Introduces ScaMo framework, validating that motion generation performance follows a logarithmic scaling law with compute, with model size and vocabulary size following power laws.

Shunlin Lu, Jingbo Wang, Zeyu Lu et al.

A qualitative study of 24 experts maps 26 LLM4SE challenges across seven software-engineering dimensions.

Cuiyun Gao, Xing Hu, Shan Gao et al.

PA-RAG introduces multi-perspective preference optimization, significantly improving RAG generators' informativeness, robustness, and citation accuracy, with an average gain of 13.97%.

Jiayi Wu, Hengyi Cai, Lingyong Yan et al.

Introduced VSI-Bench, a video-based benchmark, revealing models achieve 45% accuracy in spatial reasoning, subhuman but improving with cognitive map generation.

Jihan Yang, Shusheng Yang, Anjali W. Gupta et al.

VideoDPO employs OmniScore for multi-dimensional preference alignment in video diffusion, significantly improving visual fidelity and semantic accuracy.

Runtao Liu, Haoyu Wu, Zheng Ziqiang et al.

MetaMorph employs VPiT to enable a pretrained LLM for joint visual understanding and generation, achieving high performance with minimal data.

Shengbang Tong, David Fan, Jiachen Zhu et al.

Rango uses retrieval-augmented LLMs for automated proof synthesis, achieving 32% success rate, surpassing state-of-the-art by 29%.

Kyle Thompson, Nuno Saavedra, Pedro Carrott et al.

InstructSeg unifies image and video instructed segmentation using multi-modal large language models, achieving state-of-the-art results with a single end-to-end framework.

Cong Wei, Yujie Zhong, Haoxian Tan et al.

This paper surveys inference optimization techniques for Mixture of Experts models across model, system, and hardware levels.

Jiacheng Liu, Peng Tang, Wenfeng Wang et al.

Mix-LN combines Pre-LN and Post-LN to enhance deep LLM performance, showing superior results on models from 70M to 7B.

Pengxiang Li, Lu Yin, Shiwei Liu

Introduced Open Universal Arabic ASR Leaderboard to evaluate multi-dialect models and reveal generalization capabilities.

Yingzhi Wang, Anas Alhmoud, Muhammad Alqurishi

Introduces RAG-RewardBench, a benchmark evaluating 45 reward models across four challenging RAG scenarios, revealing significant limitations in current models' preference alignment.

Zhuoran Jin, Hongbang Yuan, Tianyi Men et al.

Proposed object, embedding, and VLM-based metrics achieve 0.55-0.87 correlation with human ratings for automatic image transcreation evaluation.

Simran Khanuja, Vivek Iyer, Claire He et al.

Introduces Policy Decorator, a model-agnostic online residual policy framework, boosting large imitation policies’ success rates by 20-35% in robotic tasks.

Xiu Yuan, Tongzhou Mu, Stone Tao et al.

Exbody2 employs automated data filtering and teacher-student reinforcement learning to enable humanoid robots to perform expressive, dynamic motions with superior tracking accuracy, surpassing prior methods.

Mazeyu Ji, Xuanbin Peng, Fangchen Liu et al.

Graph mixing analysis reveals how local and global strategies affect membership inference attack vulnerability in decentralized learning.

Ousmane Touat, Jezekael Brunon, Yacine Belal et al.

Survey on recommendation unlearning, addressing method and challenges to erase specific training data memory.

Yuyuan Li, Xiaohua Feng, Chaochao Chen et al.

CG-Bench is a clue-grounded QA benchmark for long video understanding with 12,129 QA pairs.

Guo Chen, Yicheng Liu, Yifei Huang et al.

This survey reviews multimodal large language models' (MLLMs) in mathematical reasoning, focusing on benchmarks, methodologies, and challenges, with key results showing >85% accuracy.

Yibo Yan, Jiamin Su, Jianxiang He et al.

Introduced a method for procedural mistake detection using visual self-dialog rationales, enhancing transparency and coherence.

Shane Storks, Itamar Bar-Yossef, Yayuan Li et al.