Related papers: AMES: Approximate Multi-modal Enterprise Search vi…
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)…
Existing multimodal search agents process target entities sequentially, issuing one tool call per entity and accumulating redundant interaction rounds whenever a query decomposes into independent sub-retrievals. We argue that effective…
We propose attribute-aware multimodal entity linking, where the input consists of a mention described with a text paragraph and images, and the goal is to predict the corresponding target entity from a multimodal knowledge base (KB) where…
Long-term conversational memory requires retrieving evidence scattered across multiple sessions, yet single-pass retrieval fails on temporal and multi-hop questions. Existing iterative methods refine queries via generated content or…
With the advent of large language models (LLMs), there has been a great deal of interest in applying them to solve difficult programming tasks. Recent work has demonstrated their potential at program optimization, a key challenge in…
We present READMem (Robust Embedding Association for a Diverse Memory), a modular framework for semi-automatic video object segmentation (sVOS) methods designed to handle unconstrained videos. Contemporary sVOS works typically aggregate…
Multimodal semantic communication has gained widespread attention due to its ability to enhance downstream task performance. A key challenge in such systems is the effective fusion of features from different modalities, which requires the…
Approximate Nearest Neighbor Search (ANNS) is a core primitive in modern AI systems, and graph-based methods currently offer the best accuracy-efficiency trade-off at scale. The workload is fundamentally memory-bound: graph traversal…
Agentic systems powered by Large Language Models (LLMs) have shown strong potential in recommender systems but remain hindered by several challenges. Fine-tuning LLMs is parameter-inefficient, and prompt-based agentic reasoning is limited…
Recent multimodal large language models (MLLMs) such as GPT-4o and Qwen3-Omni show strong perception but struggle in multi-speaker, dialogue-centric settings that demand agentic reasoning tracking who speaks, maintaining roles, and…
Language is often used to describe physical interaction, yet most 3D human pose estimation methods overlook this rich source of information. We bridge this gap by leveraging large multimodal models (LMMs) as priors for reconstructing…
In the context of today's high-pressure, aging society, the demand for large-scale emotional models capable of providing empathetic support is more critical than ever. However, existing benchmarks fail to simultaneously achieve ecological…
We present AutoPose, a novel neural architecture search(NAS) framework that is capable of automatically discovering multiple parallel branches of cross-scale connections towards accurate and high-resolution 2D human pose estimation.…
A core interest in building Artificial Intelligence (AI) agents is to let them interact with and assist humans. One example is Dynamic Search (DS), which models the process that a human works with a search engine agent to accomplish a…
Deep Learning Recommendation Model(DLRM)s utilize the embedding layer to represent various categorical features. Traditional DLRMs adopt unified embedding size for all features, leading to suboptimal performance and redundant parameters.…
This study proposes the design and implementation of a multimodal LLM-based Multi-Agent System (MAS) leveraging a No-Code platform to address the practical constraints and significant entry barriers associated with AI adoption in…
In modern e-commerce search systems, dense retrieval has become an indispensable component. By computing similarities between query and item (product) embeddings, it efficiently selects candidate products from large-scale repositories. With…
Audio-visual emotion recognition (AVER) methods typically fuse utterance-level features, and even frame-level attention models seldom address the frame-rate mismatch across modalities. In this paper, we propose a Transformer-based framework…
Neural Architecture Search (NAS) automates network design, but conventional methods demand substantial computational resources. We propose a closed-loop pipeline leveraging large language models (LLMs) to iteratively generate, evaluate, and…
Large Language Models (LLMs) have demonstrated success across many benchmarks. However, they still exhibit limitations in long-context scenarios, primarily due to their short effective context length, quadratic computational complexity, and…