"Today's Papers (2025-08-27) - Found 21 papers:

Title: CMPhysBench: A Benchmark for Evaluating Large Language Models in
  Condensed Matter Physics
Authors: Weida Wang, Dongchen Huang, Jiatong Li, Tengchao Yang, Ziyang Zheng, Di Zhang, Dong Han, Benteng Chen, Binzhao Luo, Zhiyu Liu, Kunling Liu, Zhiyuan Gao, Shiqi Geng, Wei Ma, Jiaming Su, Xin Li, Shuchen Pu, Yuhan Shui, Qianjia Cheng, Zhihao Dou, Dongfei Cui, Changyong He, Jin Zeng, Zeke Xie, Mao Su, Dongzhan Zhou, Yuqiang Li, Wanli Ouyang, Yunqi Cai, Xi Dai, Shufei Zhang, Lei Bai, Jinguang Cheng, Zhong Fang, Hongming Weng
Abstract: CMPhysBench evaluates LLMs in condensed matter physics using calculation problems and a new SEED score for partial credit assessment, revealing significant capability gaps....
URL: https://huggingface.co/papers/2508.18124
PDF: https://arxiv.org/pdf/2508.18124.pdf
Tags: 
--------------------------------------------------
Title: VibeVoice Technical Report
Authors: Zhiliang Peng, Jianwei Yu, Wenhui Wang, Yaoyao Chang, Yutao Sun, Li Dong, Yi Zhu, Weijiang Xu, Hangbo Bao, Zehua Wang, Shaohan Huang, Yan Xia, Furu Wei
Abstract: This report presents VibeVoice, a novel model designed to synthesizelong-form speechwith multiple speakers by employingnext-token diffusion,
which is a unified method for modeling continuous data by a...
URL: https://huggingface.co/papers/2508.19205
PDF: https://arxiv.org/pdf/2508.19205.pdf
Tags: 
--------------------------------------------------
Title: TreePO: Bridging the Gap of Policy Optimization and Efficacy and
  Inference Efficiency with Heuristic Tree-based Modeling
Authors: Yizhi Li, Qingshui Gu, Zhoufutu Wen, Ziniu Li, Tianshun Xing, Shuyue Guo, Tianyu Zheng, Xin Zhou, Xingwei Qu, Wangchunshu Zhou, Zheng Zhang, Wei Shen, Qian Liu, Chenghua Lin, Jian Yang, Ge Zhang, Wenhao Huang
Abstract: TreePO, a self-guided rollout algorithm for sequence generation, reduces computational cost and enhances exploration diversity in reinforcement learning for large language models....
URL: https://huggingface.co/papers/2508.17445
PDF: https://arxiv.org/pdf/2508.17445.pdf
Tags: 
--------------------------------------------------
Title: Spacer: Towards Engineered Scientific Inspiration
Authors: Minhyeong Lee, Suyoung Hwang, Seunghyun Moon, Geonho Nah, Donghyun Koh, Youngjun Cho, Johyun Park, Hojin Yoo, Jiho Park, Haneul Choi, Sungbin Moon, Taehoon Hwang, Seungwon Kim, Jaeyeong Kim, Seongjun Kim, Juneau Jung
Abstract: Spacer, a scientific discovery system, uses deliberate decontextualization to generate creative and factually grounded scientific concepts from keyword sets, achieving high accuracy and similarity to ...
URL: https://huggingface.co/papers/2508.17661
PDF: https://arxiv.org/pdf/2508.17661.pdf
Tags: 
--------------------------------------------------
Title: OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive
  Simulation
Authors: Jianwen Jiang, Weihong Zeng, Zerong Zheng, Jiaqi Yang, Chao Liang, Wang Liao, Han Liang, Yuan Zhang, Mingyuan Gao
Abstract: A framework using Multimodal Large Language Models and a specialized Multimodal DiT architecture generates semantically coherent and expressive character animations from multimodal inputs....
URL: https://huggingface.co/papers/2508.19209
PDF: https://arxiv.org/pdf/2508.19209.pdf
Tags: 
--------------------------------------------------
Title: UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior
  Long-Context Learning
Authors: Zihao Huang, Yu Bao, Qiyang Min, Siyan Chen, Ran Guo, Hongzhi Huang, Defa Zhu, Yutao Zeng, Banggu Wu, Xun Zhou, Siyuan Qiao
Abstract: Abstract not available in listing page...
