Related papers: Skill-Evolving Grounded Reasoning for Free-Text Pr…

Vision-language foundation models have exhibited remarkable success across a multitude of downstream tasks due to their scalability on extensive image-text paired data. However, these models also display significant limitations when applied…

Large Language Models (LLMs) have demonstrated powerful reasoning capabilities through Chain-of-Thought (CoT) in various tasks, yet the inefficiency of token-by-token generation hinders real-world deployment in latency-sensitive recommender…

Accurate and robust tracking and reconstruction of the surgical scene is a critical enabling technology toward autonomous robotic surgery. Existing algorithms for 3D perception in surgery mainly rely on geometric information, while we…

Detecting machine-generated text (MGT) has emerged as a critical challenge, driven by the rapid advancement of large language models (LLMs) capable of producing highly realistic, human-like content. However, the performance of current…

Although automatic emotion recognition (AER) has recently drawn significant research interest, most current AER studies use manually segmented utterances, which are usually unavailable for dialogue systems. This paper proposes integrating…

Deep neural networks are vulnerable to adversarial perturbations, limiting deployment in safety-critical applications such as synthetic aperture radar (SAR) automatic target recognition (ATR). Randomized smoothing improves robustness by…

Existing image editing methods can handle simple editing instructions very well. To deal with complex editing instructions, they often need to jointly fine-tune the large language models (LLMs) and diffusion models (DMs), which involves…

Many recent studies have focused on fine-tuning pre-trained models for speech emotion recognition (SER), resulting in promising performance compared to traditional methods that rely largely on low-level, knowledge-inspired acoustic…

Retrieval-Augmented Generation (RAG) is widely employed to mitigate risks such as hallucinations and knowledge obsolescence in medical question answering, yet its predominantly single-round, static retrieval paradigm misaligns with the…

This paper describes a new approach and a system SCREEN for fault-tolerant speech parsing. SCREEEN stands for Symbolic Connectionist Robust EnterprisE for Natural language. Speech parsing describes the syntactic and semantic analysis of…

Large language models (LLMs) have significantly improved their reasoning capabilities; however, they still struggle with complex multi-step mathematical problem-solving due to error propagation, lack of self-correction, and limited…

Large Language Models (LLMs) demonstrate remarkable emergent abilities across various tasks, yet fall short of complex reasoning and planning tasks. The tree-search-based reasoning methods address this by surpassing the capabilities of…

We present SEED, an elaborate image tokenizer that empowers Large Language Models (LLMs) with the emergent ability to SEE and Draw at the same time. Research on image tokenizers has previously reached an impasse, as frameworks employing…

Automatic speech recognition (ASR) is a core component of human--computer interaction and an increasingly important front-end for LLM-based assistants and agents. However, most current ASR systems still follow a single-pass paradigm, which…

In modern machine learning, the trend of harnessing self-supervised learning to derive high-quality representations without label dependency has garnered significant attention. However, the absence of label information, coupled with the…

Medical language models face critical barriers to real-world clinical reasoning applications. However, mainstream efforts, which fall short in task coverage, lack fine-grained supervision for intermediate reasoning steps, and rely on…

The current advances in generative AI for learning large neural network models with the capability to produce essays, images, music and even 3D assets from text prompts create opportunities for a manifold of disciplines. In the present…

The Segment Anything Model (SAM) has recently emerged as a groundbreaking foundation model for prompt-driven image segmentation tasks. However, both the original SAM and its medical variants require slice-by-slice manual prompting of target…

Image registration is an ill-posed dense vision task, where multiple solutions achieve similar loss values, motivating probabilistic inference. Variational inference has previously been employed to capture these distributions, however…

Open-vocabulary semantic segmentation strives to distinguish pixels into different semantic groups from an open set of categories. Most existing methods explore utilizing pre-trained vision-language models, in which the key is to adopt the…