相关论文: Dr-CiK: A Testbed for Foresight-Driven Agents
Predicting the behavior of surrounding traffic participants is crucial for advanced driver assistance systems and autonomous driving. Most researchers however do not consider contextual knowledge when predicting vehicle motion. Extending…
We study the role of linguistic context in predicting quantifiers (`few', `all'). We collect crowdsourced data from human participants and test various models in a local (single-sentence) and a global context (multi-sentence) condition.…
To answer a question, language models often need to integrate prior knowledge learned during pretraining and new information presented in context. We hypothesize that models perform this integration in a predictable way across different…
Building effective clinical decision support systems requires the synthesis of complex heterogeneous multimodal data. Such modalities include temporal electronic health records data, medical images, radiology reports, and clinical notes.…
Context is an important factor in computer vision as it offers valuable information to clarify and analyze visual data. Utilizing the contextual information inherent in an image or a video can improve the precision and effectiveness of…
Trajectory forecasting is a widely-studied problem for autonomous navigation. However, existing benchmarks evaluate forecasting based on independent snapshots of trajectories, which are not representative of real-world applications that…
The importance of time series forecasting drives continuous research and the development of new approaches to tackle this problem. Typically, these methods are introduced through empirical studies that frequently claim superior accuracy for…
Future wireless networks demand increasingly powerful intelligence to support sensing, communication, and autonomous decision-making. While scaling laws suggest improving performance by enlarging model capacity, practical edge deployments…
Long-context inference remains challenging for large language models due to attention dilution and out-of-distribution degradation. Context selection mitigates this limitation by attending to a subset of key-value cache entries, yet most…
Trajectory anomaly detection is crucial for effective decision-making in urban and human mobility management. Existing methods of trajectory anomaly detection generally focus on training a trajectory generative model and evaluating the…
It is widely acknowledged by researchers and practitioners that software development methodologies are generally adapted to suit specific project contexts. Research into practices-as-implemented has been fragmented and has tended to focus…
Extending LLM context windows is hindered by scarce high-quality long-context data. Recent methods synthesize data with genuine long-range dependencies via information-theoretic verification, selecting contexts that reduce a base model's…
Motion forecasting for agents in autonomous driving is highly challenging due to the numerous possibilities for each agent's next action and their complex interactions in space and time. In real applications, motion forecasting takes place…
Understanding toxicity in user conversations is undoubtedly an important problem. Addressing "covert" or implicit cases of toxicity is particularly hard and requires context. Very few previous studies have analysed the influence of…
Clinical Decision Support Systems (CDSSs) provide reasoning and inquiry guidance for physicians, yet they face notable challenges, including high maintenance costs and low generalization capability. Recently, Large Language Models (LLMs)…
Chunk-based inference stands out as a popular approach in developing real-time streaming speech recognition, valued for its simplicity and efficiency. However, because it restricts the model's focus to only the history and current chunk…
Multi-agent LLM orchestration systems suffer from context pollution: when N concurrent agents compete for the orchestrator's context window, each agent's task state, partial outputs, and pending questions contaminate the steering…
Modern clinical decision support systems can concurrently serve multiple, independent medical imaging institutions, but their predictive performance may degrade across sites due to variations in patient populations, imaging hardware, and…
Last-mile delivery systems commonly propose the use of autonomous robotic vehicles to increase scalability and efficiency. The economic inefficiency of collecting accurate prior maps for navigation motivates the use of planning algorithms…
Individual agents in multi-agent (MA) systems often lack robustness, tending to blindly conform to misleading peers. We show this weakness stems from both sycophancy and inadequate ability to evaluate peer reliability. To address this, we…