Daily Paper Cast

🤗 Upvotes: 25 | cs. AI Authors: Fengqi Zhu, Shaoxuan Xu, Jingyang Ou, Zebin You, Yipeng Xing, Huabin Liu, Xiaolu Zhang, Jun Zhou, Zhenzhong Lan, Yankai Lin, Wayne Xin Zhao, Jianguo Li, Chongxuan Li, Ji-Rong Wen Title: LLaDA MoE v2: Scaling Mixture-of-Experts Diffusion Language Models Arxiv: http://arxiv.org/abs/2608.03457v1 Abstract: Diffusion language models (dLLMs) offer an alternative to autor...

🤗 Upvotes: 142 | eess. AS, cs. SD Authors: Yu Zhang, Ruiqi Li, Changhao Pan, Ke Lei, Xiang Yin, Cheng Yang Title: SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Arxiv: http://arxiv.org/abs/2608.02023v2 Abstract: Speech and audio generation is often needed in animation dubbing, audio drama, movies, advertising, games, podcasts, and short-video producti...

🤗 Upvotes: 132 | cs. CV Authors: Ziyu Ma, Hailang Huang, Shun Zou, Yong Wang, Shidong Yang, Yiming Hu, Fei Wei, XiangXiang Chu Title: LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks Arxiv: http://arxiv.org/abs/2608.01964v1 Abstract: Large language model (LLM) agents increasingly undertake long-horizon tasks that require sustained reasoning, tool use, and revision across ma...

🤗 Upvotes: 77 | cs. AI Authors: Jianyu Wu, Yizhou Wang, Encheng Su, Chen Tang, Shixiang Tang Title: DAPD: Dual-Anchored Policy Distillation Arxiv: http://arxiv.org/abs/2608.01735v1 Abstract: On-policy (self) distillation (OPSD) is increasingly adopted for language-model post-training. It strengthens the teacher with privileged information but can induce a privilege illusion: the student learns pr...

🤗 Upvotes: 50 | cs. LG, cs. CL Authors: Junhao Shen, Zhanqiu Zhang, Yiwen Guo, Hong Cheng Title: Progressive Agent Skill Generation via Reinforcement Learning Arxiv: http://arxiv.org/abs/2608.01678v1 Abstract: Existing skill generation methods largely rely on heuristics or pipeline-style consolidation, which must be specially designed for different evidence sources. In contrast, learning-based ap...

🤗 Upvotes: 43 | cs. CV, cs. CL Authors: Kangning Zhang, Yixing Li, Shuai Shao, Qingyao Li, Zhengxi Lu, Zhiyuan Yao, Jianghao Lin, Wenxiang Jiao, Yuan Lu, Weiwen Liu, Weinan Zhang, Yong Yu Title: VAD: Attributing Visual Evidence for Target Reconstruction in Multimodal On-Policy Distillation Arxiv: http://arxiv.org/abs/2607.28590v1 Abstract: Multimodal on-policy distillation (OPD) transfers fine-gr...

🤗 Upvotes: 43 | cs. CV, cs. AI, cs. CL, cs. IR Authors: Tingyu Song, Mingxin Li, Yanzhao Zhang, Dingkun Long, Pengjun Xie, Zhijie Nie, Yilun Zhao, Shu Wu Title: UEmbed: Unified Sparse and Dense Multimodal Embeddings Arxiv: http://arxiv.org/abs/2608.02583v1 Abstract: Sparse retrieval underpins modern search systems, from web search to retrieval-augmented generation. Existing work has introduced Le...

🤗 Upvotes: 31 | cs. AI Authors: Zixuan Huang, Yang Zhou, Kaixuan Wang, Guli Zhang, Hongyan Xie, Yakun Zhu, Hao Geng, Xiaozhi Chen, Yikun Ban, Deqing Wang Title: Deferred Exposure of Future Trajectories for Verifiable Reasoning in Autonomous Driving VLMs Arxiv: http://arxiv.org/abs/2608.01755v2 Abstract: Recent Vision-Language-Action (VLA) models for autonomous driving (AD) increasingly utilize ch...

