Related papers: CoSteer: Collaborative Decoding-Time Personalizati…
Recent deep network-based compressive sensing (CS) methods have achieved great success. However, most of them regard different sampling matrices as different independent tasks and need to train a specific model for each target sampling…
Emerging advanced control applications, with increased complexity in software but limited computing resources, suggest that real-time controllers should have adaptable designs. These control strategies also should be designed with…
Contextual Partitioning introduces an innovative approach to enhancing the architectural design of large-scale computational models through the dynamic segmentation of parameters into context-aware regions. This methodology emphasizes the…
Listening head generation aims to synthesize a non-verbal responsive listener head by modeling the correlation between the speaker and the listener in dynamic conversion.The applications of listener agent generation in virtual interaction…
Customizing pre-trained text-to-image generation model has attracted massive research interest recently, due to its huge potential in real-world applications. Although existing methods are able to generate creative content for a novel…
To automatically tune configurations for the best possible system performance (e.g., runtime or throughput), much work has been focused on designing intelligent heuristics in a tuner. However, existing tuner designs have mostly ignored the…
Inference-time intervention (ITI) has emerged as a promising method for steering large language model (LLM) behavior in a particular direction (e.g., improving helpfulness) by intervening on token representations without costly updates to…
Efficiently modeling spatio-temporal (ST) physical processes and observations presents a challenging problem for the deep learning community. Many recent studies have concentrated on meticulously reconciling various advantages, leading to…
Large Language Models have revolutionized code generation ability by converting natural language descriptions into executable code. However, generating complex code within real-world scenarios remains challenging due to intricate…
Parameter-efficient fine-tuning methods, such as LoRA, offer a practical way to adapt large vision and language models to client tasks. However, this becomes particularly challenging under task-level heterogeneity in federated deployments.…
Spatial synchronization in roadside scenarios is essential for integrating data from multiple sensors at different locations. Current methods using cascading spatial transformation (CST) often lead to cumulative errors in large-scale…
Concept personalization methods enable large text-to-image models to learn specific subjects (e.g., objects/poses/3D models) and synthesize renditions in new contexts. Given that the image references are highly biased towards visual…
Decentralized optimization enables multiple devices to learn a global machine learning model while each individual device only has access to its local dataset. By avoiding the need for training data to leave individual users' devices, it…
Recent cross-domain recommendation (CDR) studies assume that disentangled domain-shared and domain-specific user representations can mitigate domain gaps and facilitate effective knowledge transfer. However, achieving perfect…
Unlike static documents, version controlled documents are continuously edited by one or more authors. Such collaborative revision process makes traditional modeling and visualization techniques inappropriate. In this paper we propose a new…
Sparse Autoencoders (SAEs) can extract interpretable features from large language models (LLMs) without supervision. However, their effectiveness in downstream steering tasks is limited by the requirement for contrastive datasets or large…
The complexity of the real world demands robotic systems that can intelligently adapt to unseen situations. We present STEER, a robot learning framework that bridges high-level, commonsense reasoning with precise, flexible low-level…
Today's densely instrumented world offers tremendous opportunities for continuous acquisition and analysis of multimodal sensor data providing temporal characterization of an individual's behaviors. Is it possible to efficiently couple such…
Model merging has emerged as a promising paradigm for enabling multi-task capabilities without additional training. However, existing methods often experience substantial performance degradation compared with individually fine-tuned models,…
Personalized learning is a proposed approach to address the problem of data heterogeneity in collaborative machine learning. In a decentralized setting, the two main challenges of personalization are client clustering and data privacy. In…