21 accepted papers
Vision language action models (VLAs) are increasingly used for Physical AI, but deploying a pre-trained VLA model to unseen environments, embodiments, or tasks still requires adaptation. Parameter-efficient fine-tuning (PEFT), especially LoRA, is common for VLA policies, yet the exposed capacity kno…
Large Reasoning Models (LRMs) achieve superior problem-solving through extended chain-of-thought generation, but the resulting key-value (KV) cache grows linearly with sequence length and creates severe memory bottlenecks—often exceeding GPU capacity for long reasoning traces. Existing KV cache comp…
Large vision–language models (VLMs) deliver state-of-the-art results on a wide range of multimodal tasks, yet they remain prone to visual hallucinations, producing content that is not grounded in the input image. Despite progress with visual supervision, reinforcement learning, and post-hoc attenti…
Retrieval-augmented generation (RAG) with large language models (LLMs) is especially valuable in specialized domains, where precision is critical. To more specialize the LLMs into a target domain, domain-specific RAG has recently been developed by allowing the LLM to access the target domain early v…
Modern multimodal large language models (MLLMs) can reason over hour-long video, yet their key–value (KV) cache grows linearly with time—quickly exceeding the fixed memory of phones, AR glasses, and edge robots. Prior compression schemes either assume the whole video and user query are available off…
Effective conversational search demands a deep understanding of user intent across multiple dialogue turns. Users frequently use abbreviations and shift topics in the middle of conversations, posing challenges for conventional retrievers. While query rewriting techniques improve clarity, they often
Compositional Zero-Shot Learning (CZSL) aims to identify unseen state-object compositions by leveraging knowledge learned from seen compositions. Existing approaches often independently predict states and objects, overlooking their relationships. In this paper, we propose a novel framework, learning…
Large vision-language models (LVLMs) are increasingly deployed in interactive applications such as virtual and augmented reality, where a first-person (egocentric) view captured by head-mounted cameras serves as key input. While this view offers fine-grained cues about user attention and hand-object…
Text-to-image generative models like DALL-E and Stable Diffusion have revolutionized visual content creation across various applications, including advertising, personalized media, and design prototyping. However, crafting effective textual prompts to guide these models remains challenging, often re…
The customization of large language models (LLMs) for user-specified tasks gets important. However, maintaining all the customized LLMs on cloud servers incurs substantial memory and computational overheads, and uploading user data can also lead to privacy concerns. On-device LLMs can offer a promis…
Unsupervised semantic segmentation (USS) aims to discover and recognize meaningful categories without any labels. For a successful USS, two key abilities are required: 1) information compression and 2) clustering capability. Previous methods have relied on feature dimension reduction for informatio…
Handling long input contexts remains a significant challenge for Large Language Models (LLMs), particularly in resource-constrained environments such as mobile devices. Our work aims to address this limitation by introducing InfiniPot, a novel KV cache control framework designed to enable pre-traine…
Recently, we have observed that Large Multi-modal Models (LMMs) are revolutionizing the way machines interact with the world, unlocking new possibilities across various multi-modal applications. To adapt LMMs for downstream tasks, parameter-efficient fine-tuning (PEFT) which only trains additional p…
A text encoder within Vision-Language Models (VLMs) like CLIP plays a crucial role in translating textual input into an embedding space shared with images, thereby facilitating the interpretative analysis of vision tasks through natural language. Despite the varying significance of different textual…
Monocular depth estimation is very challenging because clues to the exact depth are incomplete in a single RGB image. To overcome the limitation, deep neural networks rely on various visual hints such as size, shade, and texture extracted from RGB information. However, we observe that if such hints…
Image-text retrieval is a task to search for the proper textual descriptions of the visual world and vice versa. One challenge of this task is the vulnerability to input image/text corruptions. Such corruptions are often unobserved during the training, and degrade the retrieval model’s decision qual…
Transformer-based networks have achieved great success in image captioning because of the attention mechanism that finds relevant image locations for each word. However, the current cross-attention process, which aligns word-to-image, does not consider the spatial relationships existing in patch-to-…
Generalized zero-shot learning (GZSL) is a technique to train a deep learning model to identify unseen classes using the image attribute. In this paper, we put forth a new GZSL technique exploiting Vision Transformer (ViT) to maximize the attribute-related information contained in the image feature.…
Generalized zero-shot learning (GZSL) is a technique to train a deep learning model to identify unseen classes using the attribute. In this paper, we put forth a new GZSL technique that improves the GZSL classification performance greatly. Key idea of the proposed approach, henceforth referred to a…
Self-attention (SA) is a critical component of Transformer neural networks that have succeeded in automatic speech recognition (ASR). In this paper, we analyze the role of SA in Transformer-based ASR models for not only understanding the mechanism of improved recognition accuracy but also lowering t…
We propose a fast approximation method of a softmax function with a very large vocabulary using singular value decomposition (SVD). SVD-softmax targets fast and accurate probability estimation of the topmost probable words during inference of neural network language models. The proposed method trans…