18 accepted papers
Streaming dense video captioning requires real-time processing of continuous visual input while determining precisely when and what to caption. Current approaches primarily focus on designing complex external memory mechanisms, failing to leverage Large Multimodal Models' (LMMs) inherent long-contex
Text-guided human body animation has advanced rapidly, yet facial animation lags due to the scarcity of well-annotated, text-paired facial corpora. To close this gap, we leverage foundation generative models to synthesize a large, balanced corpus of facial behavior. We design prompts suite covering
In this work, we introduce CAT-V (Caption Anything in Video), a training-free framework for fine-grained object-centric video captioning of user-selected instances. CAT-V combines (i) a SAMURAI-based Segmenter for precise object masks across frames, (ii) a TRACE-Uni Temporal Analyzer for event bound
Vision–language models (VLMs) now support both direct Instruct and explicit-reasoning Thinking modes, but practitioners lack principled ways to decide when reasoning helps or how much computation to allocate at test time. We investigate whether VLMs encode meta-cognitive signals for adaptive inferen…
While neural PDE solvers have demonstrated significant potential for accelerating engineering simulations, existing architectures remain constrained by high memory consumption and the "single-node bottleneck," where the maximum processable mesh resolution is strictly limited by the VRAM of a single …
Test-time "thinking" (i.e., generating explicit intermediate reasoning chains) is known to boost performance in large language models and has recently shown strong gains for large vision-language models (LVLMs). However, despite these promising results, there is still no systematic analysis of how t
Large language models (LLMs) have demonstrated remarkable capabilities in natural language and multimodal domains. By fine-tuning multimodal LLMs with temporal annotations from well-annotated datasets, e.g., dense video captioning datasets, their temporal understanding capacity in video-language tas…
Large language models (LLMs) have demonstrated remarkable performance across a wide range of tasks. Advances in prompt engineering and fine-tuning techniques have further enhanced their ability to address complex reasoning challenges. However, these advanced capabilities are often exclusive to model…
Understanding perspective is fundamental to human visual perception, yet the extent to which multimodal large language models (MLLMs) internalize perspective geometry remains unclear. We introduce MMPerspective, the first benchmark specifically designed to systematically evaluate MLLMs' understandin…
Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated remarkable progress in visual understanding. This impressive leap raises a compelling question: how can language models, initially trained solely on linguistic data, effectively interpret and process visual content? Th…
The advancement of Multimodal Large Language Models (MLLMs) has enabled significant progress in multimodal understanding, expanding their capacity to analyze video content. However, existing evaluation benchmarks for MLLMs primarily focus on abstract video comprehension, lacking a detailed assessmen…
Audio source separation is fundamental for machines to understand complex acoustic environments and underpins numerous audio applications. Current supervised deep learning approaches, while powerful, are limited by the need for extensive, task-specific labeled data and struggle to generalize to the…
The capability of intelligent models to extrapolate and comprehend changes in object states is a crucial yet demanding aspect of AI research, particularly through the lens of human interaction in real-world settings. This task involves describing complex visual environments, identifying active objec…
High-dimensional expensive problems are often encountered in the design and optimization of complex robotic and automated systems and distributed computing systems, and they suffer from a time-consuming fitness evaluation process. It is extremely challenging and difficult to produce promising soluti…
Evolutionary algorithms are commonly used to solve many complex optimization problems in such fields as robotics, industrial automation, and complex system design. Yet, their performance is limited when dealing with high-dimensional complex problems because they often require enormous computational…
Real-time and precise prediction for traffic of networks is critically important for allocating the optimal computing/network resources based on users' business requirements, analyzing the network performance, and realizing intelligent congestion control and high-accuracy anomaly detection. The dram…
Learning new skills by observing humans' behaviors is an essential capability of AI. In this work, we leverage instructional videos to study humans' decision-making processes, focusing on learning a model to plan goal-directed actions in real-life videos. In contrast to conventional action recogniti…
Cloud services have rapidly grown in cloud data centers (CDCs). Accurate workload prediction benefits CDCs since appropriate resource provisioning can be performed for their providers to ensure the full satisfaction of service-level agreement (SLA) requirements from users. Yet these providers face s