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
Yuan Liang, Ruobin Zhong, Haoming Xu +46 authors
SkillNet introduces an open infrastructure for systematically accumulating and transferring AI skills through a unified ontology, significantly improving agent performance across multiple domains.
Ibragim Badertdinov, Maksim Nekrashevich, Anton Shevtsov +1 authors
A large-scale dataset of software engineering tasks spanning multiple programming languages and repositories was created using an automated pipeline that generates executable environments and filters unreliable instances through LLM validation.
Hongtao Wu, Boyun Zheng, Dingjie Song +5 authors
Medical AI Scientist represents the first autonomous research framework designed for clinical applications, enabling evidence-based hypothesis generation and manuscript drafting through clinician-engineer collaboration across three research modes.
Zhen Li, Zian Meng, Shuwei Shi +5 authors
WildWorld is a large-scale dataset for action-conditioned world modeling that provides explicit state annotations from a photorealistic game, enabling better understanding of latent-state dynamics and long-horizon consistency.
Nimrod Shabtay, Moshe Kimhi, Artem Spector +5 authors
AwaRes is a spatial-on-demand framework for vision-language models that dynamically retrieves high-resolution image segments based on query needs, using tool-calling and multi-turn reinforcement learning with composite rewards.
Fangfu Liu, Diankun Wu, Jiawei Chi +7 authors
Spatial-TTT enables streaming visual-based spatial intelligence through test-time training that adapts parameters to capture spatial evidence over long video sequences using hybrid architecture and 3D spatiotemporal convolution.
Zonglin Yang, Lidong Bing
MOOSE-Star framework enables efficient training and inference for generative reasoning by addressing combinatorial complexity through decomposed subtasks, hierarchical search, and bounded composition.
Wei Yu, Runjia Qian, Yumeng Li +8 authors
Video diffusion models use hybrid spatial memory to maintain consistency under camera motion and enable long-term scene editing and navigation.
Yuanyuan Gao, Hao Li, Yifei Liu +14 authors
Holi-Spatial presents the first fully automated, large-scale, spatially-aware multimodal dataset constructed from raw video inputs, supporting multi-level spatial supervision for 3D scene understanding and spatial reasoning tasks.
Lianghui Zhu, Yuxin Fang, Bencheng Liao +10 authors
Scaling depth is a key driver for large language models (LLMs). Yet, as LLMs become deeper, they often suffer from signal degradation: informative features formed in shallow layers are gradually diluted by repeated residual updates, making them harder to recover in deeper layers. We introduce mixture-of-depths attention (MoDA), a mechanism that allows each attention head to attend to sequence KV pairs at the current layer and depth KV pairs from preceding layers. We further describe a hardware-efficient algorithm for MoDA that resolves non-contiguous memory-access patterns, achieving 97.3% of FlashAttention-2's efficiency at a sequence length of 64K. Experiments on 1.5B-parameter models demonstrate that MoDA consistently outperforms strong baselines. Notably, it improves average perplexity by 0.2 across 10 validation benchmarks and increases average performance by 2.11% on 10 downstream tasks, with a negligible 3.7% FLOPs computational overhead. We also find that combining MoDA with post-norm yields better performance than using it with pre-norm. These results suggest that MoDA is a promising primitive for depth scaling. Code is released at https://github.com/hustvl/MoDA .
Jianing Wang, Jianfei Zhang, Qi Guo +24 authors
A 560-billion-parameter Mixture-of-Experts model advances formal reasoning in Lean4 through tool-integrated reasoning with a hybrid framework and hierarchical policy optimization for stable training on long-horizon tasks.
Qinsi Wang, Hancheng Ye, Jinhee Kim +12 authors
Structure of Thought prompting technique enhances language model performance by guiding explicit intermediate text structuring across diverse tasks, while T2S-Bench benchmark evaluates and improves text-to-structure capabilities with comprehensive scientific domain coverage.
Zorik Gekhman, Roee Aharoni, Eran Ofek +3 authors
Reasoning in large language models enhances parametric knowledge recall through computational buffer and factual priming mechanisms, though it carries risks of hallucination that can be mitigated by prioritizing accurate reasoning trajectories.
Xinping Zhao, Xinshuo Hu, Jiaxin Xu +9 authors
A new benchmark evaluates embedding models' ability to handle long-horizon memory retrieval tasks, revealing that performance in traditional passage retrieval does not generalize to complex memory retrieval scenarios.
Kaijin Chen, Dingkang Liang, Xin Zhou +4 authors
Hybrid Memory enables video world models to maintain consistent tracking of dynamic subjects during occlusion by combining archival storage for static backgrounds with active tracking for moving objects, using a specialized architecture with tokenized memory and spatiotemporal retrieval mechanisms.
Zhuolin Yang, Zihan Liu, Yang Chen +14 authors
Nemotron-Cascade 2 is a 30B parameter Mixture-of-Experts model with 3B activated parameters that achieves exceptional reasoning and agentic capabilities, matching frontier open models despite its compact size and demonstrating high intelligence density.
Yushi Bai, Qian Dong, Ting Jiang +5 authors
IndexCache reduces sparse attention computation in large language models by reusing top-k token selections across layers, achieving significant speedups with minimal quality loss.
Zimo Wen, Boxiu Li, Wanbo Zhang +11 authors
Unified multimodal models show mixed performance in generation-to-understanding tasks, with specific subtasks benefiting from enhanced spatial and reasoning capabilities while overall performance lags behind specialized vision-language models.
Danil Tokhchukov, Aysel Mirzoeva, Andrey Kuznetsov +1 authors
Diffusion Transformers can be enhanced through a parameter-efficient calibration approach that improves generative quality while reducing inference steps.
Łukasz Borchmann, Jordy Van Landeghem, Michał Turski +12 authors
MADQA benchmark evaluates multimodal agents' strategic reasoning capabilities through diverse PDF document questions, revealing gaps between human-level accuracy and efficient reasoning performance.
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