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。
Jianlyu Chen, Yuyang Hu, Hongjin Qian +8 authors
DisCo is a research agent that distills operational knowledge into reusable skills, significantly improving autonomous ML research performance across benchmarks.
50 篇论文 · 按点赞排序
Ke Yang, Chenglong Wang, Michel Galley +4 authors
StudentSim trains personalized student simulators from sparse data to mirror learner responses and adapt to tutor guidance, outperforming existing models across chess, writing, and math.
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.
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.
Jie Wu, Zhenru Zhang, Beichen Zhang +11 authors
Terminal-Universe reconstructs executable workspaces from agent trajectories to synthesize diverse training tasks and improves post-training performance through supervised fine-tuning.
Yuhao Wu, Jingyuan Zhang, Jiajun Shi +16 authors
HarnessDev evaluates agents by measuring their ability to build and iteratively improve execution infrastructure rather than final task outputs, revealing that self-built harnesses vary widely in capability and efficiency and transfer poorly across models.
Chuyan Chen, Haoxing Chen, Kun Chen +27 authors
LLaDA-Image unifies a 6B diffusion transformer with a frozen vision-language module, using image-only pre-training and a Muon optimizer to generate photorealistic images with precise editing, and is distilled into a fast 2-4 step variant that achieves state-of-the-art open-source results.
Yuhao Wu, Jingyuan Zhang, Jiajun Shi +18 authors
ASPIRE introduces a benchmark for self-evolving LLM agents from vague natural-language goals, revealing challenges in goal interpretation, data selection, and stable weight-level improvement.
Heng Wang, Jielin Qiu, Wenting Zhao +7 authors
Random eviction of reasoning tokens matches selective KV cache compression because reasoning traces are self-protecting through redundancy, making scoring unnecessary once prompts are preserved.
Tingyun Li, Wenfeng Feng, Weiqing Li +3 authors
Boundary-Calibrated Intervention Transfer selectively reuses past training evidence by checking contextual applicability and running bounded trials, reducing harmful updates and improving final model quality in autonomous post-training.
Yi Ding, Ruqi Zhang
On-policy distillation relies mainly on suppressing low-probability tokens rather than teacher guidance, motivating a supervision-free entropy-adaptive method that substantially improves reasoning performance.
Junchao Huang, Guian Fang, Shengju Qian +15 authors
SolarWM provides an open framework and unified training recipe for building interactive video world models across diverse data sources and generator backbones, enabling long-horizon real-time rollouts.
Minghan Qin, Yuang Wang, Xiuyu Yang +6 authors
Lucida improves composable indoor scene reconstruction by distributing pipeline requirements across parsing, asset generation, and VLM-guided placement to achieve high-fidelity editable replicas from cluttered captures.
Yuling Shi, Zhensu Sun, Junsen Dong +3 authors
EarlyEval predicts agent outcomes from intermediate behavior to reduce evaluation cost by halting runs early with minimal accuracy loss.
Zhengze Zhou, Hejian Sang
LatentPress compresses conversational and document context into continuous memory tokens read directly by a frozen decoder, achieving high compression with faster inference and improved accuracy over text or OCR methods.
Howard Qian, Yiting Chen, Yunfei Xie +6 authors
RoboTok retrieves relevant human manipulation videos from the web using a latent motion space derived from 3D hand trajectories to improve robot policy training.
Yi Wang, Haopeng Zhang, Chengxiang Huang +4 authors
LoopArena benchmarks how well a controller model guides a separate coding agent through long tasks, revealing low strict success rates and significant cost reductions.
Shaowen Wang, Ge Zhang, Kairong Luo +6 authors
Looping middle layers in sparse Mixture-of-Experts Transformers improves training efficiency and downstream performance while matching per-token FLOPs, parameters, and cache budgets.
Jiashu Zhu, Yanhao Zheng, Ruitian Tian +7 authors
A compact 7B native joint audio-video generator uses cross-modal attention, progressive joint training, reinforcement learning with multimodal feedback, and an autoregressive 2K refinement pipeline to produce synchronized high-resolution outputs.
Senqiao Yang, Chengyao Wang, Yuxin Chen +13 authors
VLAct improves vision-language-action model performance by pre-training on diverse robot data with preserved vision-language priors and shared action semantics, achieving strong results across simulations and unseen embodiments with limited compute.
Zixuan Fu, Bingxiang He, Yuxin Zuo +10 authors
On-policy distillation improves over hundreds of steps from a single query by rapidly covering teacher states, yet student alignment remains slow, indicating the method is algorithm-starved rather than data-starved.
Hangrui Xu, Jiarui Wang, Yang Yang +5 authors
DART-SD improves multi-turn tool-calling agents by modeling execution as a diamond-topology graph, identifying critical failure points, and applying localized self-distillation to preserve valid reasoning while correcting errors.
Sergii Kozyrev, Davyd Maiboroda
Fully quantizing hybrid LLMs—including recurrent Gated DeltaNet layers—to 4-bit NVFP4 preserves accuracy across long-context and reasoning benchmarks by localizing outliers and exploiting robust delta-rule dynamics.
Runpeng Dai, Kaili Huang, Changsung Kang +1 authors
CoGR trains LLMs to generate compact keywords for both queries and items, enabling direct inverted-index retrieval optimized via co-evolving reinforcement learning.
Namgyu Ho, Huzama Ahmad, Woosung Koh +3 authors
Declarative Attention lets language models declare relevant context regions during reasoning to skip most KV cache reads, reducing attended tokens with small accuracy trade-offs.
Guangting Zheng, Yiyuan Zhang, Tao Yang +4 authors
Direct end-to-end training of latent generative models avoids collapse via entropy preservation and asymmetric dynamics, using a generation-first strategy to achieve state-of-the-art image synthesis and unified multimodal generation.
Tianfu Wang, Zhezheng Hao, Xilin Xia +9 authors
This survey defines agentic artifact creation as stateful, feedback-driven construction of deliverables by AI systems and analyzes 259 works across artifact families, settings, and evaluation practices to propose principles for accountable control.
Kang Liao, Yihang Luo, Xiao-Ming Wu +7 authors
Puffin-World is a unified multimodal framework that jointly models physics, geometry, and appearance for physically consistent 3D world generation, reconstruction, and closed-loop exploration.
Venus Team, Zhuohan Cai, Haoxing Chen +28 authors
UI-Venus-2 is a general-purpose multimodal GUI agent that uses unified reasoning-action loops, expanded environment coverage, and robust verification to enable reliable real-world digital automation.
Zihan Qiu, Zekun Wang, Xiao Li +33 authors
Qwen3.8-Flash-Next is a sparse mixture-of-experts architecture combining hybrid gated delta-net and sparse attention layers, gated residual branches, and off-accelerator n-gram embeddings to improve efficiency, capability, and training stability.
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