Explore · 每周精选
发现最受关注的研究论文,追踪研究趋势,订阅感兴趣的期刊与关键词。
Ming Qian, Tianjian Ouyang, Mingchao Sun +25 authors
ABot-Earth 0.5 generates realistic 3D environments from satellite imagery using 3D Gaussian Splatting representation, enabling fast synthesis and real-time visualization for Embodied AI applications.
50 篇论文 · 按点赞排序
Hongyuan Adam Lu, Z. L. Victor Wei, Qun Zhang +28 authors
Looped World Models introduce iterative latent state refinement through shared transformer blocks, achieving 100x parameter efficiency while adapting computational depth to prediction complexity.
Yiyou Sun, Xinyang Han, Weichen Zhang +305 authors
Agents' Last Exam (ALE) is a benchmark for evaluating AI agents on long-term, economically valuable real-world tasks across 13 industry clusters with 1K+ tasks, revealing significant gaps between benchmark performance and practical deployment.
Haozhe Zhao, Shuzheng Si, Zhenhailong Wang +6 authors
Automated systems for generating scientific figures face limitations in handling diverse figure types and conditions, prompting the development of multi-agent frameworks that generalize across different input scenarios and produce editable output formats.
Mind Lab, Song Cao, Vic Cao +51 authors
Parameter-efficient fine-tuning can function as a compact substrate for persistent personal models by enabling small trainable adapters to store instance-specific behaviors on top of strong foundation models.
Dingyu Yao, Junhao Zhou, Chenxu Yang +12 authors
A vision-language model operates continuously in real-time, making autonomous decisions about when to respond or delegate, enabling interactive systems that perceive and act upon environmental changes without user prompting.
Jian Yang, Shawn Guo, Wei Zhang +16 authors
Parallel loop Transformers achieve better code generation performance with two loops due to refined representations, while additional loops cause diminishing returns and increased positional mismatch costs.
Kwai Keye Team, Bin Wen, Changyi Liu +50 authors
Kwai Keye-VL-2.0-30B-A3B is an open-source Mixture-of-Experts multimodal foundation model that enables long-video understanding and agentic intelligence through DeepSeek Sparse Attention and specialized training infrastructure.
Ye Jin, Yangyang Xu, Jun Zhu +1 authors
MemSlides presents a hierarchical memory framework for personalized presentation agents that separates long-term user profiles, working memory for session constraints, and tool memory for reusable execution experiences to enable stable personalization and reliable local edits across multi-turn revisions.
Yifu Yuan, Yaoting Huang, Xianze Yao +20 authors
Embodied-R1.5 is a unified embodied foundation model that integrates embodied reasoning capabilities and achieves state-of-the-art performance on embodied vision-language benchmarks through a multi-task balanced reinforcement learning approach.
Xunhao Lai, Weiqi Xu, Yufeng Yang +8 authors
MiniMax Sparse Attention enables efficient processing of ultra-long contexts in large language models through blockwise sparsity and optimized GPU execution, achieving significant speedups while maintaining performance.
Yuxin Zuo, Zikai Xiao, Li Sheng +30 authors
Language-based world models enable agentic environment simulation across multiple domains and enhance general agent performance through scalable simulation and improved downstream task performance.
Jianuo Huang, Yaojie Zhang, Qituan Zhang +3 authors
Domino is a speculative decoding framework that improves LLM inference speed by decoupling causal dependency modeling from autoregressive drafting through a parallel backbone and lightweight causal refinement head, achieving significant speedups in both end-to-end execution and throughput.
Han Luo, Bingbing Wen, Lucy Lu Wang
Agentic abstention involves determining when an AI agent should cease interaction under uncertainty, requiring sequential decision-making across multiple environments and task types.
Jundong Xu, Qingchuan Li, Jiaying Wu +11 authors
EvoArena benchmark and EvoMem memory paradigm address the challenge of dynamic environments in LLM agents by modeling progressive updates and structured memory evolution, showing improved performance on evolving tasks.
Aditi, Niket Agarwal, Arslan Ali +288 authors
Cosmos 3 is an omnimodal world model that processes and generates multiple data types through a unified mixture-of-transformers architecture, achieving state-of-the-art performance in various understanding and generation tasks.
Kangsheng Duan, Ziyang Xu, Wenyu Liu +3 authors
A lightweight image inpainting framework achieves high-fidelity results with significantly reduced parameters and inference time through novel local-global interaction blocks and adaptive distillation strategies.
Wei Zhou, Xuanhe Zhou, Shaokun Han +5 authors
Large language model agents' memory systems have evolved into complex data management frameworks requiring systematic evaluation across multiple modules and workloads to understand their performance characteristics and trade-offs.
Kevin Qinghong Lin, Batu EI, Yuhong Shi +3 authors
A multi-agent framework automates data journalism by generating evidence-grounded, multimodal news stories while maintaining transparency and verifiability.
Tianyi Zhou, Dongrui Liu, Leitao Yuan +2 authors
Person-grounded AI skills are automatically distilled from heterogeneous traces into inspectable, correctable packages that capture both capabilities and behavioral patterns.
Jiajie Jin, Yuyang Hu, Kai Qiu +15 authors
An AI framework called Arbor enables autonomous scientific research by combining strategic coordination, isolated hypothesis testing, and a persistent knowledge tree to iteratively improve research outcomes across multiple domains.
Sen Xu, Shixi Liu, Wei Wang +6 authors
VibeThinker-3B demonstrates that compact models can achieve state-of-the-art performance on verifiable reasoning tasks through specialized training techniques, challenging conventional scaling assumptions.
Mahtab Bigverdi, Linjie Li, Weikai Huang +8 authors
Imaginative Perception Tokens (IPT) enhance vision-language models' spatial reasoning by providing intermediate perceptual representations that externalize what the model would perceive from alternative viewpoints, outperforming traditional text-based reasoning methods.
Lianghua Huang, Zhifan Wu, Wei Wang +21 authors
Wan-Streamer is a unified, end-to-end multimodal model that enables real-time audio-visual interaction through causal attention mechanisms and integrated processing of visual, audio, and text modalities.
Shaoqiu Zhang, Yuhang Wang, Jialiang Liang +8 authors
SWE-Explore introduces a benchmark for evaluating coding agents' repository exploration capabilities by requiring ranked lists of relevant code regions within line budgets, demonstrating that agentic exploration outperforms traditional retrieval methods.
Zhifei Xie, Zihang Liu, Ze An +8 authors
A unified streaming audio model is developed that combines offline task execution with real-time audio instruction following through an end-to-end framework supporting multiple audio interaction capabilities.
Jisang Han, Seonghu Jeon, Jaewoo Jung +7 authors
A geometric action model leverages pretrained geometric foundation models to enable language-conditioned manipulation policies with improved accuracy, robustness, and efficiency in 3D physical environments.
Yongheng Zhang, Ziang Liu, Jiaxuan Zhu +17 authors
Large Language Models are evolving from conversational systems to integrated AI colleagues with enhanced reasoning capabilities and persistent work environments.
Jiwen Liu, Shujuan Li, Zhixue Fang +8 authors
A unified framework for camera motion cloning that uses grid motion videos as representation and integrates multimodal diffusion transformers for enhanced video generation control.
Seokju Cho, Ryo Hachiuma, Abhishek Badki +8 authors
SpatialClaw is a training-free framework that uses code as an action interface to enable flexible, stateful spatial reasoning in vision-language models, achieving superior performance across diverse 3D/4D spatial reasoning tasks.
北京市昌平区探索星信息技术及软件开发工作室
京ICP备2026059466号