This paper introduces LingBot-Video, a video pretraining paradigm for embodied intelligence using a DiT-based approach, Mixture-of-Experts framework, and extensive robot-oriented data.

This paper explores the effects of geometric perturbations on the stability of diffusion architectures, specifically Diffusion Transformers and Convolutional UNets, using a unified framework and contr…

DASH introduces a dual-branch distillation framework to effectively compress class-conditional diffusion models by independently supervising both score branches, significantly preserving guidance fide…

The paper proposes a novel layer and point-wise projection mapping combined with LoRA injection to efficiently distill knowledge from a large teacher model to a small student model, significantly impr…

The paper introduces a comprehensive framework, Realtime Risk Studio, that operationalizes qualitative risk models (Bowtie diagrams) into formal, probabilistic, and intervention-ready runtime models u…

A black-box evaluation framework is presented to assess Large Language Models' ability to generate Design Structure Matrices from technical documentation, using structural, classification, and stabili…

This paper introduces Swiss-Bench 003, an expanded evaluation framework assessing LLM reliability and adversarial security across eight dimensions using 808 Swiss-specific items, revealing that self-g…

This paper introduces DiStash, a disaggregated transactional key-value store that enables an application to use a single transaction to manage key-value pairs across different pools of stashes, preven…

The paper introduces a non-intrusive variant of index-aware learning for solving differential-algebraic equations (DAEs), ensuring that learned solutions maintain physical consistency like Kirchhoff's…

This paper introduces DDC, a Dead-Direction Conditioner that keeps a deep network's optimization on the symmetry quotient by conditioning the optimizer's state in the orbit decomposition of a $G$-inva…

FedIDM introduces a novel federated learning framework that uses iterative distribution matching to achieve fast and stable convergence and maintain high model utility even when facing a large proport…

This paper develops an adjoint-sensitivity framework for positional influence in causal residual Transformers and provides theoretical results on the residual-to-depth-flow estimate and finite-token-t…

This paper introduces a new distillation reward, the delta signal, for on-policy distillation in reinforcement learning, which captures changes induced by reasoning tuning and improves performance.

The paper proposes DareU, a novel LLM unlearning framework that optimizes unlearning by zeroing out data attribution scores instead of maximizing prediction loss, achieving effective unlearning while…

The paper proposes Guided Denoiser Self-Distillation (GDSD), a novel method that bypasses the use of likelihood surrogates (like ELBO) in RL for diffusion language models, achieving state-of-the-art p…

The paper introduces a novel, non-deep neural network architecture that achieves the performance of LLMs by finding the global optimum of the loss function in a single, closed-form iteration, eliminat…

This paper proposes DE-2LS, a late-stage, locally search-enhanced variant of differential evolution that improves the exploitation capability of the RDEx-based search framework while preserving its sp…

The paper proposes DAG-MoE, a novel sparse Mixture-of-Experts framework that replaces standard weighted-sum aggregation with structural aggregation to enhance model performance and enable multi-step r…