Tracked topic
Framework is a company that produces modular laptops designed so users can replace components like the motherboard, display, and keyboard.
Papers arxiv:2607.05391 LLM-as-a-Verifier: A General-Purpose Verification Framework Published on Jul 6 Submitted by taesiri on Jul 7 Authors: , , , , , , , , Abstract LLM-as-a-Verifier introduces a probabilistic verification framework that scales across multiple dimensions to improve solution corre… …
Papers arxiv:2604.24351 Diffusion Templates: A Unified Plugin Framework for Controllable Diffusion Published on Apr 27 Submitted by Yingda Chen on Apr 30 Authors: Zhongjie Duan , , Yingda Chen Abstract Diffusion Templates presents a unified framework that decouples base-model inference from control… …
Papers arxiv:2606.17162 MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision Published on Jun 15 Submitted by Ye Jin on Jun 22 1 Paper of the day Authors: Ye Jin , , , Abstract MemSlides presents a hierarchical memory framework for… …
Papers arxiv:2601.07525 Thinking Before Constraining: A Unified Decoding Framework for Large Language Models Published on May 28 Submitted by Ngoc Trinh Hung NGUYEN on May 29 Nokia Authors: Ngoc Trinh Hung Nguyen , Alonso Silva , , , , Abstract A hybrid approach called In-Writing is proposed that c… …
… View arXiv page View PDF Project page GitHub 3 Add to collection Community A plug-and-play, consequence-aware safety framework for securing mobile GUI agents before execution. …
… View arXiv page View PDF GitHub 18 Add to collection Community EvolvingWorld introduces an open-schema framework for long-horizon literary world simulation, enabling characters and world states to evolve together through ongoing interactions. …
… By leveraging predictive world-model embeddings, our method provides a unified framework for failure detection across different policies. …
… Existing benchmarks are poorly aligned with production inference frameworks : they evaluate kernels on a single GPU with synthetic inputs, ignore the surrounding compilation stack , and reward replicating known optimizations rather than discovering new ones. …
… We propose a scalable framework that elicits task-solving ability in such models by combining self-distillation with reinforcement learning . …
… This paper introduces MASA, a model-aware skill alignment framework that rewrites and adapts skills based on a model’s capability profile. …