Related papers: Can Language Beat Numerical Regression? Language-B…

A new trend in the computer vision community is to capture objects of interest following flexible human command represented by a natural language prompt. However, the progress of using language prompts in driving scenarios is stuck in a…

Large Reasoning Models (LRMs) still exhibit large performance gaps between English and other languages, yet much current work assumes these gaps can be closed simply by making reasoning in every language resemble English reasoning. This…

Vision-Language MOT is a crucial tracking problem and has drawn increasing attention recently. It aims to track objects based on human language commands, replacing the traditional use of templates or pre-set information from training sets…

Multimodal large language models (MLLMs) have shown satisfactory effects in many autonomous driving tasks. In this paper, MLLMs are utilized to solve joint semantic scene understanding and risk localization tasks, while only relying on…

Compared to traditional sentiment analysis, which only considers text, multimodal sentiment analysis needs to consider emotional signals from multimodal sources simultaneously and is therefore more consistent with the way how humans process…

Reasoning over sequences of images remains a challenge for multimodal large language models (MLLMs). While recent models incorporate multi-image data during pre-training, they still struggle to recognize sequential structures, often…

Multispectral pedestrian detection is a crucial component in various critical applications. However, a significant challenge arises due to the misalignment between these modalities, particularly under real-world conditions where data often…

Time series forecasting traditionally relies on unimodal numerical inputs, which often struggle to capture high-level semantic patterns due to their dense and unstructured nature. While recent approaches have explored representing time…

Forecasting conversation derailment can be useful in real-world settings such as online content moderation, conflict resolution, and business negotiations. However, despite language models' success at identifying offensive speech present in…

We introduce iMotion-LLM, a large language model (LLM) integrated with trajectory prediction modules for interactive motion generation. Unlike conventional approaches, it generates feasible, safety-aligned trajectories based on textual…

Multimodal Large Language Models (MLLMs) show promise for image-based regression tasks, but current approaches face key limitations. Recent methods fine-tune MLLMs using preset output vocabularies and generic task-level prompts (e.g., "How…

Direction reasoning is essential for intelligent systems to understand the real world. While existing work focuses primarily on spatial reasoning, compass direction reasoning remains underexplored. To address this, we propose the Compass…

Evaluating autonomous vehicles with controllability enables scalable testing in counterfactual or structured settings, enhancing both efficiency and safety. We introduce LangTraj, a language-conditioned scene-diffusion model that simulates…

Transformer-based language models (LMs) continue to achieve state-of-the-art performance on natural language processing (NLP) benchmarks, including tasks designed to mimic human-inspired "commonsense" competencies. To better understand the…

Multimodal large language models (MLLMs) have shown great potential in perception and interpretation tasks, but their capabilities in predictive reasoning remain under-explored. To address this gap, we introduce a novel benchmark that…

Multimodal recommendation combines the user historical behaviors with the modal features of items to capture the tangible user preferences, presenting superior performance compared to the conventional ID-based recommender systems. However,…

Particularly in low-data regimes, an outstanding challenge in machine learning is developing principled techniques for augmenting our models with suitable priors. This is to encourage them to learn in ways that are compatible with our…

Understanding natural-language references to objects in dynamic 3D driving scenes is essential for interactive autonomous systems. In practice, many referring expressions describe targets through recent motion or short-term interactions,…

Navigating robots through unstructured terrains is challenging, primarily due to the dynamic environmental changes. While humans adeptly navigate such terrains by using context from their observations, creating a similar context-aware…

Mobility Foundation Models (MFMs) have advanced the modeling of human movement patterns, yet they face a ceiling due to limitations in data scale and semantic understanding. While Large Language Models (LLMs) offer powerful semantic…