🤗 Upvotes: 30 | cs. CV Authors: Soslan Kabisov, Gennadiy Savrasov, Maksim Elistratov, Antonio Rodriguez, Daniil Ignatiev, Nikita Gavrilov, Rustam Uzdenov, Alexey I. Boyko, Igor Pasechnik, Anton Konushin, Andrey Kuznetsov, Dmitrii Zhemchuzhnikov Title: CADENA: Stepwise CAD Reverse Engineering Arxiv: http://arxiv.org/abs/2608.00799v1 Abstract: Computer-Aided Design (CAD) underpins modern engineerin...

🤗 Upvotes: 30 | cs. CV Authors: Yuxue Yang, Shuyao Shang, Jiahe Wang, Zitong Zhou, Liang Tan, Junhan Zeng, Ruizhi Li, Junyan Li, Yu Liu, Xiao Yang, Yong Li, Jun Zhu, Hongsheng Li, Tieniu Tan, Lue Fan, Zhaoxiang Zhang Title: WorldExam: Benchmarking World Models from Apparent Appearance to Inherent Reactivity Arxiv: http://arxiv.org/abs/2608.02603v1 Abstract: Controllable video generation models ar...

🤗 Upvotes: 27 | cs. CV Authors: Jiawei Wang, Hao Yu, Yongzhen Hu, Xinyi Yang, Tao Ni, Xin Zhan, Junbo Chen, Xiaowei Zhou, Ruizhen Hu, Sida Peng Title: InfiniSplat: Implicit Gaussian Decoding for Large-Baseline Monocular View Synthesis Arxiv: http://arxiv.org/abs/2608.02437v2 Abstract: Single-image feed-forward 3D Gaussian Splatting (3DGS) aims to directly generate a renderable 3D scene representa...

🤗 Upvotes: 79 | cs. AI Authors: Qinsi Wang, Jing Shi, Huazheng Wang, Kun Wan, Yiran Wu, Bo Liu, Qingyun Wu, Hai Helen Li, Yiran Chen, Handong Zhao, Wentian Zhao Title: From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement Arxiv: http://arxiv.org/abs/2607.23802v2 Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has driven recent...

🤗 Upvotes: 61 | cs. CL Authors: Hao Fei, Yiran Zhao Title: Mental World Modeling Arxiv: http://arxiv.org/abs/2607.27201v1 Abstract: World models enable a predictive substrate for planning and action, yet existing formulations merely answer a physical question: what/where it is, and how will it evolve. Human behavior, however, is driven by hidden mental state (what a person believes, wants, intend...

🤗 Upvotes: 52 | cs. RO Authors: NeoteAI Team, Fudan TEAI Team Title: $N_0$-VTLA: Scaling Vision-Tactile-Language-Action Model with Latent Tactile Tokens Arxiv: http://arxiv.org/abs/2607.23782v1 Abstract: We present $N_0$-VTLA, a vision-tactile-language-action (VTLA) foundation model capable of (1) fine-grained contact-rich manipulation with tactile perception and tactile-feedback control, and (2)...

🤗 Upvotes: 44 | cs. GR, cs. CV Authors: Jiale Xu, Rendong Liang, Yuhao Long, Siyuan Shen, Zangyueyang Xian, Zeyi Xu, Yuanming Hu Title: Meshy T2: Fast Native Mesh Generation with Flow Matching Arxiv: http://arxiv.org/abs/2607.28675v1 Abstract: Polygonal meshes are the standard surface representation of modern 3D pipelines, and generating high-quality meshes with artist-style topology is essential...

🤗 Upvotes: 46 | cs. LG Authors: Fangxu Yu, Weijia Xu, Michael Xu, Tianyi Zhou, Zinan Lin Title: Weak-to-Strong On-Policy Distillation Arxiv: http://arxiv.org/abs/2607.26246v2 Abstract: On-policy distillation (OPD), which aligns a student with the teacher's token-level distribution on the student's own rollouts, is an effective paradigm for transferring capabilities across LLMs. Prevailing approac...

🤗 Upvotes: 32 | cs. AI, cs. CL, cs. CY, cs. HC Authors: Xiangning Lin, Shenzhe Zhu, Shu Yang, Zhenyu Zhang, Haoqian Zhang, Yipeng Zhao, Chengxuan Qian, Tianwei Wang, Ziheng Zhang, Zhenlong Yuan, Dingcheng Wang, Juncheng Wu, Yuan Si, Jiaxin Liu, Baolong Bi, Robert Mahari, Tobin South, Dazza Greenwood, Zexue He, Rishi Bommasani, Sophia Kazinnik, Andreas Haupt, Samuele Marro, Erik Brynjolfsson, Alex...

