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。
50 篇论文 · 按点赞排序
Lanxiang Hu, Zhaoxiang Feng, Yulun Wu +9 authors
JetSpec is a speculative decoding framework that combines efficient forward drafting with causal conditioning to improve LLM inference speed and acceptance rates across various benchmarks.
Chang Nie, Chaoyou Fu, Junlan Feng +1 authors
EvoEmbedding is a dynamic embedding model that generates adaptive representations by maintaining a continuously updated latent memory, enabling improved retrieval performance in long-context scenarios.
Shanhui Zhao, Jiacheng Liu, Guohong Liu +13 authors
AOHP presents an Android-based operating system framework that treats AI agents as first-class entities, enhancing task completion rates and reducing execution costs through specialized agent-oriented mechanisms.
Xiao Zhou, Siyue Zhang, Yilun Zhao +4 authors
Computer-use agents can execute software tasks through either graphical interfaces or programmatic command interfaces, but existing evaluations confound interaction modality with differences in tasks, initial states, verifiers, and permitted actions. We introduce a matched execution-layer benchmark of 440 desktop tasks across 18 applications and 12 workflow categories, where screen-only GUI agents and skill-mediated CLI agents receive identical goals, states, and final-state verifiers while being restricted to modality-native actions. In this controlled setting, the strongest GUI agent reaches a 59.1% full pass rate, outperforming the strongest original-skill CLI agent at 48.2%; however, verifier-guided skill augmentation raises CLI success to 69.3%, showing that much of the CLI deficit comes from incomplete skill coverage rather than model capability alone. These results suggest that GUI and CLI expose different execution bottlenecks: GUI agents are limited by reliable grounded interaction over long-horizon workflows, whereas CLI agents are limited by the coverage and scalability of their skill interfaces.
Jiehui Huang, Yuechen Zhang, Bin Xia +7 authors
UnityShots is a memory-driven audio-video generation system that maintains consistent subject appearance and audio across video cuts using fixed-size long-term and short-term memory slots with boundary-conditioned gates and discrete cut-type priors.
Yuntian Gao, Xiangyu Xu
Fast-LeWM accelerates visual planning by replacing autoregressive rollout with parallel action-prefix prediction, reducing computational costs and latency accumulation during long-horizon predictions.
Haoxiang Sun, Zhihang Yi, Langxuan Deng +6 authors
A novel label-free framework for visual reasoning called V-Zero is presented, which uses contrastive evidence gating to improve fine-grained visual reasoning without requiring annotated answer labels, achieving faster training than traditional methods.
Kaiwen Zheng, Guande He, Min Zhao +7 authors
Autoregressive video diffusion extends diffusion distillation frameworks to real-time streaming generation through causal training paradigms, achieving state-of-the-art performance with fast convergence and interactive world modeling capabilities.
Xuanming Zhang, Sining Zhoubian, Yuxuan Chen +8 authors
Autoregressive generation in large language models traditionally uses the final layer for token prediction, but a new decoding strategy dynamically selects more reliable intermediate layers based on entropy-guided search, improving reasoning performance with minimal computational overhead.
Orest Kupyn, Goutam Bhat, Philipp Henzler +3 authors
Video diffusion models are adapted to decode explicit surface primitives directly from latent space, enabling high-quality 3D scene generation with improved geometric accuracy and real-time rendering capabilities.
Qizhi Pei, Zhimeng Zhou, Yi Duan +9 authors
BioMatrix is a novel multimodal foundation model that integrates molecular sequences, structures, and natural language into a unified decoder-only architecture for diverse biological tasks.
Eric Xing, Mingkai Deng, Jinyu Hou
True artificial agency requires internalized structures for goals, identity, decision-making, self-regulation, and learning, distinguishing autonomous systems from task-specific ones.
Shihao Xu, Tiancheng Zhou, Jiatong Ma +8 authors
A large-scale multi-agent benchmark for evaluating LLMs in Chinese psychiatric diagnosis is introduced, highlighting challenges in dynamic consultation and the gap between consultation quality and diagnostic accuracy.
Haggai Roitman
The book provides a comprehensive guide to building autonomous AI systems, covering foundational elements like transformer architecture and training methods, along with advanced topics such as reinforcement learning, agent architectures, and production deployment.
Amirhossein Abaskohi, Raymond Li, Gaetano Cimino +3 authors
MCompassRAG enhances retrieval-augmented generation by using topic-level metadata to guide chunk selection, improving both efficiency and precision in complex research tasks.
Mykola Vysotskyi, Runqi Lin, Grzegorz Biziel +22 authors
A web-based benchmark evaluates agent generalization across challenging scenarios, revealing significant gaps between current agentic systems and human performance in temporal perception, graphical understanding, and 3D reasoning.
Ilia Kulikov, Chenxi Whitehouse, Tianhao Wu +12 authors
Autodata enables AI agents to function as data scientists who create high-quality training data through meta-optimization, demonstrating improved performance across multiple task domains.
Zixuan Li, Haokun Lin, Yicheng Xiao +10 authors
Implicit Visual Chain-of-Thought decomposes visual conditioning into structural and semantic cascades for improved structure-aware image generation with sketch supervision.
Sara Dorfman, Maya Vishnevsky, Omer Dahary +2 authors
Text-to-image models are enhanced with controlled diversity through semantic browsing capabilities that enable structured navigation of image variations based on meaningful semantic decisions.
Yurun Chen, Biao Yi, Keting Yin +1 authors
SkillHarness is a framework that enables computer-use agents to safely learn and execute skills in dynamic environments by incorporating safety constraints and adaptive skill selection mechanisms.
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