Proposes BridgeNav, a vision-based, instruction-guided indoor-outdoor navigation system achieving 89.55% success rate without priors.

Yuxiang Zhao, Yirong Yang, Yanqing Zhu et al.

Proposes DesignAsCode framework using HTML/CSS for editable and high-fidelity graphic design, outperforming state-of-the-art baselines.

Ziyuan Liu, Shizhao Sun, Danqing Huang et al.

Diamond Maps employs stochastic flow maps for efficient reward alignment, enabling rapid adaptation during inference with minimal computational overhead.

Peter Holderrieth, Douglas Chen, Luca Eyring et al.

This survey organizes graph-based agent memory around extraction, storage, retrieval, and evolution, but reports no unified benchmark or quantitative gain.

Chang Yang, Chuang Zhou, Yilin Xiao et al.

A-GRAE dynamically adjusts exploration incentives and sample difficulty focus, improving GRPO's exploration and adaptation in complex tasks.

Zhiqi Yu, Zhangquan Chen, Mengting Liu et al.

Unified clipping framework using KL3 estimator improves stability and exploration in GRPO, boosting math reasoning performance.

Qingyuan Wu, Yuhui Wang, Simon Sinong Zhan et al.

Proposes MFTR, a multi-field tool retrieval framework using structured representations and dynamic weighting.

Yichen Tang, Weihang Su, Yiqun Liu et al.

EmbedOpt optimizes protein diffusion model embeddings during inference, improving cryo-EM fitting and sparse distance constraints with fewer steps and enhanced robustness.

Minhuan Li, Jiequn Han, Pilar Cossio et al.

GT-SVJ transforms video generative models into energy-based discriminators using contrastive learning, reducing human annotation by 6-65x while improving temporal sensitivity.

Shivanshu Shekhar, Uttaran Bhattacharya, Raghavendra Addanki et al.

Research-level math questions test AI's autonomous reasoning; framework involves encrypted questions, external resource access, and human validation.

Mohammed Abouzaid, Andrew J. Blumberg, Martin Hairer et al.

The paper proposes a novel uncertainty quantification framework for interactive LLM agents, addressing uncertainty in multi-step reasoning.

Changdae Oh, Seongheon Park, To Eun Kim et al.

VISTA enhances VLA visual conditioning via track-following preference optimization, improving success rate by 3.15%.

Yiye Chen, Yanan Jian, Xiaoyi Dong et al.

Proposes EntRGi for discrete diffusion language models, balancing gradient reliability and reward accuracy via entropy-based adaptive interpolation.

Atula Tejaswi, Litu Rout, Constantine Caramanis et al.

LABBench2 enhances AI's real-world biology research capabilities with 1,900 tasks, models' accuracy drops 26%-46%.

Jon M Laurent, Albert Bou, Michael Pieler et al.

VISTA-Bench reveals a significant modality gap in vision-language models when processing visualized text versus pure text, based on multi-task evaluation.

Qing'an Liu, Juntong Feng, Yuhao Wang et al.

NeuroCanvas transforms multichannel EEG into images, improving seizure detection accuracy by 20% and reducing inference latency by 88%.

Yan Chen, Jie Peng, Moajjem Hossain Chowdhury et al.

Proposes Adaptive Prompt Elicitation (APE), using an information-theoretic framework with visual queries to improve user intent alignment in text-to-image generation.

Xinyi Wen, Lena Hegemann, Xiaofu Jin et al.

LinGO uses linguistic graph optimization with LLMs to interpret online uncivil discourse, improving accuracy and F1 scores.

Yuan Zhang, Thales Bertaglia

Inference-time backdoor via chat template reduces accuracy from 90% to 15%.

Ariel Fogel, Omer Hofman, Eilon Cohen et al.

RexBERT excels in e-commerce with Ecom-niverse corpus and three-phase training.

Rahul Bajaj, Anuj Garg