Introduced MathVerse, a multi-version benchmark with chain-of-thought analysis, revealing most models rely heavily on text rather than visual understanding in math problems.

Renrui Zhang, Dongzhi Jiang, Yichi Zhang et al.

PEFT fine-tunes large models by adjusting minimal parameters, reducing training costs by over 80%.

Zeyu Han, Chao Gao, Jinyang Liu et al.

RCT shows GPT-4 with personalization increases persuasion odds by 81.7%, surpassing humans.

Francesco Salvi, Manoel Horta Ribeiro, Riccardo Gallotti et al.

Unsupervised cross-view geo-localization using projection and re-ranking achieves over 40% pseudo-label accuracy.

Guopeng Li, Ming Qian, Gui-Song Xia

Testing model defenses with the simple ‘Purple’ rule reveals fundamental vulnerabilities, even with perfect definitions.

Taeyoun Kim, Suhas Kotha, Aditi Raghunathan

Proposes a multi-model ensemble and multi-criteria decision approach to select optimal counterfactual explanations, improving trade-offs among quality metrics.

Ignacy Stępka, Mateusz Lango, Jerzy Stefanowski

Proposes a probabilistic forecasting framework using stochastic interpolants and Föllmer processes, leveraging SDEs for high-dimensional condition sampling.

Yifan Chen, Mark Goldstein, Mengjian Hua et al.

LlamaFactory unifies 100+ models for efficient fine-tuning, enabling codeless customization.

Yaowei Zheng, Richong Zhang, Junhao Zhang et al.

Semantic search engine for mathlib4 using large language models and vector similarity, achieving 50%+ improvement over baselines.

Guoxiong Gao, Haocheng Ju, Jiedong Jiang et al.

Introduces the concept of 'effective cutoff' by probing perplexity across data versions, revealing discrepancies between reported and actual knowledge cutoffs in LLMs.

Jeffrey Cheng, Marc Marone, Orion Weller et al.

mPLUG-DocOwl 1.5 improves document understanding via Unified Structure Learning, achieving >10-point SOTA gains on 5/10 benchmarks.

Anwen Hu, Haiyang Xu, Jiabo Ye et al.

Introduces RouterBench, a benchmark with 405k samples, evaluating multi-LLM routing systems for cost and performance.

Qitian Jason Hu, Jacob Bieker, Xiuyu Li et al.

SpatialPIN enhances VLM's 3D reasoning via multi-model prompting, improving spatial VQA and robotics tasks without training.

Chenyang Ma, Kai Lu, Ta-Ying Cheng et al.

Larimar model enables rapid knowledge updates with distributed episodic memory, achieving 8-10x speed improvement.

Payel Das, Subhajit Chaudhury, Elliot Nelson et al.

Proposes CoVR method leveraging visual residuals and large multimodal models for preference inference, achieving 72% success in simulation.

Joonhyung Lee, Sangbeom Park, Yongin Kwon et al.

GL-MSDA method enhances cross-domain performance in grasp detection via global-to-local RGB-D adaptation.

Haoxiang Ma, Ran Qin, Modi shi et al.

VideoAgent integrates structured memory with foundation models, boosting long video understanding by 6.6% on NExT-QA.

Yue Fan, Xiaojian Ma, Rujie Wu et al.

ALDM-Grasping uses diffusion models for zero-shot Sim-to-Real transfer in robot grasping, achieving a 75% success rate.

Yiwei Li, Zihao Wu, Huaqin Zhao et al.

RebQ framework improves average precision from 20.00 to 50.92 and reduces forgetting from 75.95 to 8.56 in missing modality learning.

Shu Zhao, Xiaohan Zou, Tan Yu et al.

DiffUIR employs a selective hourglass mapping strategy with strong condition guidance and shared distribution terms, achieving state-of-the-art performance in multi-task image restoration with only 0.89M parameters.

Dian Zheng, Xiao-Ming Wu, Shuzhou Yang et al.