InSight: Self-Guided Skill Acquisition via Steerable VLAs
Vision-language-action (VLA) models can learn manipulation skills from demonstrations, but their capabilities are bounded by the skills in the training data. We present InSight, a framework…
Papers 5173 stories
Multi4D: High-Fidelity Dynamic Gaussian Splatting via Multi-Level Competitive Allocation
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…
Semantic Browsing: Controllable Diversity for Image Generation
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…
AGORA: An Archive-Grounded Benchmark for Agentic Workplace Document Reasoning
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…
ChartWalker: Benchmarking the Cross-Chart RAG Task
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…
QG-MIL: A Gated Transformer Aggregator for Domain-Agnostic Multiple Instance Learning in Medical Imaging
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…
EventVLA: Event-Driven Visual Evidence Memory for Long-Horizon Vision-Language-Action Policies
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…
LingxiDiagBench: A Multi-Agent Framework for Benchmarking LLMs in Chinese Psychiatric Consultation and Diagnosis
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…
FLAT: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene Generation
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…
AOHP: An Open-Source OS-Level Agent Harness for Personalized, Efficient and Secure Interaction
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…
Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning
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…
FlowR2A: Learning Reward-to-Action Distribution for Multimodal Driving Planning
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…
An Efficient Method for the Optimal Control of Microgrids Under Uncertainties using Local Reduction
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…
NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers?
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…
DREAM: Dense Retrieval Embeddings via Autoregressive Modeling
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…
FedOT: Ownership Verification and Leakage Tracing via Watermarks for Federated LDMs
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…
ReMMD: Realistic Multilingual Multi-Image Agentic Verification for Multimodal Misinformation Detection
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…
Holistic Data Scheduler for LLM Pre-training via Multi-Objective Reinforcement Learning
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…
Are Text-to-Image Models Inductivist Turkeys? A Counterfactual Benchmark for Causal Reasoning
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…
World Value Models for Robotic Manipulation
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…
Qwen-AgentWorld: Language World Models for General Agents
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…
MemGUI-Agent: An End-to-End Long-Horizon Mobile GUI Agent with Proactive Context Management
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…
OpenThoughts-Agent: Data Recipes for Agentic Models
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…
FLUX3D: High-Fidelity 3D Gaussian Generation with Diffusion-Aligned Sparse Representation
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…