Dynamic 3D Gaussian splatting faces a fundamental tension between motion consistency and visual fidelity. Deformation-based approaches preserve temporal correspondence but suffer from motion over-factorization, oversmoothing high-frequency…
Modern text-to-image models excel in visual fidelity and prompt adherence. However, this strict adherence comes at the cost of diversity: generated samples tend to collapse into…
Large language models are increasingly deployed as agents that reason over documents rather than answer from parametric knowledge. We study archive-grounded reasoning: locating sparse evidence across…
Cross-Chart Retrieval-Augmented Generation (RAG) is critical for complex multi-modal analytical tasks in scientific, business, and political domains. However, existing benchmarks either focus on tables, which are…
Attention-based Multiple Instance Learning aggregators in medical imaging are prone to attention concentration, producing overconfident and unstable predictions. We introduce QG-MIL, a gated transformer aggregator that…
Memory remains a critical bottleneck for long-horizon robotic manipulation, as standard Vision-Language-Action (VLA) policies often fail when task-relevant cues become occluded or unobservable over time. While…
Mental disorders are highly prevalent worldwide, but the shortage of psychiatrists and the inherent subjectivity of interview-based diagnosis create substantial barriers to timely and consistent mental-health…
Generating explorable 3D scenes from a single image requires strong generative priors and accurate geometric representations suitable for downstream use. Current video diffusion models offer high-quality…
AI agents are driving a new software paradigm, with the ability to autonomously call tools, extract information, manage memory, and complete tasks that span applications and…
Experience-driven self-evolution is critical for large language model (LLM) agents to improve through open-world interaction. However, existing experience learning methods mostly rely on single-agent loops, where…
Multimodal driving planning faces a long-standing tension between two paradigms: scoring-based methods benefit from dense reward supervision but are confined to a fixed action vocabulary, while…
The problem of optimal sizing and power scheduling in microgrids subject to uncertainties is well known to the control community. Commonly, the optimal control problem is…
We introduce NatureBench, a cross-discipline benchmark of 90 tasks distilled from peer-reviewed Nature-family publications, designed to evaluate whether AI coding agents can move beyond reproduction toward…
Dense retrieval embedding models are a fundamental component of modern retrieval-based AI systems. Most dense retrievers are trained with contrastive objectives, which require labeled positive and…
Training Latent Diffusion Models (LDMs) within Federated Learning (FL) has attracted increasing attention due to its ability to combine the powerful generative capacity of LDMs with…
Multimodal misinformation detection is increasingly important because viral posts now combine long multilingual narratives, several images, mixed provenance, and subtle text--image framing errors. Existing benchmarks and…
The composition of training data, governed by the diversity of sources and their mixing strategy, is a cornerstone of Large Language Model (LLM) pre-training. Online Data…
Text-to-image (T2I) generation models have achieved remarkable progress in producing visually realistic images from natural language prompts. Yet it remains unclear whether their success reflects genuine…
Generalist value models play a pivotal role in scaling robotic policy learning from large-scale, mixed-quality data. Mathematically, accurate value estimation demands deep temporal understanding, requiring models…
A world model predicts environment dynamics based on current observations and actions, serving as a core cognitive mechanism for reasoning and planning. In this work, we…
MLLM-based mobile GUI agents have made substantial progress on short-horizon tasks, yet remain unreliable on long-horizon tasks that require retaining intermediate facts across many steps and…
Agentic language models dramatically expand the applications of AI yet little is publicly known about how to curate training data for broadly capable agents. Existing open…
Sparse voxel representation has emerged as a scalable foundation for image-to-3D Gaussian Splatting (3DGS) generation, yet current methods struggle to preserve high-frequency visual details of input…
MLLM-based mobile GUI agents have made substantial progress in UI understanding and action execution, but adapting them to real target apps remains costly because mobile apps…