Paper page - GORGO: Online Tuning for Cross-Region Network-Aware LLM Serving
…During held-out evaluation windows, we fix the parameter values learned from tuning and improve p95 TTFT by 6.9-15.5% and p95 end-to-end (E2E) latency by 14.3…
Search
Paper page - SANA-Streaming: Real-time Streaming Video Editing with Hybrid Diffusion Transformer
…The resulting system achieves real-time 1280 x 704 resolution editing at 24 end-to-end FPS on a single RTX 5090 GPU, with the DiT core running at 58 FPS. Experimental…
Paper page - CPCANet: Deep Unfolding Common Principal Component Analysis for Domain Generalization
…This approach integrates the statistical properties of CPCA into an end-to-end trainable framework, enforcing the discovery of a shared subspace across diverse domains while preserving interpretability. Experiments on four standard…
Paper page - A Frozen Pixel-Space Diffusion Model Can Guide Itself with Its Own Samples
…Generated by thinkingmachines/Inkling-Small Pixel-space diffusion models aim to learn an end-to-end generator directly over raw pixels. This is challenging because a single model must capture both global…
Paper page - High-Fidelity Two-Step Image Generation via Teacher-Aligned End-to-End Distillation
Papers arxiv:2606.12575 High-Fidelity Two-Step Image Generation via Teacher-Aligned End-to-End Distillation Published on Jun 10 Submitted by Dongyang Liu (Chris Liu) on Jun 12 Tongyi-MAI…
Paper page - Can Generalist Agents Automate Data Curation?
…agents mainly tune local policy variants rather than explore new policy families, even when given strategy guides and paper references. Scaffolds requiring each iteration to cite, instantiate, and adapt a prior method…
Paper page - Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance
…Kangsheng Duan , Ziyang Xu , , , , Abstract A lightweight image inpainting framework achieves high-fidelity results with significantly reduced parameters and inference time through novel local-global interaction blocks and adaptive distillation strategies. Generated…
Paper page - SAAS: Self-Aware Reinforcement Learning for Over-Search Mitigation in Agentic Search
…To this end, we propose SAAS, a novel RL framework designed to cultivate dynamic self-awareness that precisely regulates search behavior without compromising accuracy. SAAS introduces three key components: (i) a search…
Paper page - Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning
…We further improve this single-rollout strategy with practical value-model training designs. To improve optimization stability, we introduce a strict double-side token-level clipping strategy. SAO is able to train…
Paper page - LoomVideo: Unifying Multimodal Inputs into Video Generation and Editing
…End-to-End MultiModal Customization for Joint Audio-Video Generation (2026) Mamoda2.5: Enhancing Unified Multimodal Model with DiT-MoE (2026) Please give a thumbs up to this comment if you found…