相关论文: The Open Vault Challenge -- Learning how to build …
Traditional assessment methods collapse when students use generative AI to complete work without genuine engagement, creating an illusion of competence where they believe they're learning but aren't. This paper presents the conversational…
The rapid progress in AI and Robotics may lead to a profound societal transformation, as humans and robots begin to coexist within shared communities, introducing both opportunities and challenges. To explore this future, we present Virtual…
To unleash the full potential of AI for Science, we must untether the agents from a purely digital environment. The agent's ability to control and explore in real-world labs is essential because the physical lab remains foundational to…
System prompts have emerged as a critical control surface for specifying the behavior of LLMs in chat and agent settings. Developers depend on system prompts to specify important context, output format, personalities, guardrails, content…
The ISCSLP 2024 Conversational Voice Clone (CoVoC) Challenge aims to benchmark and advance zero-shot spontaneous style voice cloning, particularly focusing on generating spontaneous behaviors in conversational speech. The challenge…
IFTT-PIN is a self-calibrating version of the PIN-entry method introduced in Roth et al. (2004) [1]. In [1], digits are split into two sets and assigned a color respectively. To communicate their digit, users press the button with the same…
Fully functional program verification is an undecidable$\unicode{x2014}$and, hence, inherently difficult$\unicode{x2014}$task, that is not automatically solvable but typically requires user interaction and guidance. Existing verifiers…
With a vast domain of applications and now having quantum computing hardware available for commercial use, an education challenge arises in getting people of various background to become quantum literate. Quantum Odyssey is a new piece of…
CAPTCHAs have long been essential tools for protecting applications from automated bots. Initially designed as simple questions to distinguish humans from bots, they have become increasingly complex to keep pace with the proliferation of…
Programming education often assumes English proficiency and text-based interaction, creating barriers for students from multilingual regions such as India. We present CodeVaani, a multilingual speech-driven assistant for understanding code,…
Visual imitation learning provides a framework for learning complex manipulation behaviors by leveraging human demonstrations. However, current interfaces for imitation such as kinesthetic teaching or teleoperation prohibitively restrict…
Virtual Reality (VR) enables users to collaborate while exploring scenarios not realizable in the physical world. We propose CollabVR, a distributed multi-user collaboration environment, to explore how digital content improves expression…
Given the widespread use of procedural instructions with non-linear access (situational information retrieval), there has been a proposal to accommodate both linear and non-linear usage in instructional design. However, it has received…
Large language models (LLMs) have shown great potential in automating significant aspects of coding by producing natural code from informal natural language (NL) intent. However, when interacting with LLMs, users have no guarantees that the…
The widespread adoption of AI-assisted development tools in 2025 -- and the emergence of vibe coding, a practice of generating complete applications from natural language without verification -- exposed a critical and tool-agnostic failure…
To harness the potential of advanced computing technologies, efficient (real time) analysis of large amounts of data is as essential as are front-line simulations. In order to optimise this process, experts need to be supported by…
Traditional approaches in physics-based motion generation, centered around imitation learning and reward shaping, often struggle to adapt to new scenarios. To tackle this limitation, we propose AnySkill, a novel hierarchical method that…
Standard single-turn, static benchmarks fall short in evaluating the nuanced capabilities of Large Language Models (LLMs) on complex tasks such as software engineering. In this work, we propose a novel interactive evaluation framework that…
Customization has long been a central goal in interactive systems, yet prior work shows that end-user tailoring occurs infrequently and is often confined to initial setup or moments of breakdown. Recent advances in generative AI suggest…
This paper is preoccupied with the following question: given a (possibly opaque) learning system, how can we understand whether its behaviour adheres to governance constraints? The answer can be quite simple: we just need to "ask" the…