Related papers: Rank-and-Reason: Multi-Agent Collaboration Acceler…

Building robust vision systems for high-stakes domains such as remote sensing requires stronger visual reasoning than what single-pass inference typically provides; yet, retraining large models is often computationally expensive and data…

Interactive multimodal agents must convert raw visual observations into coherent sequences of language-conditioned actions -- a capability that current vision-language models (VLMs) still lack. Earlier reinforcement-learning (RL) efforts…

Accurate document retrieval is crucial for the success of retrieval-augmented generation (RAG) applications, including open-domain question answering and code completion. While large language models (LLMs) have been employed as dense…

Visual Retrieval-Augmented Generation (VRAG) enhances Vision-Language Models (VLMs) by incorporating external visual documents to address a given query. Existing VRAG frameworks usually depend on rigid, pre-defined external tools to extend…

Multi-agent reinforcement learning (MARL) is a powerful paradigm for solving cooperative and competitive decision-making problems. While many MARL benchmarks have been proposed, few combine continuous state and action spaces with…

Current embodied VLM evaluation relies on static, expert-defined, manually annotated benchmarks that exhibit severe redundancy and coverage imbalance. This labor intensive paradigm drains computational and annotation resources, inflates…

Multimodal Retrieval-Augmented Generation (mRAG) has emerged as a promising solution to address the temporal limitations of Multimodal Large Language Models (MLLMs) in real-world scenarios like news analysis and trending topics. However,…

Retrieval-augmented generation (RAG) enhances large language models (LLMs) for domain-specific question-answering (QA) tasks by leveraging external knowledge sources. However, traditional RAG systems primarily focus on relevance-based…

Retrieval-augmented generation (RAG) enhances the text generation capabilities of large language models (LLMs) by integrating external knowledge and up-to-date information. However, traditional RAG systems are limited by static workflows…

Existing Vision-Language Navigation (VLN) agents based on Large Vision-Language Models (LVLMs) often suffer from perception errors, reasoning errors, and planning errors, which significantly hinder their navigation performance. To address…

Protein Structure Prediction (PSP) is an unsolved problem in the field of computational biology. The problem of protein structure prediction is about predicting the native conformation of a protein, while its sequence of amino acids is…

Analysis of state-of-the-art VO/VSLAM system exposes a gap in balancing performance (accuracy & robustness) and efficiency (latency). Feature-based systems exhibit good performance, yet have higher latency due to explicit data association;…

The rise of short-form video platforms and the emergence of multimodal large language models (MLLMs) have amplified the need for scalable, effective, zero-shot text-to-video retrieval systems. While recent advances in large-scale…

Recent advancements in Retrieval-Augmented Generation (RAG) have enabled Large Language Models to answer financial questions using external knowledge bases of U.S. SEC filings, earnings reports, and regulatory documents. However, existing…

In protein engineering, while computational models are increasingly used to predict mutation effects, their evaluations primarily rely on high-throughput deep mutational scanning (DMS) experiments that use surrogate readouts, which may not…

Reasoning is central to purposeful action, yet most robotic foundation models map perception and instructions directly to control, which limits adaptability, generalization, and semantic grounding. We introduce Action Reasoning Models…

Foundation models face growing compute and memory bottlenecks, hindering deployment on resource-limited platforms. While compression techniques such as pruning and quantization are widely used, most rely on uniform heuristics that ignore…

AI agents could accelerate scientific discovery by automating hypothesis formation, experiment design, coding, execution, and analysis, yet existing benchmarks probe narrow skills in simplified settings. To address this gap, we introduce…

State-of-the-art neural rankers pre-trained on large task-specific training data such as MS-MARCO, have been shown to exhibit strong performance on various ranking tasks without domain adaptation, also called zero-shot. However, zero-shot…

In modern medicine, clinical diagnosis relies on the comprehensive analysis of primarily textual and visual data, drawing on medical expertise to ensure systematic and rigorous reasoning. Recent advances in large Vision-Language Models…