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。
875 篇论文 · 按点赞排序
Haoyu Zhao, Zihao Zhang, Xudong Wang +4 authors
MaLiang-Harness defines the Program-to-Visual gap and uses persistent executable generation, traceable editing, and revision-aware verification to improve multimodal language model-driven visual creation.
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.
Zheyuan Zhang, Alvin Zhang, Daniel Khashabi +1 authors
Composing complementary continual learning mechanisms substantially improves long-horizon memorization in language models by combining data, function, and weight anchors with merged low-rank updates.
Ruisi Wang, Zhongang Cai, Fanyi Pu +11 authors
Diffusion-based video models demonstrate reasoning capabilities through denoising steps rather than frame sequences, exhibiting behaviors like working memory, self-correction, and perception-before-action within specialized transformer layers.
Yuhan Zhu, Xiangyu Zeng, Qingyi Si +15 authors
VideoJev converts video observations into structured decisions by scoring temporal intervals and text options, enabling efficient reusable inference for visual agents.
Hao Liang, Zhengyang Zhao, Meiyi Qiang +22 authors
DataFlex is a unified framework for dynamic data-centric training of large language models that supports sample selection, domain mixture adjustment, and sample reweighting while maintaining compatibility with standard training workflows and enabling efficient large-scale deployment.
Xin Zhou, Zongchuang Zhao, Zhibo Yang +13 authors
Qwen-Drive-1.0 is a vision-language foundation model for autonomous driving that unifies 3D perception, visual question answering, and motion planning via shared representations and staged training.
Haoquan Fang, Jiafei Duan, Donovan Clay +26 authors
MolmoAct2 presents an open-action reasoning model for robotics that improves upon previous systems through specialized vision-language-model backbones, new datasets, open-weight action tokenizers, architectural redesign for continuous-action prediction, and adaptive reasoning for reduced latency.
Luozheng Qin, Yuhan Zhu, Changhai Zhou +9 authors
MJev-Spatial is a fast multimodal decision model that unifies spatial reasoning tasks into a single-pass classification framework, improving speed and accuracy over autoregressive vision-language models.
Shaobo Wang, Xuan Ouyang, Tianyi Xu +9 authors
OPUS is a dynamic data selection framework that improves pre-training efficiency by scoring data candidates based on optimizer-induced update projections in a stable proxy-derived target space, achieving superior performance with reduced computational overhead.
Chiyu Ma, Shuo Yang, Kexin Huang +7 authors
FIPO enhances reinforcement learning for language models by using discounted future-KL divergence to improve credit assignment and extend reasoning chains, achieving better mathematical problem-solving performance.
Tianle Zeng, Hanxuan Chen, Yanci Wen +1 authors
CARLA-Air integrates high-fidelity driving and multirotor flight simulation within a unified Unreal Engine framework, supporting joint air-ground agent modeling with photorealistic environments and multi-modal sensing capabilities.
Weijie Wang, Haomin Zhang, Ye Li +7 authors
ATAS improves long-form video consistency by compiling screenplays into referenced shot requests, retrieving spatial and temporal evidence from scene and event memories, and conditionally updating memory after generation.
Mingyu Ouyang, Yiran Wang, Siyuan Hu +9 authors
Player-1 improves game control by combining supervised fine-tuning on gameplay trajectories with reinforcement learning across synthetic environments, achieving substantial gains over demonstration-only baselines.
Tong Zheng, Xidong Wu, Zheng Zhang +14 authors
Dream-RSI enables scalable recursive self-improvement by using historical discovery replay to evaluate exploration policies offline, reducing costly online evaluations.
Yuntian Deng, Pengyu Nie, Stuart Shieber
Compile by training converts natural-language specifications into reusable neural functions by distilling teacher-generated examples into small adapters, enabling efficient deployment without remote model dependencies.
Qihan Ren, Peng Wang, Ruikun Cai +8 authors
Supervised finetuning and reinforcement learning exhibit conditional cross-domain generalization in reasoning tasks, influenced by optimization dynamics, data quality, and model capability, with asymmetric outcomes between reasoning improvement and safety degradation.
