Speculative decoding accelerates large language model inference through collaboration between a lightweight draft model and a target verifier. Existing methods mainly improve the draft side, while the target model is typically kept dense and unchanged. We show that, under domain-specific inference, full-depth target ve...
Hai-Bo Hu, Lian-Ming Huang, Qiao Li et al.· 0 citations
Inter-agent communication is essential to multi-agent language-model systems, yet a single message may combine task-critical information with instructions not authorized by the original request. Prompt-based defenses leave enforcement to models exposed to adversarial messages, while indiscriminate message removal disca...
Jinghan Xu, Longze Fan, Zeyuan Wang et al.· 0 citations
Context: Secondary studies are fundamental practices in Evidence- Based Software Engineering, but teaching them requires activities that expose students to authentic methodological decisions. Objective: This paper reports an experience in a graduate course in which ten doctoral students in Software Engineering, organiz...
CricRAG, a retrieval-augmented framework that aligns VLMs with skill-appropriate benchmarks for personalized cricket coaching, is presented, finding that by retrieving similar-but-better techniques as reference points, it can guide VLMs to provide developmentally appropriate feedback that mirrors human coaching practic...
Agamdeep Singh, PB Sujit, M. Vatsa· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Point cloud generation has emerged as a crucial task for accurately capturing and reproducing the complexity of the physical world. However, existing generative approaches, predominantly relying on Transformers and Variational Autoencoders (VAEs), frequently ignore the continuous, non-grid topologies inherent to 3D spa...
Ilias Mitsouras, Nikolaos Chaidos, Giorgos Stamou et al.· 0 citations
Explanations are central to causal reasoning, and cognitive science has long established that the human drive to explain is itself a mechanism for learning about causality. Despite this, learning from those abductive signals is largely ignored in artificial intelligence. While explainable AI (XAI) increasingly draws on...
Nicholas Tagliapietra, Florian Peter Busch, Moritz Willig et al.· 0 citations
Large audio-language models may mention acoustic events that are absent from the input. A separate audio event detector can verify these mentions, but doing so requires a second audio encoder and a separate forward pass. We propose Reused Encoder States for Verifying Events (REVE), a lightweight method that uses states...
Hong-Jin Song, Ji-Shen Kuang, Xin-Yu Yang et al.· 0 citations
This paper explores the relationship between cultural heritage institutions, Arts, Humanities&Social Sciences, and technology-led AI research and the impact of current technological advances in AI and proposes five key practices to form a framework for greater understanding across this divide.
Amber L. Cushing, Suzanne Little, Giulia Osti· 0 citations
We call the object this paper derives and certifies a minimal sufficient governance context: given a finite reachable-state model, a deterministic declared verdict, and candidate observable attributes, we compute sufficient observation sets, distinguish attributes that are individually indispensable from contracts that...
Monocular drone navigation requires reaching a goal in an unseen environment from a single forward-facing camera, which offers few cues for depth and scale. World models address this by modelling how observations evolve under actions, but they are built to be executed: the prediction is produced at deployment and fed b...
Yu-Hang Zhang, Rangya Zhang, Yu-Jing Shang et al.· 0 citations
A fully unpaired SE framework that uses principled Diffusion Schr\"odinger Bridges (DSB) to learn a stochastic transport process between a clean and a degraded speech distribution, offering a robust and efficient solution for real-world speech restoration.
A. Bagge, Andreas Nymand, M. R. Andersen et al.· 0 citations
This work studies training-free coupling of frozen TSFM marginals into multivariate forecast sample paths, finding the same pattern persists when the fixed-marginal constraint is removed and paths are sampled directly, and remains present under native multivariate backbone inference.
Jinmyeong Choi, Jin-Kwan Jang, Seul Lee et al.· 0 citations
With $2.1 million funding from Google.org, the open-source Public Transit Intelligence Hub will unify public transit monitoring, operations, and passenger communication.
Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.
