arXiv:2607. 23159v1 Announce Type: new Abstract: Test-time search lets small video diffusion models rival larger ones, but costs 2-10x more.
arXiv:2608. 12032v1 Announce Type: cross Abstract: Video diffusion transformers are costly to sample: every denoising step applies self-attention over a long 3D token sequence, a quadratic cost that dominates as resolution and duration grow.
arXiv:2608. 13043v1 Announce Type: new Abstract: Diffusion models have achieved dominant performance in visual generation but suffer from substantial inference overhead.
arXiv:2606. 19004v1 Announce Type: cross Abstract: Reinforcement learning (RL) post-training of Diffusion Transformers (DiTs) is prohibitively expensive, requiring thousands of high-end GPUs.
arXiv:2607. 29398v1 Announce Type: new Abstract: Diffusion models have revolutionized generative tasks but incur high latency due to iterative denoising.
arXiv:2607. 15516v1 Announce Type: cross Abstract: Production LLM deployments combine two cost-reduction primitives: prompt caching (a discounted rate for re-used token prefixes) and prompt compression (fewer tokens sent).
arXiv:2606. 13035v1 Announce Type: cross Abstract: Autoregressive video diffusion models provide a natural formulation for streaming and variable-length video generation by conditioning newly generated frames on previously generated content.
Video Diffusion Transformers (DiTs) spend most of their compute inside the Self-Attention operation, whose cost grows quadratically, $\mathcal{O}(n^2)$, with the number of latent tokens $n$. For the task of video generation, the token count is large, so this term dominates runtime and memory, and thereby caps the resolution and duration we can generate.
arXiv:2606. 26778v1 Announce Type: cross Abstract: Diffusion Transformers (DiTs) have driven substantial progress in image and video generation but suffer from prohibitive computational costs.
arXiv:2607. 04281v1 Announce Type: cross Abstract: Semantic caching reduces the latency and cost of retrieval-augmented generation (RAG) by serving cached answers to semantically similar queries, but most existing methods do not model the time-varying freshness of open-web evidence.
arXiv:2606. 09682v1 Announce Type: new Abstract: AutoMegaKernel (AMK) compiles a HuggingFace Llama-family model into a single persistent cooperative CUDA kernel that runs the whole forward pass in one launch, with no per-model hand-written CUDA.
arXiv:2608. 05358v1 Announce Type: new Abstract: Federated learning repeatedly incurs local optimization and model-update transmission.
arXiv:2608. 07303v1 Announce Type: new Abstract: Comparisons between AutoML systems at short time budgets -- tens of seconds rather than hours -- are common in tool READMEs and workshop papers, and they are easy to get wrong.