research note
This paper addresses the challenge of robotic imitation learning under partial observability caused by occlusion, where robots must not only execute actions but also actively choose informative vie…
research note
Lift4D addresses the challenge of reconstructing dynamic, non-rigid 4D (3D + time) representations of unknown objects from monocular in-the-wild videos, where data is scarce and occlusions plus lar…
research note
This paper investigates the underexplored question of how prompt optimization, a technique well-established for single LLMs, transfers to multi-agent systems (MAS) composed of multiple LLM-based ag…
research note
This paper addresses the challenging task of estimating 6D poses of unseen objects in open-world settings without relying on CAD models or heavy onboarding
research note
This paper addresses inefficiencies and security limitations of classical proof-of-work (PoW) blockchains, which consume vast energy producing hash puzzles with no external utility and face emergin…
research note
This paper addresses the challenge of length generalization in large language models (LLMs), where models pretrained on short sequences struggle to generalize to much longer context lengths during …
research note
This paper addresses the inefficiencies of passive imitation learning for fine-tuning Vision-Language-Action (VLA) models, where additional demonstrations are collected only after policy failures, …
research note
Variational Monte Carlo (VMC) methods are widely used to simulate quantum many-body dynamics, but real-time evolution following a local quench by a charged operator suffers from a severe ‘‘support …
research note
This paper addresses the difficult problem of solving bit manipulation puzzles, where an AI must deduce a hidden logical bitwise transformation rule from a small number of input-output binary examp…
research note
This paper addresses a core challenge in text-driven video editing — preserving original video content outside of the edited regions
research note
This paper addresses the challenge of scaling high-quality pretest question generation and evaluation using large language models (LLMs)
research note
This paper investigates why a large, continuously passing automated test suite failed to prevent production defects in a modern web application integrating large language models (LLMs), multi-marke…
