DiffusionNFT: Online Diffusion Reinforcement with Forward Process
arXiv:2509.16117v1 Announce Type: cross Abstract: Online reinforcement learning (RL) has been central to post-training language models, but its extension to…
Beyond Pointwise Scores: Decomposed Criteria-Based Evaluation of LLM Responses
arXiv:2509.16093v1 Announce Type: cross Abstract: Evaluating long-form answers in high-stakes domains such as law or medicine remains a fundamental challenge.…
Sea-ing Through Scattered Rays: Revisiting the Image Formation Model for Realistic Underwater Image Generation
arXiv:2509.15011v2 Announce Type: replace-cross Abstract: In recent years, the underwater image formation model has found extensive use in the generation…
Unified Crew Planning and Replanning Optimization in Multi-Line Metro Systems Considering Workforce Heterogeneity
arXiv:2509.14251v1 Announce Type: new Abstract: Metro crew planning is a key component of smart city development as it directly impacts…
Dense Video Understanding with Gated Residual Tokenization
arXiv:2509.14199v2 Announce Type: replace-cross Abstract: High temporal resolution is essential for capturing fine-grained details in video understanding. However, current video…
Blockchain-Enabled Explainable AI for Trusted Healthcare Systems
arXiv:2509.14987v1 Announce Type: cross Abstract: This paper introduces a Blockchain-Integrated Explainable AI Framework (BXHF) for healthcare systems to tackle two…
BWCache: Accelerating Video Diffusion Transformers through Block-Wise Caching
arXiv:2509.13789v2 Announce Type: replace-cross Abstract: Recent advancements in Diffusion Transformers (DiTs) have established them as the state-of-the-art method for video…
Intercropping with robots
Post Content
COMI-LINGUA: Expert Annotated Large-Scale Dataset for Multitask NLP in Hindi-English Code-Mixing
arXiv:2503.21670v3 Announce Type: replace-cross Abstract: We introduce COMI-LINGUA, the largest manually annotated Hindi-English code-mixed dataset, comprising 125K+ high-quality instances across…