URL: https://huggingface.co/papers/2508.18756
PDF: https://arxiv.org/pdf/2508.18756.pdf
Tags: 
--------------------------------------------------
Title: VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D
  Space
Authors: Lin Li, Zehuan Huang, Haoran Feng, Gengxiong Zhuang, Rui Chen, Chunchao Guo, Lu Sheng
Abstract: VoxHammer is a training-free method that performs precise and coherent 3D editing in latent space, ensuring consistency in preserved regions and high-quality overall results....
URL: https://huggingface.co/papers/2508.19247
PDF: https://arxiv.org/pdf/2508.19247.pdf
Tags: 
--------------------------------------------------
Title: Pixie: Fast and Generalizable Supervised Learning of 3D Physics from
  Pixels
Authors: Long Le, Ryan Lucas, Chen Wang, Chuhao Chen, Dinesh Jayaraman, Eric Eaton, Lingjie Liu
Abstract: PIXIE, a neural network method, predicts physical properties of 3D scenes from visual features, enabling fast and realistic physics simulation using supervised learning and pretrained visual features....
URL: https://huggingface.co/papers/2508.17437
PDF: https://arxiv.org/pdf/2508.17437.pdf
Tags: 
--------------------------------------------------
Title: Autoregressive Universal Video Segmentation Model
Authors: Miran Heo, Sukjun Hwang, Min-Hung Chen, Yu-Chiang Frank Wang, Albert Gu, Seon Joo Kim, Ryo Hachiuma
Abstract: AUSM, an autoregressive universal segmentation model, unifies prompted and unprompted video segmentation by treating it as sequential mask prediction, achieving superior performance and faster trainin...
URL: https://huggingface.co/papers/2508.19242
PDF: https://arxiv.org/pdf/2508.19242.pdf
Tags: 
--------------------------------------------------
Title: Wan-S2V: Audio-Driven Cinematic Video Generation
Authors: Xin Gao, Li Hu, Siqi Hu, Mingyang Huang, Chaonan Ji, Dechao Meng, Jinwei Qi, Penchong Qiao, Zhen Shen, Yafei Song, Ke Sun, Linrui Tian, Guangyuan Wang, Qi Wang, Zhongjian Wang, Jiayu Xiao, Sheng Xu, Bang Zhang, Peng Zhang, Xindi Zhang, Zhe Zhang, Jingren Zhou, Lian Zhuo
Abstract: Abstract not available in listing page...
URL: https://huggingface.co/papers/2508.18621
PDF: https://arxiv.org/pdf/2508.18621.pdf
Tags: 
--------------------------------------------------
Title: CineScale: Free Lunch in High-Resolution Cinematic Visual Generation
Authors: Haonan Qiu, Ning Yu, Ziqi Huang, Paul Debevec, Ziwei Liu
Abstract: CineScale is a novel inference paradigm that enables high-resolution visual generation for both images and videos without extensive fine-tuning, addressing issues of repetitive patterns and high-frequ...
URL: https://huggingface.co/papers/2508.15774
PDF: https://arxiv.org/pdf/2508.15774.pdf
Tags: 
--------------------------------------------------
Title: ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks
Authors: Minghao Li, Ying Zeng, Zhihao Cheng, Cong Ma, Kai Jia
Abstract: We introduce ReportBench, the first systematic benchmark for evaluating research reports generated by Deep Research agents. By leveraging expert-authored survey papers from arXiv as gold standards, Re...
URL: https://huggingface.co/papers/2508.15804
PDF: https://arxiv.org/pdf/2508.15804.pdf
Tags: 
--------------------------------------------------
Title: ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large
  Language Models
Authors: Qianyu He, Siyu Yuan, Xuefeng Li, Mingxuan Wang, Jiangjie Chen
Abstract: ThinkDial is an open-source framework that implements controllable reasoning in large language models through discrete operational modes, achieving performance while reducing computational effort....
URL: https://huggingface.co/papers/2508.18773
PDF: https://arxiv.org/pdf/2508.18773.pdf
Tags: 
--------------------------------------------------
Title: FastMesh:Efficient Artistic Mesh Generation via Component Decoupling
Authors: Jeonghwan Kim, Yushi Lan, Armando Fortes, Yongwei Chen, Xingang Pan
Abstract: A framework for efficient artistic mesh generation reduces redundancy by separating vertex and face generation, using an autoregressive model for vertices and a bidirectional transformer for faces, an...
