Podcast Episodes
Back to SearchCalibri: Enhancing Diffusion Transformers via Parameter-Efficient Calibration
Episode 1686
🤗 Upvotes: 40 | cs.CV
Authors:
Danil Tokhchukov, Aysel Mirzoeva, Andrey Kuznetsov, Konstantin Sobolev
1Â month, 1Â week ago
RealRestorer: Towards Generalizable Real-World Image Restoration with Large-Scale Image Editing Models
Episode 1685
🤗 Upvotes: 39 | cs.CV
Authors:
Yufeng Yang, Xianfang Zeng, Zhangqi Jiang, Fukun Yin, Jianzhuang Liu, Wei Cheng, …
1Â month, 1Â week ago
MACRO: Advancing Multi-Reference Image Generation with Structured Long-Context Data
Episode 1684
🤗 Upvotes: 26 | cs.CV
Authors:
Zhekai Chen, Yuqing Wang, Manyuan Zhang, Xihui Liu
Title:
…
1Â month, 1Â week ago
Voxtral TTS
Episode 1683
🤗 Upvotes: 24 | cs.AI
Authors:
Alexander H. Liu, Alexis Tacnet, Andy Ehrenberg, Andy Lo, Chen-Yo Sun, Guillaume …
1Â month, 1Â week ago
Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Episode 1682
🤗 Upvotes: 27 | cs.CL, cs.LG
Authors:
Jeonghye Kim, Xufang Luo, Minbeom Kim, Sangmook Lee, Dohyung Kim, Jiwon Je…
1Â month, 1Â week ago
MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding
Episode 1681
🤗 Upvotes: 112 | cs.CV
Authors:
Hejun Dong, Junbo Niu, Bin Wang, Weijun Zeng, Wentao Zhang, Conghui He
1Â month, 1Â week ago
WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG
Episode 1680
🤗 Upvotes: 69 | cs.CV
Authors:
Zhen Li, Zian Meng, Shuwei Shi, Wenshuo Peng, Yuwei Wu, Bo Zheng, Chuanhao Li, Ka…
1Â month, 1Â week ago
From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents
Episode 1679
🤗 Upvotes: 43 | cs.AI, cs.CL
Authors:
Ling Yue, Kushal Raj Bhandari, Ching-Yun Ko, Dhaval Patel, Shuxin Lin, Nia…
1Â month, 1Â week ago
SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning
Episode 1678
🤗 Upvotes: 43 | cs.CV, cs.CL
Authors:
Haoyu Huang, Jinfa Huang, Zhongwei Wan, Xiawu Zheng, Rongrong Ji, Jiebo Lu…
1Â month, 1Â week ago
PEARL: Personalized Streaming Video Understanding Model
Episode 1677
🤗 Upvotes: 36 | cs.CV, cs.AI, cs.IR
Authors:
Yuanhong Zheng, Ruichuan An, Xiaopeng Lin, Yuxing Liu, Sihan Yang, …
1Â month, 1Â week ago