Aya Expanse combines multi-model data arbitration, preference tuning, and merging, achieving top performance in 8B/32B multilingual models, surpassing state-of-the-art open models.

John Dang, Shivalika Singh, Daniel D'souza et al.

Relign framework uses reliability alignment to reduce tool hallucinations, boosting task success and efficiency.

Hongshen Xu, Zichen Zhu, Lei Pan et al.

Monet enhances Transformer interpretability with 262,144 monosemantic experts per layer.

Jungwoo Park, Young Jin Ahn, Kee-Eung Kim et al.

Proposes NoiseRefine, mapping noise to enable guidance-free high-quality image synthesis, trained with only 50K text-image pairs.

Donghoon Ahn, Jiwon Kang, Sanghyun Lee et al.

Survey on social simulation driven by large language model-based agents, categorized into individual, scenario, and society simulations.

Xinyi Mou, Xuanwen Ding, Qi He et al.

MIDI extends pre-trained single-object 3D models into multi-instance diffusion, capturing spatial relations with attention mechanisms.

Zehuan Huang, Yuan-Chen Guo, Xingqiao An et al.

PaliGemma 2 integrates SigLIP-So400m and Gemma 2, employing a three-stage training process across multiple scales, achieving state-of-the-art transfer performance on diverse tasks.

Andreas Steiner, André Susano Pinto, Michael Tschannen et al.

Proposes BTimer, a real-time monocular dynamic scene reconstruction model using bullet-time representation, achieving 150ms high-quality scene synthesis.

Hanxue Liang, Jiawei Ren, Ashkan Mirzaei et al.

Mimir enhances video diffusion models' text comprehension by integrating text encoders and large language models.

Shuai Tan, Biao Gong, Yutong Feng et al.

Proposes Pragmatic Metacognitive Prompting (PMP), integrating pragmatics and reflection, boosting LLM sarcasm detection; GPT-4o achieves SOTA on MUStARD and SemEval2018 with +20% accuracy.

Joshua Lee, Wyatt Fong, Alexander Le et al.

HunyuanVideo is an open-source large-scale video generation model with over 1.3 billion parameters, matching or surpassing top industry closed-source models.

Weijie Kong, Qi Tian, Zijian Zhang et al.

Proves coin-betting as the optimal e-variable strategy for sequential mean testing, establishing its uniqueness and theoretical guarantees.

Eugenio Clerico

Proposed Transformer-based multimodal medical foundation model enhances multi-organ data fusion, achieving 85% accuracy in disease classification.

Kai Sun, Siyan Xue, Fuchun Sun et al.

UNIFY constructs a unified PG-based index supporting hybrid, pre-, and post-filtering for RF-ANNS, achieving logarithmic complexity and high scalability.

Anqi Liang, Pengcheng Zhang, Bin Yao et al.

Dual-exposure stereo extends dynamic range for improved 3D depth estimation accuracy.

Juhyung Choi, Jinnyeong Kim, Seokjun Choi et al.

SceneFactor employs factored latent diffusion models for controllable large-scale 3D scene generation and editing, enabling intuitive object manipulation with minimal clicks.

Alexey Bokhovkin, Quan Meng, Shubham Tulsiani et al.

Commit0 benchmarks AI's ability to generate full libraries from scratch via multi-stage feedback, with limited success (~17-26% test pass rate).

Wenting Zhao, Nan Jiang, Celine Lee et al.

LamRA leverages large multimodal models with two-stage training and lightweight LoRA modules to unify multi-task retrieval and reranking, achieving strong zero-shot performance.

Yikun Liu, Pingan Chen, Jiayin Cai et al.

Proposes Structured LATent (SLAT) for scalable 3D generation, integrating sparse grids with multiview features, enabling multi-format outputs with up to 2 billion parameters.

Jianfeng Xiang, Zelong Lv, Sicheng Xu et al.

Enhancing AI models for feature extraction in artistic images using geometric data, tested on PACS dataset.

Mridula Vijendran, Jingjing Deng, Shuang Chen et al.