A robot following a multi-step instruction needs to act on the right objects in the right order, even as the scene changes. It must also maintain awareness of task progress and determine when to advance. To address these challenges, we introduce Orchestra, an agent harness that separates task planning and execution man...
You-Peng Wen, Gang Wang, Tian-Yu Huang et al.· 0 citations
Post-training quantisation reduces the memory cost of large language models, but it remains unclear whether compression preserves language skills of regional varieties as reliably as their standard-language counterparts. We study this question for Bavarian, Standard German, and English using BAVGROUND, a multiple-choic...
Jophin John, Michael Hoffmann, Piroska Lendvai et al.· 0 citations
Virtual footwear try-on (VFTON), a critical yet underexplored area in virtual try-on (VTON), aims to synthesize faithful try-on results given diverse footwear and model images while maintaining 3D consistency and texture authenticity. Unlike conventional garment-focused VTON methods, VFTON presents unique challenges du...
Yuhan Li, Zhiyu Jin, Yifan Tong et al.· 0 citations
Conversational Recommender Systems (CRSs) require reliable user simulators for cost-effective evaluation. LLM-based simulators have made realistic simulation possible but typically condition on profiles derived from explicit ratings, demographics, and static sources capturing surface preferences while omitting implicit...
Erfan Shahabi, Amirhossein Roshandel, Mohammad Sadegh Sadeghi et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
The world encompasses both physical environments and human actors. Predicting its evolution requires understanding both physical laws and how emotions shape human actions. However, existing world model benchmarks primarily assess physical plausibility and perceptual quality, leaving emotion-driven world evolution large...
Changhao Song, Yacong Chen, Hui Gao et al.· 0 citations
Releasing a neural network checkpoint can leak information about its training data, and existing reconstruction results rely on gradient-descent training. We ask whether the choice of optimizer affects the ability to recover the training data. Extending work connecting Karush--Kuhn--Tucker conditions to training-data r...
Autonomous research agents must acquire and reason over evidence within a limited budget. Yet relevant sources can remain uninspected or unused, leaving a gap between retrieval coverage and the evidence that informs research. The challenge is to align fast local judgments with changing evidence needs and feed their fin...
Ya-Sheng Sun, Yan Dai, Yi-Meng Chen et al.· 0 citations
This work evaluates Caesar and layered variants across eight models and 139 injection-task pairs, separating instruction recovery from attack success, and highlights the risk of promoting decoded, untrusted content into actionable instructions.
Wearable fall detection is hampered by rare fall events, scarce labeled IMU data, and the cost of training deep models on large, imbalanced corpora. Existing methods either rely on hand-crafted features with shallow classifiers, which limits learning from raw signals, or train deep networks on full datasets that requir...
Given the growing global burden of liver tumors and diffuse liver diseases, non-contrast computed tomography (NCCT) is increasingly used for opportunistic screening because of its low cost and favorable safety profile. However, downstream tasks such as tumor detection and fine-grained disease diagnosis remain challengi...
Vision-language models (VLMs) have been widely adopted for document parsing and optical character recognition (OCR), as they can accurately extract page-level elements. However, downstream applications such as retrieval-augmented generation (RAG) also require coherent document-level structure. Although these models ind...
Qian Chen, Xianyin Zhang, Lifan Guo et al.· 0 citations
While AI agents are useful for many tasks, they regularly misbehave in destructive ways, such as deleting important data. While prior work has focused on preventing such misbehavior, we consider how to recover after an agent misbehaves. We propose verifiable agent insurance (VAI), a framework for agent providers to com...
Hua Cheng, Taro Tsuchiya, Nicolas Christin et al.· 0 citations
