Daily Paper Cast

🤗 Upvotes: 52 | cs. LG, cs. AI Authors: Zhengze Zhou, Hejian Sang Title: LatentPress: Context Compression Beyond Text and Vision Arxiv: http://arxiv.org/abs/2609.01507v2 Abstract: Compressed context is usually carried as human-readable text or as rendered images that must be decoded, even when its consumer is a language model. We introduce LatentPress, which writes conversational histories and lo...

🤗 Upvotes: 51 | cs. AI Authors: Sergii Kozyrev, Davyd Maiboroda Title: Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLM Arxiv: http://arxiv.org/abs/2609.04098v1 Abstract: Hybrid LLMs pair softmax attention with linear-attention layers such as Gated DeltaNet (GDN), whose recurrent state summarizes the context in fixed size. Early community 4-bit...

🤗 Upvotes: 50 | cs. CL Authors: Heng Wang, Jielin Qiu, Wenting Zhao, Cheng Qian, Liangwei Yang, Jiawei Han, Heng Ji, Silvio Savarese, Shelby Heinecke, Huan Wang Title: Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning Arxiv: http://arxiv.org/abs/2609.03430v1 Abstract: Large language models achieve superior performance on tasks that require extended reasoning, but long chains...

🤗 Upvotes: 43 | cs. AI, cs. CL Authors: Zixuan Fu, Bingxiang He, Yuxin Zuo, Haohuan Huang, Jinqian Zhang, Ruhang Xiao, Cheng Qian, Qinyu Luo, Huan-ang Gao, Yudong Wang, Zhiyuan Liu, Ning Ding, Chaojun Xiao Title: Rethinking On-Policy Distillation of Large Language Models II: One Training Example Arxiv: http://arxiv.org/abs/2609.04172v1 Abstract: On-policy distillation (OPD) combines student-gener...

🤗 Upvotes: 29 | cs. CV Authors: Kang Liao, Yihang Luo, Xiao-Ming Wu, Linyi Jin, Size Wu, Chunyu Lin, Yao Zhao, Fei Wang, Wei Li, Chen Change Loy Title: Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States Arxiv: http://arxiv.org/abs/2609.04196v1 Abstract: We propose Puffin-World, a unified multimodal architecture that integrates physical understanding, spatial simulation,...

🤗 Upvotes: 23 | cs. AI, cs. CL Authors: Jie Wu, Zhenru Zhang, Beichen Zhang, Xuwu Wang, Yuhui Su, Mouxiang Chen, Peng Wang, Zhihai Wang, Que Shen, Hao Zhou, An Yang, Fei Huang, Yujiu Yang, Dayiheng Liu Title: Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments Arxiv: http://arxiv.org/abs/2609.04148v1 Abstract: As terminal-based code agents become prevalent, agent tra...

🤗 Upvotes: 257 | cs. AI, cs. CL Authors: Jianlyu Chen, Yuyang Hu, Hongjin Qian, Jiawei Liu, Wenqing Wei, Xiaolong Chen, Defu Lian, Zhicheng Dou, Chaozhuo Li, Qiwei Ye, Zheng Liu Title: Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills Arxiv: http://arxiv.org/abs/2609.02749v1 Abstract: Autonomous agents are beginning to carry out machine-learning (ML) research end to end. These agent...

🤗 Upvotes: 103 | cs. CV Authors: Junchao Huang, Guian Fang, Shengju Qian, Xianghao Kong, Zhuoran Zhao, Wei Huang, Yihua Du, Zixin Zhang, Justin Cui, Yuchao Gu, Yukang Chen, Xinting Hu, Tianyu He, Shaoshuai Shi, Zhuotao Tian, Xin Wang, Mike Zheng Shou, Li Jiang Title: SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models Arxiv: http://arxiv.org/abs/2609.02886v1 Abstract: We...

🤗 Upvotes: 70 | cs. CL Authors: Yuling Shi, Zhensu Sun, Junsen Dong, Chengcheng Wan, David Lo, Xiaodong Gu Title: EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction Arxiv: http://arxiv.org/abs/2609.02783v1 Abstract: Evaluating LLM agents is essential for guiding their development, yet it has grown prohibitively expensive: a single pass of a frontier model over an agentic benchmark c...

