Related papers: S-MARC: Causal Streaming Reasoning for Full-Duplex…
The rapid growth of streaming video applications demands multimodal models with enhanced capabilities for temporal dynamics understanding and complex reasoning. However, current Video Question Answering (VideoQA) datasets suffer from two…
Training machines to understand natural language and interact with humans is one of the major goals of artificial intelligence. Recent years have witnessed an evolution from matching networks to pre-trained language models (PrLMs). In…
In high-conflict mixed-traffic scenarios involving human-driven and autonomous vehicles, most existing autonomous driving systems default to overly conservative behaviors, lack proactive interaction, and consequently suffer from limited…
Sequential modelling entails making sense of sequential data, which naturally occurs in a wide array of domains. One example is systems that interact with users, log user actions and behaviour, and make recommendations of items of potential…
Human perception of events is intrinsically tied to distinguishing between completed (perfect and telic) and ongoing (durative) actions, a process mediated by both linguistic structure and visual cues. In this work, we introduce the…
Recently, Large Language Models (LLMs) have demonstrated remarkable capabilities. Chain-of-Thought (CoT) has been proposed as a way of assisting LLMs in performing complex reasoning. However, developing effective prompts can be a…
Semantic communications could improve the transmission efficiency significantly by exploring the semantic information. In this paper, we make an effort to recover the transmitted speech signals in the semantic communication systems, which…
Several applications demand the timely detection of critical situations, such as threats to safety and transparency, over high-velocity streams of symbolic events. This demand has motivated the development of (i) event specification…
Recent text-to-video generation models have made remarkable progress in visual realism, motion fidelity, and text-video alignment, yet they still struggle to produce socially coherent behavior. Unlike humans, who readily infer intentions,…
Extracting real-time insights from multi-modal data streams from various domains such as healthcare, intelligent transportation, and satellite remote sensing remains a challenge. High computational demands and limited knowledge scope…
Throughout a conversation, the way participants interact with each other is in constant flux: their tones may change, they may resort to different strategies to convey their points, or they might alter their interaction patterns. An…
We propose communication pattern logic. A communication pattern describes how processes or agents inform each other, independently of the information content. The full-information protocol in distributed computing is the special case…
Language understanding (LU) and dialogue policy learning are two essential components in conversational systems. Human-human dialogues are not well-controlled and often random and unpredictable due to their own goals and speaking habits.…
Diffusion Transformers have demonstrated remarkable capabilities in visual synthesis, yet they often struggle with high-level semantic reasoning and long-horizon planning. This limitation frequently leads to visual hallucinations and…
Heterogeneous graph neural networks have become popular in various domains. However, their generalizability and interpretability are limited due to the discrepancy between their inherent inference flows and human reasoning logic or…
Emotion recognition is a crucial task for human conversation understanding. It becomes more challenging with the notion of multimodal data, e.g., language, voice, and facial expressions. As a typical solution, the global- and the local…
Latent visual reasoning aims to mimic human's imagination process by meditating through hidden states of Multimodal Large Language Models. While recognized as a promising paradigm for visual reasoning, the underlying mechanisms driving its…
Discourse signals are often implicit, leaving it up to the interpreter to draw the required inferences. At the same time, discourse is embedded in a social context, meaning that interpreters apply their own assumptions and beliefs when…
Online conversation understanding is an important yet challenging NLP problem which has many useful applications (e.g., hate speech detection). However, online conversations typically unfold over a series of posts and replies to those…
Recommendation dialogue systems aim to build social bonds with users and provide high-quality recommendations. This paper pushes forward towards a promising paradigm called target-driven recommendation dialogue systems, which is highly…