Related papers: HyperEyes: Dual-Grained Efficiency-Aware Reinforce…

Generative models often use human evaluations to measure the perceived quality of their outputs. Automated metrics are noisy indirect proxies, because they rely on heuristics or pretrained embeddings. However, up until now, direct human…

Multimodal recommender systems leverage diverse data sources, such as user interactions, content features, and contextual information, to address challenges like cold-start and data sparsity. However, existing methods often suffer from one…

We present two novel hyperparameter optimization strategies for optimization of deep learning models with a modular architecture constructed of multiple subnetworks. As complex networks with multiple subnetworks become more frequently…

New technologies drastically change recruitment techniques. Some research projects aim at designing interactive systems that help candidates practice job interviews. Other studies aim at the automatic detection of social signals (e.g.…

Existing multimodal retrieval systems excel at semantic matching but implicitly assume that query-image relevance can be measured in isolation. This paradigm overlooks the rich dependencies inherent in realistic visual streams, where…

In Multi-Goal Reinforcement Learning, an agent learns to achieve multiple goals with a goal-conditioned policy. During learning, the agent first collects the trajectories into a replay buffer, and later these trajectories are selected…

Large reasoning models, such as OpenAI o1 and DeepSeek-R1, tend to become increasingly verbose as their reasoning capabilities improve. These inflated Chain-of-Thought (CoT) trajectories often exceed what the underlying problems require,…

Acquiring complex behaviors is essential for artificially intelligent agents, yet learning these behaviors in high-dimensional settings poses a significant challenge due to the vast search space. Traditional reinforcement learning (RL)…

Recently, multi-modality scene perception tasks, e.g., image fusion and scene understanding, have attracted widespread attention for intelligent vision systems. However, early efforts always consider boosting a single task unilaterally and…

Enabling robots to explore and act in unfamiliar environments under ambiguous human instructions by interactively identifying task-relevant objects (e.g., identifying cups or beverages for "I'm thirsty") remains challenging for existing…

We present PREMISE (PREdict with Matching ScorEs), a new architecture for the matching-based learning in the multimodal fields for the multimodal review helpfulness (MRHP) task. Distinct to previous fusion-based methods which obtains…

We propose DeepRAG, a novel framework that integrates DeepSeek hierarchical question decomposition capabilities with RAG Gym unified retrieval-augmented generation optimization using process level supervision. Targeting the challenging…

Combining multiple modalities carrying complementary information through multimodal learning (MML) has shown considerable benefits for diagnosing multiple pathologies. However, the robustness of multimodal models to missing modalities is…

User-Centric Embodied Visual Tracking (UC-EVT) presents a novel challenge for reinforcement learning-based models due to the substantial gap between high-level user instructions and low-level agent actions. While recent advancements in…

In the evolving landscape of human-autonomy teaming (HAT), fostering effective collaboration and trust between human and autonomous agents is increasingly important. To explore this, we used the game Overcooked AI to create dynamic teaming…

Optimization of hyper-parameters in reinforcement learning (RL) algorithms is a key task, because they determine how the agent will learn its policy by interacting with its environment, and thus what data is gathered. In this work, an…

Training a Multimodal Large Language Model (MLLM) from scratch, like GPT-4, is resource-intensive. Regarding Large Language Models (LLMs) as the core processor for multimodal information, our paper introduces LMEye, a human-like eye with a…

Multimodal Entity Linking (MEL) aims to associate textual and visual mentions with entities in a multimodal knowledge graph. Despite its importance, current methods face challenges such as incomplete contextual information, coarse…

Robust deployment of large multimodal models (LMMs) in real-world scenarios requires access to external knowledge sources, given the complexity and dynamic nature of real-world information. Existing approaches such as retrieval-augmented…

Universal multimodal embedding models have achieved great success in capturing semantic relevance between queries and candidates. However, current methods either condense queries and candidates into a single vector, potentially limiting the…