This paper proves that Transformers trained via gradient descent cannot efficiently learn majority Boolean functions, with error growing exponentially with input dimension.

Bo Chen, Zhenmei Shi, Zhao Song et al.

Proposes scalable Sinkhorn-based algorithms for regularized OT linear models supporting various penalties and loss functions.

Tomasz Kacprzak, Francois Kamper, Michael W. Heiss et al.

VideoAgent2 employs uncertainty-aware chain-of-thought reasoning with plan adjustment, achieving 13.1% average improvement on long video benchmarks.

Zhuo Zhi, Qiangqiang Wu, Minghe shen et al.

JarvisIR employs VLM-controlled multi-expert restoration models, achieving 50% improvement in perception metrics under adverse weather, enhancing autonomous driving robustness.

Yunlong Lin, Zixu Lin, Haoyu Chen et al.

View2CAD employs view-centric B-rep representation and iterative geometric optimization to reconstruct high-precision CAD models from a single RGB-D image, achieving 95% accuracy.

James Noeckel, Benjamin Jones, Adriana Schulz et al.

Multi-variable batch Bayesian optimization in materials research analyzes noise sensitivity and problem landscape effects.

Imon Mia, Armi Tiihonen, Anna Ernst et al.

This tutorial reviews LLM adaptation techniques, including parametric fine-tuning and retrieval-augmented methods, emphasizing multi-stage training and evaluation frameworks.

Zixuan Ke, Yifei Ming, Shafiq Joty

APIGen-MT employs a two-phase blueprint validation and simulated interaction to generate high-quality multi-turn data, surpassing GPT-4o and Claude 3.5.

Akshara Prabhakar, Zuxin Liu, Ming Zhu et al.

Introduces KnowSelf for LLMs' situational self-awareness, using two-stage training to enhance planning with minimal external knowledge.

Shuofei Qiao, Zhisong Qiu, Baochang Ren et al.

Diverse in-context example selection after program decomposition boosts semantic parsing accuracy.

Mayank Kothyari, Sunita Sarawagi, Soumen Chakrabarti et al.

ScreenSeekeR uses hierarchical reasoning and visual search to boost GUI grounding accuracy to 48.1% in high-res professional settings.

Kaixin Li, Ziyang Meng, Hongzhan Lin et al.

AD-GPT combines Llama3 and BERT to enhance Alzheimer's disease information retrieval accuracy.

Ziyu Liu, Lintao Tang, Zeliang Sun et al.

Introduced RISEBench, a benchmark for reasoning-based visual editing; top model GPT-4o-Image scores only 28.8%, highlighting significant gaps.

Xiangyu Zhao, Peiyuan Zhang, Kexian Tang et al.

HyperRAG leverages KV-cache reuse to boost RAG reranker efficiency by 2-3x, maintaining high quality.

Yuwei An, Yihua Cheng, Seo Jin Park et al.

MultiBLiMP 1.0 employs an automated pipeline leveraging UD and UniMorph to generate over 128,000 minimal pairs across 101 languages, evaluating large language models' formal syntactic competence.

Jaap Jumelet, Leonie Weissweiler, Joakim Nivre et al.

Multi-SWE-bench covers 7 languages, with expert annotations, evaluating LLMs' performance in multilingual issue resolution.

Daoguang Zan, Zhirong Huang, Wei Liu et al.

Proposes RASP, a differentiable rendering framework using multi-view shadows to optimize complex 3D object packing.

Soumyaratna Debnath, Ashish Tiwari, Kaustubh Sadekar et al.

Proposes multi-layered memory combining text, KV cache, parameters, and hidden states to enhance long-term memory in LLMs.

Lianlei Shan, Shixian Luo, Zezhou Zhu et al.

SkyReels-A2 employs video diffusion transformers with multi-modal joint embedding to generate controllable videos with high element fidelity.

Zhengcong Fei, Debang Li, Di Qiu et al.

Proposes WoTE framework using BEV world model for online trajectory evaluation, achieving state-of-the-art results.

Yingyan Li, Yuqi Wang, Yang Liu et al.