InfiniBench uses LLM-guided, cluster-based layout and task-aware camera planning to generate infinite customizable 3D scenes, enhancing spatial reasoning benchmarks.

Haoming Wang, Qiyao Xue, Wei Gao

Muskie learns multi-view geometry through masked completion, reaching 2.38 cm 3D ATE on NAVI.

Wenyu Li, Sidun Liu, Peng Qiao et al.

Deming-cycle-based multi-agent system SciEducator achieves superior scientific video understanding and multimodal education, outperforming SOTA models with 65.31% relevance and 81.88% accuracy.

Zhiyu Xu, Weilong Yan, Yufei Shi et al.

MobileVLA-R1 combines CoT reasoning with GRPO RL, achieving 5% improvement in quadruped robot vision-language control.

Ting Huang, Dongjian Li, Rui Yang et al.

Demonstrates double descent in a decentralized analog resistive network trained via local contrastive rules, validating physical systems' capacity for complex generalization.

Sam Dillavou, Jason W Rocks, Jacob F Wycoff et al.

SketchVerify enhances motion planning quality for physics-aware video generation using sketch-guided verification.

Yidong Huang, Zun Wang, Han Lin et al.

SMILE integrates semantic and lexical precision, achieving efficient and accurate QA evaluation.

Shrikant Kendre, Austin Xu, Honglu Zhou et al.

ReBaPL integrates cyclical SGHMC and representation-space repulsion to enhance multi-modal prompt Bayesian inference, capturing multi-peak posteriors for better generalization.

Yassir Bendou, Omar Ezzahir, Eduardo Fernandes Montesuma et al.

Study shows boundary samples in non-overfitted models are vulnerable to membership inference attacks; proposes logit reweighting defense.

Mona Khalil, Alberto Blanco-Justicia, Najeeb Jebreel et al.

Proposes TwiG framework enabling real-time textual reasoning during visual generation, significantly enhancing semantic richness.

Ziyu Guo, Renrui Zhang, Hongyu Li et al.

Nemotron Elastic achieves efficient many-in-one reasoning by embedding nested submodels, reducing training costs by 360x.

Ali Taghibakhshi, Sharath Turuvekere Sreenivas, Saurav Muralidharan et al.

Proposes AINA, a framework using smart glasses to learn multi-finger robot manipulation from in-the-wild human videos without robot data.

Irmak Guzey, Haozhi Qi, Julen Urain et al.

Proposes a taxonomy of 28 cognitive elements, analyzes 192K model and 54 human reasoning traces, and improves complex reasoning by 66.7%.

Priyanka Kargupta, Shuyue Stella Li, Haocheng Wang et al.

MiMo-Embodied is a unified cross-embodied foundation model integrating autonomous driving and embodied AI, achieving SOTA on 17 embodied AI and 12 autonomous driving benchmarks through multi-stage training.

Xiaoshuai Hao, Lei Zhou, Zhijian Huang et al.

Proposes a convex inverse optimal transport framework for estimating Markov transition matrices from aggregate data, demonstrating high accuracy and robustness in noisy and limited-sample scenarios.

Michele Mascherpa, Axel Ringh, Amirhossein Taghvaei et al.

VLA-Fool framework combines textual, visual, and cross-modal attacks, revealing vulnerabilities in embodied VLA models under multimodal perturbations.

Yuping Yan, Yuhan Xie, Yixin Zhang et al.

Expanding Neural Networks and Tikhonov-NN regularize ill-posed inverse problems; theory gives width O(δ^{-2/θ}) and convergence as noise vanishes.

Lan Wang, Qiao Zhu, Bangti Jin et al.

Introduces weighted Token importance in ColBERT, improving Recall@10 by 1.28% zero-shot and 3.66% with fine-tuning.

Archish S, Ankit Garg, Kirankumar Shiragur et al.

GESC introduces a projection-based interference cancellation in complex space, achieving state-of-the-art accuracy of 84.9% on node classification benchmarks.

Yoonhyuk Choi, Jiho Choi, Jiwoo Kang

QueryGym is an open-source Python toolkit supporting multiple LLM query reformulation methods, integrating BEIR and MS MARCO benchmarks, significantly improving retrieval performance.

Amin Bigdeli, Radin Hamidi Rad, Mert Incesu et al.