Yuntai Bao, Qinfeng Li, Guoqing Jiang +5 authors
On-policy distillation of reinforcement learning improves reasoning across model scales with predictable scaling laws, showing that smaller teachers can outperform larger ones at matched scores and that students often exceed their teachers.
I. Apanasevich, M. Artemyev, R. Babakyan +25 authors
Green-VLA is a five-stage vision-language-action framework for real-world robot deployment that achieves generalization across different robot embodiments through multimodal training and reinforcement learning.
Guan Wang, Changling Liu, Chenyu Wang +6 authors
A Hierarchical Recurrent Model architecture with specialized training on instruction-response pairs achieves competitive language modeling performance with significantly reduced computational requirements compared to traditional Transformer-based approaches.
Qize Yu, Lianrui Fan, Boyu Chen +23 authors
GroundingPI is a 4B grounding foundation model that improves precise object localization and downstream robotic and autonomous driving performance through multimodal pretraining and reinforcement learning.
Zhenglin Wan, Jiayu Chen, Zhengfeiyang Zhang +6 authors
DiffusionART improves reinforcement learning fine-tuning of diffusion models by removing hidden consistency forces and enabling stable, efficient training without EMA tuning or differentiable rewards.
Jiyan He, Guang Liang, Hao Liu +19 authors
ZGCM-1 is a 7B open foundation model that combines internal reasoning with external tool use, trained via efficient architecture-system co-design, progressive long-context scaling, and autonomous agent workflows to achieve strong reasoning and efficiency.
Hanzhang Zhou, Long Li, Quyu Kong +12 authors
OpenGCUA introduces an open generalist computer-use agent that integrates visual and programmatic interfaces, harness-to-model decision transfer, and code execution to improve task performance and efficiency across models.
Fan Jiang, Zhaoxu Sun, Mengchao Wang +38 authors
ABot-World-0 is a real-time action-conditioned video world model that uses progressive distillation, long-horizon alignment, and a co-designed streaming stack to enable efficient, long-horizon interactive world generation.
Jian Yang, Wei Zhang, Jiajun Wu +25 authors
InCoder-32B is a 32-billion-parameter code model trained on industrial datasets with extended context length and execution verification to improve performance in hardware-aware programming tasks.
Wentao Zhang, Liliana Hotsko, Woojeong Kim +3 authors
Fuzzy-function programming compiles natural-language specifications into compact neural artifacts using a 4B compiler and 0.6B interpreter, achieving efficient, local execution with reduced memory usage and faster inference.
Hanzhang Zhou, Panrong Tong, Xu Zhang +13 authors
Qwen-UI-Agent is a foundation GUI agent that integrates mobile, computer, web, and search environments with CLI execution, long-horizon online reinforcement learning, and autonomous data generation to achieve state-of-the-art real-world device performance.
Bing Yan, Gregory Wolfe, Stefano Martiniani +1 authors
Chemistry literature synthesis often requires assembling specific findings scattered across many publications, yet existing literature-search systems primarily return ranked document lists. As a result, scientists and AI agents need to locate relevant information, verify their provenance, and assemble cross-paper answers manually. We present AskChem, a claim-centered infrastructure for cross-paper chemistry search. AskChem changes the unit of retrieval from the paper to the provenance-carrying claim: each paper is converted into atomic, typed claims, each grounded by a source DOI and a verbatim quote or an explicit evidence locator. Over this shared claim store, AskChem exposes complementary structures for search and synthesis: a stabilized faceted taxonomy for hierarchical retrieval and browsing, an evidence graph linking claims through relations, and an exploratory living taxonomy that situates indexed papers under scientific principles. AskChem currently indexes 2.4M claims from 147K papers and provides a web interface, as well as REST, SDK, and MCP access for AI agents. On AskChem-Bench, grounding a GPT-5.5 reader in AskChem yields 100% resolvable DOIs, compared with 88.3% without retrieval, and the highest citation density among five tested systems. AskChem is live at https://askchem.org.
Zhiyuan Shi, Xiang Li, Xingzhuo Guo +8 authors
Multimodal language models use an intrinsic linear subspace called S-Space to encode object coordinates, supporting spatial perception, reasoning, and response generation, while also revealing bottlenecks in viewpoint transformation.
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