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。
686 篇论文 · 按点赞排序
Lianghua Huang, Zhifan Wu, Wei Wang +21 authors
Wan-Streamer is a unified, end-to-end multimodal model that enables real-time audio-visual interaction through causal attention mechanisms and integrated processing of visual, audio, and text modalities.
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.
Weijie Wang, Xiaoxuan He, Youping Gu +9 authors
World-R1 framework improves video generation by incorporating 3D constraints through reinforcement learning and specialized text datasets while maintaining visual quality and scalability.
Yanqi Dai, Yuxiang Ji, Xiao Zhang +3 authors
MathForge enhances mathematical reasoning in large models through a dual framework combining difficulty-aware policy optimization and multi-aspect question reformulation to address limitations in existing reinforcement learning methods.
Jisang Han, Seonghu Jeon, Jaewoo Jung +7 authors
A geometric action model leverages pretrained geometric foundation models to enable language-conditioned manipulation policies with improved accuracy, robustness, and efficiency in 3D physical environments.
Alexander Panfilov, David Schmotz, Ilia Shumailov +5 authors
Encrypted reasoning traces shared across sessions and models can be intercepted and injected into weaker models to extract proprietary reasoning, private data, hidden hazards, and hidden prompts.
Jiabin Hua, Hengyuan Xu, Aojie Li +4 authors
A diffusion framework called PixelSmile is introduced that disentangles facial expression semantics through symmetric joint training and contrastive learning to enable precise, controllable, and fine-grained expression editing with robust identity preservation.
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.
Yu Zeng, Wenxuan Huang, Zhen Fang +13 authors
Vision-DeepResearch benchmark addresses limitations in evaluating visual-textual search capabilities of multimodal models by introducing realistic evaluation conditions and improving visual retrieval through multi-round cropped-search workflow.
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.
Weian Mao, Xi Lin, Wei Huang +5 authors
TriAttention addresses KV cache memory bottlenecks in LLMs by leveraging Q/K vector concentration in pre-RoPE space to improve key importance estimation and enable efficient long-context generation.
Yongheng Zhang, Ziang Liu, Jiaxuan Zhu +17 authors
Large Language Models are evolving from conversational systems to integrated AI colleagues with enhanced reasoning capabilities and persistent work environments.
Yanlun Tu, Huacan Wang, Ziyue Zhou +10 authors
SemaPLC is a verification-gated agent harness that validates generated PLC logic through external compilation and live runtime execution, achieving higher verified pass rates than baseline methods.
Zhengyang Sun, Yu Chen, Xin Zhou +4 authors
NUMINA enhances text-to-video diffusion models' numerical accuracy through a training-free identify-then-guide framework that uses attention heads to detect layout inconsistencies and refine object counts.
Bing Zhao, Chenfei Wu, Deqing Li +72 authors
Qwen-Image-2.0 is an advanced image generation model that combines high-fidelity synthesis with precise editing capabilities through a unified framework using Qwen3-VL as condition encoder and Multimodal Diffusion Transformer for joint modeling.
Wenhao Zeng, Yuling Shi, Xiaodong Gu +10 authors
A Dockerless environment-free agentic patch verifier improves code patch evaluation accuracy and enables effective post-training without execution-based verification costs.
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.
Yaorui Shi, Yuxin Chen, Zhengxi Lu +6 authors
Skill1 is a unified framework that trains a single policy to simultaneously evolve skill selection, utilization, and distillation capabilities using a shared task-outcome objective, demonstrating superior performance over existing baselines in complex task environments.
Yukang Chen, Luozhou Wang, Wei Huang +13 authors
LongLive-2.0 presents an NVFP4-based parallel infrastructure for long video generation that addresses training and inference bottlenecks through sequence-parallel autoregressive training and diffusion model tuning.
Zhengxi Lu, Zhiyuan Yao, Zhuowen Han +8 authors
SDAR enhances reinforcement learning for multi-turn agent training by integrating self-distillation through a sigmoid gate that selectively strengthens positive token-level guidance while mitigating negative teacher rejections.
Cheng Qian, Wenting Zhao, Liangwei Yang +6 authors
Stronger models can build inference-time harnesses that substantially improve weaker models' task performance without parameter updates by offloading reasoning into structured code and routing.
Muxi Diao, Lele Yang, Wuxuan Gong +6 authors
Entropy-Adaptive Fine-Tuning addresses catastrophic forgetting in supervised fine-tuning by using token-level entropy to distinguish uncertainty from knowledge conflict, enabling better preservation of general capabilities.
Tu Hu, Ronghao Chen, Shuo Zhang +9 authors
Controlled Self-Evolution method improves code generation through diversified initialization, feedback-guided genetic evolution, and hierarchical memory to enhance exploration efficiency and solution quality.
Guibin Zhang, Leo Lu, Fangzhou Xie +13 authors
JIT-Agent is a trainable model that synthesizes adaptive agent harnesses for off-the-shelf LLMs, improving performance across diverse models and tasks.
Xinlei Yu, Gen Li, Qingyi Si +13 authors
DOPD addresses privilege illusion in on-policy distillation by dynamically routing token-level supervision between teacher and student policies based on advantage gaps and probabilities, improving capability transfer in large and vision-language models.
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.
Ximing Lu, David Acuna, Jaehun Jung +12 authors
Golden Goose synthesizes unlimited RLVR tasks from unverifiable internet text by creating multiple-choice question-answering versions of fill-in-the-middle tasks, enabling large-scale training and achieving state-of-the-art results in cybersecurity and other domains.
Zhongming Yu, Hengjia Yu, Boqin Yuan +12 authors
CodeNib provides reusable multi-view repository indexing with faster updates and reduced context tokens while maintaining accurate navigation across code edits.
Jiwen Liu, Shujuan Li, Zhixue Fang +8 authors
A unified framework for camera motion cloning that uses grid motion videos as representation and integrates multimodal diffusion transformers for enhanced video generation control.
Yaxuan Li, Yuxin Zuo, Bingxiang He +8 authors
On-policy distillation dynamics in large language models depend on compatible thinking patterns between teacher and student models, with successful distillation characterized by alignment on high-probability tokens and requiring teachers to provide novel capabilities beyond student training data.
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