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。
Björn Engdahl, Adrian Kosowski, Jan Chorowski +6 authors
A 150M-parameter reasoning model using recurrent latent reasoning and in-context learning achieves a new cost-accuracy frontier on ARC-AGI-1.
50 篇论文 · 按点赞排序
Xuan He, Cong Wei, Yuhao Cheng +20 authors
VGI-bench evaluates visual reasoning in video generation models through 27 tasks, revealing limited reliability and self-correction capabilities.
Zihao Liu, Xiaolong Shen, Zhenglin Zhou +2 authors
Latent-to-4D enables reusable direct 4D generation from video diffusion latents via alignment with a pretrained decoder and spatiotemporal attention, transferring across generators without retraining.
Mind Lab, Vin Bo, Asher Cai +73 authors
Macaron-V1 is an open agent-model family that uses a Mixture-of-LoRA architecture and recursive self-improvement to enable continual learning and collaboration across specialized tasks.
Weiliang Chen, Haowen Sun, Jun Gao +40 authors
HarnessEval-W uses hierarchical sub-agents to decompose world-model evaluations into verifiable reasoning chains that justify scores with transparent evidence.
Jianyu Wu, Yizhou Wang, Encheng Su +2 authors
Dual-Anchored Policy Distillation resolves privilege illusion in on-policy self-distillation by aligning matched-information paths and reducing reliance on privileged guidance, improving performance across model scales.
Zhuoyang Qian, Biao Wu, Yiran Wang +6 authors
Spark-to-Paper is a lightweight, composable workflow inside coding assistants that generates research papers by separating planning from reporting, enforcing evidence-based claim revision, and using integrity checks to reduce fabrication.
Zihao Wu, Hongyao Tang, Yi Ma +9 authors
Off-policy reinforcement learning stabilizers vary with data availability, motivating regime-aware algorithms that adapt normalization and Q-function clipping to improve efficiency across CPU and GPU-parallel training.
Shuo Liang, Yixing Ma, Pengfei Zhou +32 authors
A new benchmark for AI-generated video detection reveals that current detectors fail to generalize across realistic crisis-related videos and become less reliable as content spreads socially.
Yunhao Chen, Xin Wang, Yixu Wang +6 authors
OpenART introduces a scalable red-teaming arena with evolving stateful environments to evaluate long-horizon AI agent safety, using the EMHA attack policy to expose increasing failure rates as task complexity grows.
Zhongzhi Li, Yucheng Shi, Zongxia Li +8 authors
Recursive verified synthesis generates scalable long-horizon terminal-agent training data, substantially improving model performance on terminal benchmarks through supervised fine-tuning and reinforcement learning.
Chengsong Huang, Zifeng Wang, Rujun Han +14 authors
EnvHarness and EnvRigger dynamically reshape static environments via programmable plugins to target agent weaknesses and improve reinforcement learning co-evolution.
Yijiang Li, Bingyang Wang, Yijun Liang +3 authors
Unsupervised on-policy self-distillation improves large language models by using internal consistency and majority-vote pseudo-solutions to correct confident errors without external supervision.
Apodex Team, B. An, B. Li +68 authors
Apodex 1.1 improves sustained, verifiable progress on complex real-world tasks by scaling executable environments and training agents to coordinate long-horizon work with state maintenance and recovery.
Zhiyuan Jiang, Fangrui Huang, Hanwen Xing +6 authors
Skills enhance LLM agents primarily by stabilizing execution through procedural anchoring rather than injecting missing knowledge, though retrieval bottlenecks and brittle assumptions limit their effectiveness.
Yijiang Li, Yijun Liang, Yunjie Tian +6 authors
Self-supervised visual on-policy distillation improves small vision-language models by distilling from original images into strongly augmented student views without privileged annotations or larger teachers.
Qianggang Ding, Xingyao Wang, Rui Feng +19 authors
Combodied Agents integrate digital and embodied tools into a closed-loop framework that models individual human-state trajectories over time to provide proportionate, consent-aware support.
Keyu Tu, Zhuowei Chen, Mengqi Huang +4 authors
Semantic task completion video generation evaluates whether generated videos achieve intended outcomes with semantic grounding, supported by a curated dataset and vision-language model-based benchmark.
Yu Zhang, Ruiqi Li, Changhao Pan +3 authors
SwanTale is a multi-speaker expressive speech and audio generation model that supports both instruction-based and zero-shot synthesis with high-quality multi-modality outputs.
Liangcai Su, Zhaopeng Feng, Zhuo Chen +13 authors
FrontierChallenge evaluates end-to-end scientific workflows across domains, revealing that frontier models complete only about 20% of tasks despite high partial scores and frequent claims of completion.
Xin Ding, Liang Mi, Mingzhe Huang +12 authors
Zetta is a closed-loop embodied harness that evolves runtime critics and recovery skills online to govern physical execution at action frequency, achieving high success on robot benchmarks with faster inference and scaling self-exploration.
Ziyu Ma, Hailang Huang, Shun Zou +5 authors
LongHorizon-Harness improves long-horizon agent performance by explicitly tracking verified task states outside context via a manage-execute-audit loop.
Yixuan Wang, Yifei Chen, Haichao Zhang +6 authors
SA-MRPO independently standardizes multi-objective rewards and adaptively discounts saturated objectives to redirect optimization toward under-optimized goals.
Liya Zhu, Xin Ma, Tao Liu +35 authors
StartupBench evaluates end-to-end AI agents on real-world startup workflows and reveals that even top models complete only about 30% of tasks, highlighting gaps in instruction following and domain expertise.
Zhifei Xie, Jiaqi Lang, Ze An +7 authors
VoiceMem introduces a dual-brain streaming memory architecture for speech language models that improves retrieval accuracy, emotional personalization, and real-time efficiency.
Qing Zong, Jiayu Liu, Junhao Shen +9 authors
Agentic systems can achieve open-ended improvement through multi-component co-evolution that progressively removes fixed human constraints across agents, environments, and evolution mechanisms.
Zixuan Huang, Yang Zhou, Kaixuan Wang +6 authors
Proposed multiple-choice planning and deferred trajectory verification reduce reasoning bias and improve verifiable autonomous driving decisions.
Pengfei Zhou, Hexin Wang, Zhengfeiyang Zhang +5 authors
Game engines provide executable verification and long-horizon trajectories for reinforcement learning post-training of spatial world models, motivating a human-engine verification paradigm.
Ziheng Qin, Yaxin Lu, Zhangyang Atlas Wang +1 authors
StateM is a runtime system that improves long-horizon agent execution through durable states, recoverable runbooks, and enforceable procedural controls without altering model weights.
Yifan Zhang, Yutong Dai, Juntao Tan +9 authors
DarwinX evolves agent harnesses via population selection with frozen models, improving verified performance across benchmarks without benchmark-specific patches.
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