Related papers: Persistent Contextual Values as Inter-Process Laye…
MetaML-style metaprogramming languages allow programmers to construct, manipulate and run code. In the presence of higher-order references for code, ensuring type safety is challenging, as free variables can escape their binders. In this…
Generalisation in machine learning often relies on the ability to encode structures present in data into an inductive bias of the model class. To understand the power of quantum machine learning, it is therefore crucial to identify the…
We focus on control constructs that allow programmers define actions to be performed when respective conditions are met without requiring the explicit evaluation and testing of conditions as part of an imperative algorithm. Such elements…
Analysis tools like abstract interpreters, symbolic execution tools and testing tools usually require a proper context to give useful results when analyzing a particular function. Such a context initializes the function parameters and…
Threads and events are two common abstractions for writing concurrent programs. Because threads are often more convenient, but events more efficient, it is natural to want to translate the former into the latter. However, whereas there are…
Efficient long-context LLM deployment is stalled by a dichotomy between amortized compression, which struggles with out-of-distribution generalization, and Test-Time Training, which incurs prohibitive synthetic data costs and requires…
Context awareness is an important enabler for next generation of Mobile Core Networks (MCN). However there exist a number of challenges in this regard. For example how to develop a framework which 1) is able to generate context richer than…
Large language models (LLMs) call for extension of context to handle many critical applications. However, the existing approaches are prone to expensive costs and inferior quality of context extension. In this work, we propose Extensible…
Architecture Decision Records (ADRs) play a critical role in preserving the rationale behind system design, yet their creation and maintenance are often neglected due to the associated authoring overhead. This paper investigates whether…
As a result of the phenomenal proliferation of modern mobile Internet-enabled devices and the widespread utilization of wireless and cellular data networks, mobile users are increasingly requiring services tailored to their current context.…
Large language models (LLMs) have achieved remarkable success across various domains, but effectively incorporating complex and potentially noisy user timeline data into LLMs remains a challenge. Current approaches often involve translating…
Pervasive applications are involving more and more autonomous computing and communicating devices, augmented with the abilities of sensing and controlling the logical / physical environment. To enable context-awareness for such…
App usage prediction is important for smartphone system optimization to enhance user experience. Existing modeling approaches utilize historical app usage logs along with a wide range of semantic information to predict the app usage;…
Recent advances in interactive video generation have shown promising results, yet existing approaches struggle with scene-consistent memory capabilities in long video generation due to limited use of historical context. In this work, we…
Context-aware neural machine translation aims to use the document-level context to improve translation quality. However, not all words in the context are helpful. The irrelevant or trivial words may bring some noise and distract the model…
Context awareness is an essential part of mobile and ubiquitous computing. Its goal is to unveil situational information about mobile users like locations and activities. The sensed context can enable many services like navigation, AR, and…
Computational agents support humans in many areas of life and are therefore found in heterogeneous contexts. This means they operate in rapidly changing environments and can be confronted with huge state and action spaces. In order to…
Embodied agents need to plan and act reliably in real and complex 3D environments. Classical planning (e.g., PDDL) offers structure and guarantees, but in practice it fails under noisy perception and incorrect predicate grounding. On the…
Deploying useful Long-Context Transformer Models (LCTMs) requires addressing two key challenges: (1) A growing memory footprint due to quadratic self-attention and linear KV-cache scaling in memory as sequence length increases; (2) the…
Decoder-only large language models (LLMs) have been increasingly adopted to build embedding models for diverse tasks. To overcome the inherent limitations of causal attention in representation learning, many existing methods modify the…