VipDiff uses optical flow and training-free diffusion models for video inpainting, enhancing spatio-temporal coherence.

Chaohao Xie, Kai Han, Kwan-Yee K. Wong

Hunyuan3D 2.0 employs flow-based diffusion transformers for high-res textured 3D asset creation, integrating ShapeVAE and multi-view texture synthesis.

Zibo Zhao, Zeqiang Lai, Qingxiang Lin et al.

Proposes a prompt engineering + Balanced RAG framework for detecting disinformation campaigns, achieving 42.4% precision and 85.1% recall on election data.

Nikos Kanakaris, Heng Ping, Xiongye Xiao et al.

Zep employs Graphiti's time-aware knowledge graph, dynamically integrating conversational and business data, achieving 94.8% accuracy and 90% latency reduction, outperforming MemGPT.

Preston Rasmussen, Pavlo Paliychuk, Travis Beauvais et al.

Study explores intrinsic rewards' impact on RL exploration; State Count excels in low-dimensional settings.

Aya Kayal, Eduardo Pignatelli, Laura Toni

Proposes a linear-scaling causal discovery framework based on dynamical community detection for high-dimensional time series.

Matteo Allione, Vittorio Del Tatto, Alessandro Laio

Proposes a character prediction algorithm from subword LLMs, improving AAC accuracy; domain adaptation further enhances simple conversational text performance.

Dylan Gaines, Keith Vertanen

Proposes One-D-Piece, a variable-length image tokenizer with Tail Token Drop, achieving high-quality, flexible compression surpassing JPEG/WebP.

Keita Miwa, Kento Sasaki, Hidehisa Arai et al.

GVMGen employs hierarchical attention for video-music alignment, outperforming SOTA with improved relevance and diversity.

Heda Zuo, Weitao You, Junxian Wu et al.

FAST uses DCT-based compression to encode robot action sequences, enabling efficient training of autoregressive VLAs on high-frequency, dexterous tasks.

Karl Pertsch, Kyle Stachowicz, Brian Ichter et al.

Unified inference-time guidance framework for diffusion models using reward and value functions, improving protein design performance without model fine-tuning.

Masatoshi Uehara, Yulai Zhao, Chenyu Wang et al.

This survey reviews LLMs in EDA, focusing on architectures, model size effects, and customization techniques, highlighting their impact on chip design automation.

Jingyu Pan, Guanglei Zhou, Chen-Chia Chang et al.

WMamba combines wavelet analysis with dynamic contour convolution, achieving SOTA face forgery detection with high robustness and efficiency.

Siran Peng, Tianshuo Zhang, Li Gao et al.

Proposes Fuzzy Full Disjunction combining semantic embeddings and bipartite matching, improving data lake table integration with minimal runtime overhead.

Aamod Khatiwada, Roee Shraga, Renée J. Miller

Agentic RAG enhances real-time response by embedding autonomous AI agents for dynamic retrieval and generation.

Aditi Singh, Abul Ehtesham, Saket Kumar et al.

MMDocIR benchmark introduces dual-level multimodal long document retrieval, outperforming text-only models with significant improvements in Recall@1 and layout understanding.

Kuicai Dong, Yujing Chang, Xin Deik Goh et al.

VRS-HQ employs hierarchical multimodal tokens with dynamic temporal aggregation, achieving 63.3% J&F on ReVOS, surpassing VISA.

Sitong Gong, Yunzhi Zhuge, Lu Zhang et al.

MiniMax-01 leverages Lightning Attention combined with MoE, reaching 4560B parameters, supporting up to 4 million tokens, matching GPT-4 performance.

MiniMax, Aonian Li, Bangwei Gong et al.

TempoGPT uses vector quantization of temporal embeddings to enhance multimodal time series reasoning, outperforming existing models.

Haochuan Zhang, Chunhua Yang, Jie Han et al.

Using conformal prediction to ensure at least 90% coverage in deep learning-based weed detection for precision spraying.

Paul Melki, Lionel Bombrun, Boubacar Diallo et al.