research note
This paper addresses the challenge of modeling view-dependent appearance in novel-view synthesis and radiance reconstruction, where capturing complex angular effects such as specularities typically…
research note
The paper addresses the growing complexity and fragility in modifying large neural network checkpoints, which increasingly hampers research workflows such as model merging, LoRA factorization, prun…
research note
This paper addresses a fundamental limitation of behavior cloning (BC) in imitation learning — poor generalization and instability when encountering out-of-distribution (OOD) states due to compoundi…
research note
This paper addresses the problem of unsupervised disentangled representation learning by proposing a novel approach that leverages holographic reduced representations (HRRs), a type of vector symbo…
research note
Analyzing the second EPTA data release's new timing measurements for 25 millisecond pulsars over 10.3 years, the authors identify two regimes in reheating temperature — a low Trh (<1 GeV) regime wit…
research note
This paper addresses a critical limitation in current large language models (LLMs) for open-ended long-form text generation, a difficulty known as "Length Collapse" where generation quality and len…
research note
This paper addresses the challenge of circumventing exponentially closing spectral gaps that limit the runtime efficiency of conventional adiabatic quantum annealing (QA) for optimization problems
research note
This paper develops a rigorous theoretical connection between finite-player $\alpha$-potential games and potential mean field games (MFGs) as the number of players $N$ tends to infinity
research note
This study targets the problem of automated exploration and generation of novel and diverse synthetic sounds for composers and sound designers, overcoming technical skill barriers and enabling sere…
research note
This paper introduces SUPERBROWSER, an autonomous web-navigation agent explicitly designed to mimic human browsing cognition rather than merely accumulating all observations in large prompt context…
research note
This paper presents enhancements to the FOOTPASS baselines for player-centric ball-action spotting in broadcast soccer video, as part of the SoccerNet 2026 challenge
research note
WeaveBench addresses a critical gap in evaluating computer-use agents (CUAs) that must orchestrate complex workflows involving both graphical user interfaces (GUIs) and command-line/code interface …
