PLoRA adapts only image tokens, enabling InternLM2-7B to compose and understand free-form interleaved text-image content.

Xiaoyi Dong, Pan Zhang, Yuhang Zang et al.

Mobile-Agent uses visual perception with DINO, OCR, and GPT-4V to autonomously operate mobile apps, achieving 91% success in Mobile-Eval.

Junyang Wang, Haiyang Xu, Jiabo Ye et al.

SERL uses RLPD with off-policy deep RL, achieving policies in 25-50 min with over 90% success, outperforming state-of-the-art.

Jianlan Luo, Zheyuan Hu, Charles Xu et al.

Motion-I2V combines diffusion-based motion prediction with an enhanced temporal attention mechanism to produce consistent, controllable videos from images, supporting sparse trajectories and zero-shot translation.

Xiaoyu Shi, Zhaoyang Huang, Fu-Yun Wang et al.

Study shows Soft MoE outperforms sparse MoE under fixed compute budget.

Tianlin Liu, Mathieu Blondel, Carlos Riquelme et al.

SIO-MFG learns MFG solution operators unsupervised with sampling-invariant attention, cutting new-instance solve time by over five orders of magnitude.

Han Huang, Rongjie Lai

This study systematically analyzes retrieval strategies in RAG, showing random documents can boost accuracy by up to 35%.

Florin Cuconasu, Giovanni Trappolini, Federico Siciliano et al.

Marabou 2.0 employs optimized architecture and DeepSoI algorithm to support multiple activation functions, boosting neural network formal verification efficiency.

Haoze Wu, Omri Isac, Aleksandar Zeljić et al.

Proposed USE2-Comp and USE2-Swin architectures significantly improve input condition invariant speech enhancement, especially in real-world noisy multi-microphone scenarios.

Wangyou Zhang, Jee-weon Jung, Shinji Watanabe et al.

Grounded SAM combines Grounding DINO with SAM, achieving 48.7 mAP on SegInW zero-shot benchmark, enabling open-vocabulary detection and segmentation.

Tianhe Ren, Shilong Liu, Ailing Zeng et al.

Proposed Energy-Based Concept Bottleneck Models, improving prediction accuracy and concept interpretation.

Xinyue Xu, Yi Qin, Lu Mi et al.

Routoo uses a lightweight predictor and cost-aware routing to reduce inference costs by 33% while maintaining performance.

Alireza Mohammadshahi, Arshad Rafiq Shaikh, Majid Yazdani

WebVoyager achieves a 59.1% task success rate using large multimodal models.

Hongliang He, Wenlin Yao, Kaixin Ma et al.

Proposes spectral clustering with MMD and Wasserstein distance, using LOT for scalable discrete distribution clustering, outperforming baselines.

Zixiao Wang, Dong Qiao, Jicong Fan

LAA-Net: Localized Artifact Attention Network achieves 99.96% AUC in high-quality deepfake detection by explicitly focusing on local artifacts using multi-task learning and enhanced feature pyramid networks.

Dat Nguyen, Nesryne Mejri, Inder Pal Singh et al.

SEER enhances structured reasoning via reinforcement learning, achieving a 6.9% improvement on EntailmentBank.

Guoxin Chen, Kexin Tang, Chao Yang et al.

Proposed HAZARD benchmark evaluates embodied agents' decision-making in dynamic scenarios with LLMs, achieving up to 77.8% rescue value in fire, flood, and wind environments.

Qinhong Zhou, Sunli Chen, Yisong Wang et al.

Kernel mean embedding-based measure transport improves Bayesian inference in nonlinear, non-Gaussian systems, outperforming Kalman and particle filters.

L. Wang, N. Nüsken

Introduced persona-centric metamorphic relations for robustness testing; prompt learning shows lower violation rates (~20%) compared to other paradigms.

Yanbing Chen, Lin Li, Xiaohui Tao et al.

SpatialVLM employs large-scale internet data to enhance vision-language models' 3D spatial reasoning, achieving 99% accuracy in distance estimation.

Boyuan Chen, Zhuo Xu, Sean Kirmani et al.