Proposes Contextual Dual Learning Algorithm with Listwise Distillation (CDLA-LD) to address position and contextual biases in unbiased learning to rank, improving real-world performance.

Lulu Yu, Keping Bi, Shiyu Ni et al.

Anim-Director employs GPT-4-driven multimodal models for fully autonomous, controllable animation video generation from simple narratives.

Yunxin Li, Haoyuan Shi, Baotian Hu et al.

Proposes fixed and adaptive kNN-UCB methods for unbounded contexts, achieving near-minimax regret bounds, with the adaptive approach nearly optimal across all regimes.

Puning Zhao, Rongfei Fan, Shaowei Wang et al.

ContactSDF employs signed distance functions (SDF) to model multi-contact dynamics, enabling efficient collision detection and time-stepping for dexterous manipulation.

Wen Yang, Wanxin Jin

ConVerSum employs contrastive learning for data-efficient cross-lingual summarization, outperforming baselines in low-resource settings.

Sanzana Karim Lora, M. Sohel Rahman, Rifat Shahriyar

Math-PUMA uses 692K alignment pairs and three-stage training to reduce the text–vision gap in mathematical reasoning.

Wenwen Zhuang, Xin Huang, Xiantao Zhang et al.

Proposes Meta Agent Search, an automated code-based agent discovery method outperforming manual designs with strong cross-domain transfer.

Shengran Hu, Cong Lu, Jeff Clune

Proposes a derivative-free guidance method using soft value functions integrated into diffusion models for efficient goal-oriented generation without model fine-tuning.

Xiner Li, Yulai Zhao, Chenyu Wang et al.

Combining LLMs with web retrieval improves misinformation detection by 20%.

Jacob-Junqi Tian, Hao Yu, Yury Orlovskiy et al.

RAVE checklist offers 15 recommendations to tackle challenges in automated driving system safety studies.

John M. Scanlon, Eric R. Teoh, David G. Kidd et al.

EEPPR uses 3D correlation on event streams to estimate periodic phenomena frequency with 0.1% error, outperforming existing methods.

Jakub Kolář, Radim Špetlík, Jiří Matas

DC3DO combines LION and diffusion models for zero-shot 3D shape classification, achieving 12.5% improvement over multi-view methods.

Nursena Koprucu, Meher Shashwat Nigam, Shicheng Xu et al.

Introduces OpenEP task and OpenEPBench dataset, combined with StkFEP framework, for open-ended future event prediction with multi-perspective, diverse outputs.

Yong Guan, Hao Peng, Xiaozhi Wang et al.

UniT uses VQGAN to learn tactile features from one simple object and transfers zero-shot to multiple tasks.

Zhengtong Xu, Raghava Uppuluri, Xinwei Zhang et al.

VAB benchmark evaluates large multimodal models as visual agents across diverse scenarios; behavior cloning significantly improves open model performance.

Xiao Liu, Tianjie Zhang, Yu Gu et al.

Integrating Active Inference with topological mapping enables rapid environment structure learning in navigation agents, outperforming CSCG with fewer steps and no prior environment knowledge.

Daria de Tinguy, Tim Verbelen, Bart Dhoedt

Proposes Speculative Diffusion Decoding (SpecDiff), achieving up to 7.2× speedup by integrating discrete diffusion models for parallel sequence generation.

Jacob K Christopher, Brian R Bartoldson, Tal Ben-Nun et al.

SWIFT supports 550+ LLMs and 200+ MLLMs, integrating multiple training techniques for scalable, efficient fine-tuning.

Yuze Zhao, Jintao Huang, Jinghan Hu et al.

Proposes multi-agent LLM framework for automated data storytelling, with 1494 real-world examples.

Mohammed Saidul Islam, Md Tahmid Rahman Laskar, Md Rizwan Parvez et al.

Unsupervised multimodal embedding guides GFlowNets to generate molecules mimicking cell morphology.

Stephen Zhewen Lu, Ziqing Lu, Ehsan Hajiramezanali et al.