Related papers: Learning to Approximate: Auto Direction Vector Set…

Vision encoders typically generate a large number of visual tokens, providing information-rich representations but significantly increasing computational demands. This raises the question of whether all generated tokens are equally valuable…

Chart-to-code generation is a critical task in automated data visualization, translating complex chart structures into executable programs. While recent Multi-modal Large Language Models (MLLMs) improve chart representation, existing…

Currently, inspired by the success of vision-language models (VLMs), an increasing number of researchers are focusing on improving VLMs and have achieved promising results. However, most existing methods concentrate on optimizing the…

Long-horizon robotic manipulation remains challenging for Vision-Language-Action (VLA) models despite recent progress in zero-shot generalization and simulation-to-real-world transfer. Current VLA models suffer from stage hallucination,…

Parameter efficient fine tuning methods like LoRA have enabled task specific adaptation of large language models, but efficiently composing multiple specialized adapters for unseen tasks remains challenging. We present a novel framework for…

Fast gradient-based optimization algorithms have become increasingly essential for the computationally efficient training of machine learning models. One technique is to multiply the gradient by a preconditioner matrix to produce a step,…

In computational reinforcement learning, the default representation (DR) and its principal eigenvector have been shown to be effective for a wide variety of applications, including reward shaping, count-based exploration, option discovery,…

Self-supervision has emerged as a propitious method for visual representation learning after the recent paradigm shift from handcrafted pretext tasks to instance-similarity based approaches. Most state-of-the-art methods enforce similarity…

Hyperdimensional computing (HDC), also known as vector symbolic architectures (VSA), is a computing framework used within artificial intelligence and cognitive computing that operates with distributed vector representations of large fixed…

Low-rank adapation (LoRA) is a popular method that reduces the number of trainable parameters when finetuning large language models, but still faces acute storage challenges when scaling to even larger models or deploying numerous per-user…

Understanding visual inputs for a given task amidst varied changes is a key challenge posed by visual reinforcement learning agents. We propose \textit{Value Explicit Pretraining} (VEP), a method that learns generalizable representations…

Conventional end-to-end (E2E) driving models are effective at generating physically plausible trajectories, but often fail to generalize to long-tail scenarios due to the lack of essential world knowledge to understand and reason about…

We present \textbf{Met}a-\textbf{T}oken \textbf{Le}arning (Mettle), a simple and memory-efficient method for adapting large-scale pretrained transformer models to downstream audio-visual tasks. Instead of sequentially modifying the output…

Data representation in non-Euclidean spaces has proven effective for capturing hierarchical and complex relationships in real-world datasets. Hyperbolic spaces, in particular, provide efficient embeddings for hierarchical structures. This…

Prompt learning has become a prevalent strategy for adapting vision-language foundation models (VLMs) such as CLIP to downstream tasks. With the emergence of large language models (LLMs), recent studies have explored the potential of using…

Most existing vision-language-action (VLA) models for robotic manipulation lack progress awareness, typically relying on hand-crafted heuristics for task termination. This limitation is particularly severe in long-horizon tasks involving…

This paper investigates a turbo receiver employing a variational quantum circuit (VQC). The VQC is configured with an ansatz of the quantum approximate optimization algorithm (QAOA). We propose a 'learning to learn' (L2L) framework to…

In Recommender systems, data representation techniques play a great role as they have the power to entangle, hide and reveal explanatory factors embedded within datasets. Hence, they influence the quality of recommendations. Specifically,…

Learning useful representations of complex data has been the subject of extensive research for many years. With the diffusion of Deep Neural Networks, Variational Autoencoders have gained lots of attention since they provide an explicit…

Direction of Arrival (DoA) estimation techniques face a critical trade-off, as classical methods often lack accuracy in challenging, low signal-to-noise ratio (SNR) conditions, while modern deep learning approaches are too energy-intensive…