MCJudgeBench evaluates LLM judge accuracy and stability at constraint level, distinguishing intrinsic and procedural inconsistencies.

Jaeyun Lee, Junyoung Koh, Zeynel Tok et al.

Uni-OPD unifies on-policy distillation with dual strategies, boosting multi-task and multi-modal model performance.

Wenjin Hou, Shangpin Peng, Weinong Wang et al.

ProgramBench evaluates LMs' ability to rebuild programs from scratch; the best model passes 95% of tests on only 3% of tasks, spanning CLI tools to complex software.

John Yang, Kilian Lieret, Jeffrey Ma et al.

FSTM employs a two-stage training process with a single SDF to achieve indoor scene geometry and semantic reconstruction, improving speed by 2.3×.

Remi Chierchia, Léo Lebrat, David Ahmedt-Aristizabal et al.

By decomposing travel planning tasks, the study reveals LLMs' deficiencies in implicit constraint inference.

Bo-Wen Zhang, Jin Ye, Peng-Yu Hua et al.

This study compares additive and multiplicative RNN architectures incorporating action embeddings for RL, showing multiplicative models improve efficiency and accuracy.

Matthew Schlegel, Volodymyr Tkachuk, Adam White et al.

Proposes CAFe-DINO, leveraging DINOv3 for open-vocabulary remote sensing segmentation without fine-tuning, outperforming supervised models.

Ryan Faulkenberry, Saurabh Prasad

Proposes SCPRM, integrating schema-aware distance for risk-sensitive multi-hop KG reasoning, improving accuracy by 1.18%.

Jiujiu Chen, Yazheng Liu, Sihong Xie et al.

PFlowNet achieves visual reasoning via variational reinforcement learning, scoring 90.6% on V* Bench.

Yangfu Li, Yuning Gong, Hongjian Zhan et al.

Foundation-model-based industrial agents leverage large language models for autonomous decision-making, enhancing human interaction (+37%) and uncertainty handling (+35%).

Vincent Henkel, Felix Gehlhoff, David Kube et al.

Hyp2Former employs hyperbolic hierarchical embeddings to improve open-set panoptic segmentation, achieving state-of-the-art results.

Yao Lu, Rohit Mohan, Florian Drews et al.

Proposes a six-layer semantic autonomy framework combining hybrid deterministic-VLM reasoning and cross-robot memory transfer, enabling efficient indoor robot navigation.

Bogdan Felician Abaza, Andrei-Alexandru Staicu, Cristian Vasile Doicin

POO algorithm optimizes noisy functions with unknown smoothness, error within √ln n of best algorithms.

Jean-Bastien Grill, Michal Valko, Rémi Munos

Introduces InfoLaw, a data-aware scaling law using information theory to predict large language model performance with quality-weighted data and repetition, achieving 0.15% loss prediction error.

Fengze Liu, Weidong Zhou, Binbin Liu et al.

NTIRE 2026 Challenge introduces RetinexFormerRefine, achieving SSIM of 0.5654 with models under 1MB for low-light image enhancement.

Jiebin Yan, Chenyu Tu, Weixia Zhang et al.

Proposed a planner-centric multi-agent framework, significantly improving long-horizon task success rates.

Wenyi Wu, Sibo Zhu, Kun Zhou et al.

MIRA scores condition distribution accuracy via sample regions, enabling scalable Bayesian model validation and comparison.

Sammy Sharief, Justine Zeghal, Gabriel Missael Barco et al.

TMD-Bench introduces a multi-level evaluation framework for music-dance co-generation, showcasing RhyJAM's competitive rhythmic synchronization.

Xiaoda Yang, Majun Zhang, Changhao Pan et al.

Decoupling Exploration and Commitment with Calibration-Aware Generation boosts factuality by up to 13% in long-form outputs.

Wen Luo, Guangyue Peng, Liang Wang et al.

VOFA integrates vision-based policies with force-adaptive control, achieving over 90% success in pushing unknown objects up to 17kg in real and simulated environments.

Zichao Hu, Zifan Xu, Dongsik Chang et al.