🤗 Upvotes: 60 | cs. IR, cs. CL Authors: Runpeng Dai, Kaili Huang, Changsung Kang, Ciya Liao Title: It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement Learning Arxiv: http://arxiv.org/abs/2609.00638v1 Abstract: Retrieval is the first stage of modern search and advertising systems, selecting a candidate set from a large item universe for downstream ranking and auction. Recen...

🤗 Upvotes: 37 | cs. CL, cs. AI, cs. LG Authors: Namgyu Ho, Huzama Ahmad, Woosung Koh, Se-Young Yun, Tal Schuster, Cicero Nogueira dos Santos Title: Language Models Can Control Their Own Attention Arxiv: http://arxiv.org/abs/2609.02737v1 Abstract: Language models spend most of their attention on a small fraction of context, yet they read the entire KV cache to find the few tokens that matter. If t...

🤗 Upvotes: 24 | cs. CV, cs. CL Authors: Chaohao Yuan, Ruifeng Yuan, Zhuoxu Huang, Yu Rong, Hong Cheng, Hou Pong Chan, Chenghao Xiao Title: On the Design Fundamentals of Pixel Text Representation Learning Arxiv: http://arxiv.org/abs/2609.01147v1 Abstract: Text-rich visual inputs require models that can read, retrieve, and compress language directly in pixel space, yet existing pixel-text encoders...

🤗 Upvotes: 196 | cs. CL Authors: Ke Yang, Chenglong Wang, Michel Galley, Chandan Singh, Jeevana Priya Inala, ChengXiang Zhai, Jianfeng Gao Title: StudentSim: Training LLM-based Student Simulators Arxiv: http://arxiv.org/abs/2609.01591v1 Abstract: AI tutors are most useful when they adapt to each student's strengths, weaknesses, and preferred guidance, but evidence about which guidance works for w...

🤗 Upvotes: 53 | cs. LG Authors: Shaowen Wang, Ge Zhang, Kairong Luo, Yuhao Wu, Shaofan Liu, Jiaheng Liu, Wenhao Huang, Shen Yan, Jian Li Title: SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers Arxiv: http://arxiv.org/abs/2609.01343v1 Abstract: Looped Transformers increase effective depth by iterating a shared block of layers, but most evaluations compare at fixed model size, confla...

🤗 Upvotes: 49 | cs. AI, cs. CL, cs. CV, cs. LG Authors: Venus Team, Zhuohan Cai, Haoxing Chen, Jiaxuan Chen, Weizhi Chen, Changlong Gao, Zhangxuan Gu, Yuan Guo, Yusong Hu, Jianrong Jiang, Jianguo Li, Runze Li, Jinzhen Lin, Zhenyu Ma, Changhua Meng, Han Peng, Xinyu Qiu, Shuheng Shen, Zhongyi Shui, Weiqiang Wang, Ming Wen, Zhuoer Xu, Hang Yan, Kaiwen Yang, Ruilin Yao, Nanjun Yu, Zhengwen Zeng, Lian...

🤗 Upvotes: 47 | cs. CV Authors: Xin Zhou, Zongchuang Zhao, Zhibo Yang, Mingsheng Li, Humen Zhong, Shuai Bai, Du Chu, Ruizhe Chen, Zhaohai Li, Jun Tang, Qiuyue Wang, Mingkun Yang, Jiazhao Zhang, Dayiheng Liu, Dingkang Liang, Xiang Bai Title: Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving Arxiv: http://arxiv.org/abs/2609.00111v1 Abstract: We presen...

🤗 Upvotes: 34 | cs. CV Authors: Xionghao Wu, Yijun Yang, Shiyang Zhou, Haoze Sun, Jianhui Liu, Songsong Yu, Jiyao Zhang, Wenbo Li, Bo Wang, Guoqing Ma, Lin Song, Renjie Liao, Shenghe Zheng, Wei Tang, Xiaojuan Qi, Yanwei Li, Yuan Zhang, Zhuotao Tian, Haoyang Huang, Nan Duan Title: ZimaBlue: Evolving Generalizable World Action Models through Scalable Video Pre-training Arxiv: http://arxiv.org/abs/2...

