and streaming nature of…
research note
This study investigates the gas-phase mass-metallicity relation (MZR) in dwarf galaxies (stellar mass 8.9 < log(M*/M☉) < 9.5) across different large-scale cosmic environments — voids, filaments, and…
research note
This paper addresses a key limitation in emotional text-to-speech (TTS) systems — the insufficient modeling and control of non-verbal vocalizations (NVs) such as laughter, crying, and yelling, which…
research note
The paper "APT-Agent — Automated Penetration Testing using Large Language Models" addresses key challenges in automating penetration testing (pen-testing) workflows with large language models (LLMs)
research note
The paper addresses the persistent problem of electricity theft in smart grids, a critical challenge affecting financial, operational, and security aspects of power distribution networks
research note
This paper addresses the challenge that Generative Artificial Intelligence (GenAI) poses to STEM educational assessments by undermining traditional validity assumptions
research note
This paper addresses the challenge of inducing expert-level, deep mechanistic reasoning in language models (LMs) within the specialized scientific domain of neuroscience
research note
Meta-Agent addresses the brittleness and error propagation challenges in existing multi-agent AI frameworks that arise as task workflows increase in scale and complexity
research note
This paper addresses the efficiency challenges faced by multimodal AI agents operating in web task environments, focusing on reducing the growing inference-time costs as agents accumulate experience
research note
This paper addresses the under-explored problem of transfer-based adversarial attacks in the textual domain, where attackers craft adversarial examples using surrogate ensemble models without query…
