Related papers: FlowSeg: Dynamic Semantic Guidance for LLM-Conditi…

Dialogue topic segmentation supports summarization, retrieval, memory management, and conversational continuity. Despite decades of work, evaluation practice remains dominated by strict boundary matching and F1-based metrics. Modern large…

Multimodal Large Language Models (MLLMs) have demonstrated strong image-level visual understanding and reasoning, yet their pixel-level perception across both images and videos remains limited. Foundation segmentation models such as the SAM…

Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated significant potential in recommendation systems. However, the effective application of MLLMs to multimodal sequential recommendation remains unexplored: A)…

Semantic segmentation is an important task for numerous applications but it is still quite challenging to achieve advanced performance with limited computational costs. In this paper, we present CGRSeg, an efficient yet competitive…

Self-attention is of vital importance in semantic segmentation as it enables modeling of long-range context, which translates into improved performance. We argue that it is equally important to model short-range context, especially to…

Joint multilingual instruction tuning is a widely adopted approach to improve the multilingual instruction-following ability and downstream performance of large language models (LLMs), but the resulting multilingual capability remains…

Sequential Recommenders generate recommendations based on users' historical interaction sequences. However, in practice, these collected sequences are often contaminated by noisy interactions, which significantly impairs recommendation…

We tackle the challenge of open-vocabulary segmentation, where we need to identify objects from a wide range of categories in different environments, using text prompts as our input. To overcome this challenge, existing methods often use…

Recent advances in Large Language Models (LLMs) have shifted in recommendation systems from the discriminative paradigm to the LLM-based generative paradigm, where the recommender autoregressively generates sequences of semantic identifiers…

Self-conditioning has been central to the success of continuous diffusion language models, as it allows models to correct previous errors. Yet its ability degrades precisely in the regime where diffusion is most attractive for deployment:…

Strong semantic representations improve the convergence and generation quality of diffusion and flow models. Existing approaches largely rely on external models, which require separate training, operate on misaligned objectives, and exhibit…

Multimodal Large Language Models (MLLMs) have made remarkable progress in multimodal perception and reasoning by bridging vision and language. However, most existing MLLMs perform reasoning primarily with textual CoT, which limits their…

Ambiguous words are often found in modern digital communications. Lexical ambiguity challenges traditional Word Sense Disambiguation (WSD) methods, due to limited data. Consequently, the efficiency of translation, information retrieval, and…

Large language models (LLMs) have made remarkable strides in complex reasoning tasks, but their safety and robustness in reasoning processes remain underexplored. Existing attacks on LLM reasoning are constrained by specific settings or…

Understanding human intents from multimodal signals is critical for analyzing human behaviors and enhancing human-machine interactions in real-world scenarios. However, existing methods exhibit limitations in their modality-level reliance,…

Large language models (LLMs) are increasingly applied to sequential decision-making through in-context learning (ICL), yet their effectiveness is highly sensitive to prompt quality. Effective prompts should meet three principles: focus on…

Large Language Models (LLMs) are increasingly deployed to automatically label and analyze educational dialogue at scale, yet current pipelines lack reliable ways to detect when models are wrong. We investigate whether reasoning generated by…

Referring remote sensing image segmentation is crucial for achieving fine-grained visual understanding through free-format textual input, enabling enhanced scene and object extraction in remote sensing applications. Current research…

Vision-Language Models (VLMs) have recently shown promising advancements in sequential decision-making tasks through task-specific fine-tuning. However, common fine-tuning methods, such as Supervised Fine-Tuning (SFT) and Reinforcement…

Continual semantic segmentation aims to learn new classes while maintaining the information from the previous classes. Although prior studies have shown impressive progress in recent years, the fairness concern in the continual semantic…