🤗 Upvotes: 26 | cs. CV, cs. AI Authors: Danze Chen, Zeqing Wang, Ziyue Lin, Xingyi Yang, Yeying Jin Title: H3-World: Turning Language Understanding into World Control Arxiv: http://arxiv.org/abs/2609.01560v1 Abstract: We present H3-World, an efficient framework that turns the 33B MiniMax-H3 video generator into an interactive world model. Our key finding is that, as large video generators become...

🤗 Upvotes: 22 | cs. CL, cs. IR Authors: Jueun Kim, Sungho Park, Wook-Shin Han Title: Hi-Q: Hierarchical Evidence-guided Query Refinement for Multi-Hop Question Answering Arxiv: http://arxiv.org/abs/2608.30468v1 Abstract: A central bottleneck in multi-hop Question Answering (QA) is that the granularity at which a question is expressed often differs from the granularity at which corpus evidence is...

🤗 Upvotes: 64 | cs. CV, cs. SD Authors: Jiashu Zhu, Yanhao Zheng, Ruitian Tian, Rujing Dang, Shen Zhang, Bingze Song, Jiachen Lei, Ruimin Lin, Jiahong Wu, Xiangxiang Chu Title: DreamX-Creator: Democratizing Native Audio-Video Generation at 2K Resolution Arxiv: http://arxiv.org/abs/2608.31106v1 Abstract: Recent video generators often omit audio or synthesize it in a separate stage, limiting recipr...

🤗 Upvotes: 46 | cs. CV Authors: Guangting Zheng, Yiyuan Zhang, Tao Yang, Yunpeng Chen, Rui Zhu, Jiajun Deng, Yanyong Zhang Title: GenFirst: Generation Before Reconstruction for Stable End-to-End Latent Generative Modeling Arxiv: http://arxiv.org/abs/2608.29335v1 Abstract: Latent generative models typically follow a two-stage pipeline, training a variational autoencoder for reconstruction and then...

🤗 Upvotes: 38 | cs. CV, cs. AI Authors: Minghan Qin, Yuang Wang, Xiuyu Yang, Yushi Long, Yujian Zhang, Ruihuan Wang, Kai Ye, Yangang Zhang, Hang Li Title: Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling Arxiv: http://arxiv.org/abs/2608.30821v1 Abstract: Composable scene modeling aims to recover a real indoor scene as complete, editable object assets arranged as observ...

🤗 Upvotes: 36 | cs. LG, cs. CL Authors: Yi Ding, Ruqi Zhang Title: Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement Arxiv: http://arxiv.org/abs/2608.31046v1 Abstract: On-policy distillation (OPD) offers dense token-level supervision as an alternative to the sparse outcome-level advantages of reinforcement learning with verifiable rewards (RLVR). However, the teac...

🤗 Upvotes: 28 | cs. CL Authors: Yuhan Wang, Zhengxi Lu, Yuchen Yan, Kaitao Song, Wenqi Zhang, Weiming Lu, Jun Xiao, Yueting Zhuang, Yongliang Shen Title: PaperGym: Rubric-Centered Evolution for Research-Plan Generation Arxiv: http://arxiv.org/abs/2608.31119v1 Abstract: Research planning is the decisive capability of AI scientists. Yet a research plan admits no verifiable answer, so reinforcement...

🤗 Upvotes: 23 | cs. LG Authors: Jiale Kang, Ziyin Yue, Zheng Zhan, Yangyi Huang, Weiyang Liu Title: Normalized Low-Rank Adaptation Arxiv: http://arxiv.org/abs/2608.31036v1 Abstract: While low-rank adaptation (LoRA) is widely used for parameter-efficient model adaptation, how to regularize its training dynamics for stable and effective optimization remains underexplored. Because LoRA initializes t...