🤗 Upvotes: 30 | cs. RO Authors: NeoteAI Team, Fudan TEAI Team Title: $N_0$-TWAM: Scaling Tactile-Native World-Action Model for Contact-Rich Manipulation Arxiv: http://arxiv.org/abs/2607.23783v1 Abstract: We present $N_0$-TWAM, a tactile-native world-action model for contact-rich manipulation that predicts both future vision and future contact. To our knowledge, it is the first tactile world-actio...

🤗 Upvotes: 27 | cs. CV Authors: Zilong Chen, Chaorui Deng, Kunchang Li, Hongyi Yuan, Haoqi Fan Title: Scaling Properties of Text Conditioning in Visual Generation Arxiv: http://arxiv.org/abs/2607.29679v1 Abstract: We study empirical scaling properties for text conditioning in visual generation. Such properties have rarely been measured because diffusion loss does not scale with the number of toke...

🤗 Upvotes: 24 | cs. LG, cs. AI, cs. CV, cs. MM, cs. RO Authors: Zhoushun Yu, Xiaoyu Hu, Xiangyu Xu Title: QQWorld: Quantile-Quantile Matching for World Model Regularization Arxiv: http://arxiv.org/abs/2607.28415v1 Abstract: Latent world models enable efficient planning by predicting future states in a compact representation space, but their performance depends critically on the quality of the lea...

🤗 Upvotes: 285 | cs. CL, cs. AI, cs. IR, cs. LG Authors: Bing Yan, Gregory Wolfe, Stefano Martiniani, Kyunghyun Cho Title: AskChem: Claim-Centered Infrastructure for Chemistry Literature Synthesis Arxiv: http://arxiv.org/abs/2607.28618v1 Abstract: Chemistry literature synthesis often requires assembling specific findings scattered across many publications, yet existing literature-search systems p...

🤗 Upvotes: 271 | cs. AI, cs. CV Authors: Hanzhang Zhou, Panrong Tong, Xu Zhang, Quyu Kong, Chenglin Cai, Tianyu Xia, Gongjie Zhang, Jianan Zhang, Long Li, Long Chen, Lei Wang, Gaole Dai, Pengxiang Li, Liangyu Chen, Yue Wang, Steven Hoi Title: Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents Arxiv: http://arxiv.org/abs/2607.28227v1 Abstract: GUI agent...

🤗 Upvotes: 245 | cs. CL, cs. LG Authors: Zeyu Zhang, Ziliang Guo, Yihang Sun, Xichong Zhang, Xixuan Hao, Zehao Lin, Yang Zhang, Xiaoyan Zhao, Tong Shen, Bo Tang, Zhi-Qin John Xu, Junchi Yan, Haofen Wang, Xu Chen, Feiyu Xiong, Zhiyu Li, Tat-Seng Chua Title: Metis: Memory Foundation Model Arxiv: http://arxiv.org/abs/2607.26760v1 Abstract: Recent advances in AI agents have increasingly internalized...

🤗 Upvotes: 158 | cs. CL Authors: Junlin Yang, Che Jiang, Yu Fu, Tianwei Luo, Can Ren, Weizhi Wang, Kaikai Zhao, Hongyi Liu, Yuxin Zuo, Yuru Wang, Yuchen Fan, Kai Tian, Zhenzhao Yuan, Xiaojian Lin, Li Sheng, Rushi Qiang, Guoli Jia, Xingtai Lv, Ermo Hua, Dianqiao Lei, Youbang Sun, Ning Ding, Bowen Zhou, Kaiyan Zhang Title: Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in M...

🤗 Upvotes: 150 | cs. CV Authors: Shuyao Shang, Yuqi Wang, Ruopeng Gao, Xu Chen, Tieniu Tan, Lue Fan, Zhaoxiang Zhang Title: PhiZero: A World Model Built Around Physical Language Arxiv: http://arxiv.org/abs/2607.28624v1 Abstract: We introduce PhiZero, a physical world model built around physical language, a compact discrete representation of world-state transitions. Existing physical world models...