Tracked topic
Framework is a company that produces modular laptops designed so users can replace components like the motherboard, display, and keyboard.
…To rigorously diagnose grounding behavior, we propose Calibrated Accuracy (mathrm{Cal)}, which jointly rewards correct grounding and appropriate abstention, incorporating absent-persona queries within a unified evaluation framework. On our dedicated experiments…
…Rishabh Tiwari , , Lakshya A Agrawal , , , , , , Abstract A fast-slow learning framework for large language models combines fixed parameters with optimized context to achieve better sample efficiency, reduced catastrophic forgetting, and improved adaptability…
…Existing few-step methods address this through distillation, consistency training, or adversarial objectives, but sacrifice the likelihood framework in the process. We introduce Normalizing Trajectory Models (NTM), which models each reverse step…
…Cross-Architecture Distillation for Diffusion Large Language Models Published on Apr 29 Submitted by N2048M on Apr 30 Peking University Authors: , Wen Wang , , Abstract Researchers developed TIDE, a framework for cross-architecture…
…George Wu , , Qing Yi , , , , , , , Abstract TMAS is a multi-agent framework for test-time scaling that enhances large language model reasoning through structured collaboration and hierarchical memory systems. AI-generated summary Test…
…Joint Talking Audio-Video Generation with Autoregressive Diffusion Modeling Published on Apr 26 Submitted by Hongzhan Lin on May 4 Authors: , , , , , , , , , , Abstract Talker-T2AV presents an autoregressive diffusion framework for talking head…
…AI-generated summary We present Qwen-Image-2.0, an omni-capable image generation foundation model that unifies high-fidelity generation and precise image editing within a single framework. Despite recent progress…
…Juanxi Tian , Fengyuan Liu , , , , , Haodong Li , , Abstract Auto-Rubric as Reward (ARR) framework externalizes implicit preference knowledge into structured rubrics for improved multimodal alignment, while Rubric Policy Optimization (RPO) stabilizes policy gradients…
…Shijie Lian , , , , , , , , , , Abstract IntentVLA is a history-conditioned visual-language action framework that improves robot imitation learning stability by encoding short-horizon intents from visual observations, addressing challenges from partial observability and…
Papers arxiv:2605.04569 Lightning Unified Video Editing via In-Context Sparse Attention Published on May 6 Submitted by taesiri on May 7 Authors: , , , , , , Abstract In-context sparse attention framework enables efficient…