Related papers: Systematic Generalization on gSCAN: What is Nearly…
In this study, we use the existing Large Language Models ENnhanced to See Framework (LENS Framework) to test the feasibility of multimodal task-oriented dialogues. The LENS Framework has been proposed as a method to solve computer vision…
Fingerspelling in sign language has been the means of communicating technical terms and proper nouns when they do not have dedicated sign language gestures. Automatic recognition of fingerspelling can help resolve communication barriers…
Language is highly structured, with syntactic and semantic structures, to some extent, agreed upon by speakers of the same language. With implicit or explicit awareness of such structures, humans can learn and use language efficiently and…
The distributed data analytic system -- Spark is a common choice for processing massive volumes of heterogeneous data, while it is challenging to tune its parameters to achieve high performance. Recent studies try to employ auto-tuning…
GUI grounding is a critical component in building capable GUI agents. However, existing grounding benchmarks suffer from significant limitations: they either provide insufficient data volume and narrow domain coverage, or focus excessively…
When answering questions about an image, it not only needs knowing what -- understanding the fine-grained contents (e.g., objects, relationships) in the image, but also telling why -- reasoning over grounding visual cues to derive the…
Large AI models have been widely adopted in wireless communications for channel modeling, beamforming, and resource optimization. However, most existing efforts remain limited to single-modality inputs and channel-specific objec- tives,…
While the exploration for embodied AI has spanned multiple decades, it remains a persistent challenge to endow agents with human-level intelligence, including perception, learning, reasoning, decision-making, control, and generalization…
Instruction-tuned large language models (LLMs) have demonstrated promising zero-shot generalization capabilities across various downstream tasks. Recent research has introduced multimodal capabilities to LLMs by integrating independently…
Machine learning for robot manipulation promises to unlock generalization to novel tasks and environments. But how should we measure the progress of these policies towards generalization? Evaluating and quantifying generalization is the…
Humans can flexibly switch between different modes of thinking based on task complexity: from rapid intuitive judgments to in-depth analytical understanding. However, current Graphical User Interface (GUI) grounding systems which locate…
In Model Predictive Control (MPC), world models predict the future outcomes of various action proposals, which are then scored to guide the selection of the optimal action. For visuomotor MPC, the score function is a distance metric between…
Compared with previous 3D reconstruction methods like Nerf, recent Generalizable 3D Gaussian Splatting (G-3DGS) methods demonstrate impressive efficiency even in the sparse-view setting. However, the promising reconstruction performance of…
Visual grounding is a ubiquitous building block in many vision-language tasks and yet remains challenging due to large variations in visual and linguistic features of grounding entities, strong context effect and the resulting semantic…
Graph machine learning methods excel at leveraging pairwise relations present in the data. However, graphs are unable to fully capture the multi-way interactions inherent in many complex systems. An effective way to incorporate them is to…
A desirable trait of an artificial agent acting in the visual world is to continually learn a sequence of language-informed tasks while striking a balance between sufficiently specializing in each task and building a generalized knowledge…
In recent years, Graph Neural Networks (GNNs) have achieved remarkable success in many graph mining tasks. However, scaling them to large graphs is challenging due to the high computational and storage costs of repeated feature propagation…
Advances in machine learning technology have enabled real-time extraction of semantic information in signals which can revolutionize signal processing techniques and improve their performance significantly for the next generation of…
Evaluating Large Language Models (LLMs) has become increasingly important, with automatic evaluation benchmarks gaining prominence as alternatives to human evaluation. While existing research has focused on approximating model rankings,…
Large Language Models (LLMs) have delivered impressive results in language understanding, generation, reasoning, and pushes the ability boundary of multimodal models. Transformer models, as the foundation of modern LLMs, offer a strong…