URL: https://huggingface.co/papers/2508.19188
PDF: https://arxiv.org/pdf/2508.19188.pdf
Tags: 
--------------------------------------------------
Title: MovieCORE: COgnitive REasoning in Movies
Authors: Gueter Josmy Faure, Min-Hung Chen, Jia-Fong Yeh, Ying Cheng, Hung-Ting Su, Yung-Hao Tang, Shang-Hong Lai, Winston H. Hsu
Abstract: MovieCORE is a video question answering dataset that uses multiple large language models to generate deep cognitive questions, and introduces an agentic enhancement module to improve VQA model perform...
URL: https://huggingface.co/papers/2508.19026
PDF: https://arxiv.org/pdf/2508.19026.pdf
Tags: 
--------------------------------------------------
Title: Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning
  Tasks
Authors: Taishi Nakamura, Satoki Ishikawa, Masaki Kawamura, Takumi Okamoto, Daisuke Nohara, Jun Suzuki, Rio Yokota
Abstract: MoE models introduce sparsity that affects memorization and reasoning capabilities differently in large language models, with reasoning performance potentially regressing despite increased parameters....
URL: https://huggingface.co/papers/2508.18672
PDF: https://arxiv.org/pdf/2508.18672.pdf
Tags: 
--------------------------------------------------
Title: Training Language Model Agents to Find Vulnerabilities with CTF-Dojo
Authors: Terry Yue Zhuo, Dingmin Wang, Hantian Ding, Varun Kumar, Zijian Wang
Abstract: CTF-Dojo, a large-scale executable runtime with 658 CTF challenges, enables rapid training of LLM-based agents with verifiable feedback, achieving state-of-the-art performance in competitive benchmark...
URL: https://huggingface.co/papers/2508.18370
PDF: https://arxiv.org/pdf/2508.18370.pdf
Tags: 
--------------------------------------------------
Title: QueryBandits for Hallucination Mitigation: Exploiting Semantic Features
  for No-Regret Rewriting
Authors: Nicole Cho, William Watson, Alec Koppel, Sumitra Ganesh, Manuela Veloso
Abstract: QueryBandits, a bandit framework, effectively mitigates hallucinations in LLMs by proactively rewriting queries based on linguistic features, outperforming static prompting strategies....
URL: https://huggingface.co/papers/2508.16697
PDF: https://arxiv.org/pdf/2508.16697.pdf
Tags: 
--------------------------------------------------
Title: ObjFiller-3D: Consistent Multi-view 3D Inpainting via Video Diffusion
  Models
Authors: Haitang Feng, Jie Liu, Jie Tang, Gangshan Wu, Beiqi Chen, Jianhuang Lai, Guangcong Wang
Abstract: ObjFiller-3D uses video editing models to achieve high-quality and consistent 3D object completion, outperforming previous methods in terms of reconstruction fidelity and practical deployment....
URL: https://huggingface.co/papers/2508.18271
PDF: https://arxiv.org/pdf/2508.18271.pdf
Tags: 
--------------------------------------------------
Title: Demystifying Scientific Problem-Solving in LLMs by Probing Knowledge and
  Reasoning
Authors: Alan Li, Yixin Liu, Arpan Sarkar, Doug Downey, Arman Cohan
Abstract: SciReas and SciReas-Pro benchmarks, along with KRUX framework, provide insights into the distinct roles of knowledge and reasoning in scientific tasks, highlighting critical bottlenecks and improvemen...
URL: https://huggingface.co/papers/2508.19202
PDF: https://arxiv.org/pdf/2508.19202.pdf
Tags: 
--------------------------------------------------
Title: Unraveling the cognitive patterns of Large Language Models through
  module communities
Authors: Kushal Raj Bhandari, Pin-Yu Chen, Jianxi Gao
Abstract: A network-based framework links cognitive skills, LLM architectures, and datasets, revealing unique emergent skill patterns in LLMs that benefit from dynamic, cross-regional interactions....
URL: https://huggingface.co/papers/2508.18192
PDF: https://arxiv.org/pdf/2508.18192.pdf
Tags: 
--------------------------------------------------"