Tracked topic
Framework is a company that produces modular laptops designed so users can replace components like the motherboard, display, and keyboard.
…Reinforcement learning (RL) provides a principled framework for optimizing such sequential decision tasks, as path rewards can naturally capture both short-term acceptance and long-term guidance effectiveness. However, naively applying policy…
…The question of "does this complicated agent framework really improve performance over a simpler approach" doesn't have an immediately obvious answer to me. I took the liberty of converting your javascript…
…Ziyu Guo , , , Abstract ATLAS presents a visual reasoning framework that combines agentic operations and latent representations using functional tokens, enabling efficient training and improved performance on complex benchmarks. AI-generated summary Visual…
…To address these limitations, we propose Ψ-RAG, a tree-RAG framework with two key components. First, a hierarchical abstract tree index built through an iterative "merging and collapse" process that adapts…
…Yaorui Shi , Yuxin Chen , Zhengxi Lu , , , , , , Abstract Skill1 is a unified framework that trains a single policy to simultaneously evolve skill selection, utilization, and distillation capabilities using a shared task-outcome objective…
…We present PRISM, a single-step diffusion-based Text-SR framework that addresses these two challenges through Flow-Matching Prior Rectification ( FMPR ) and a Structure-guided Uncertainty-aware Residual Encoder ( SURE ). FMPR…
…Self-Evolving Agentic Post-Training Published on May 9 Submitted by Penghui Du on May 15 Natural and Artificial Intelligence Lab Authors: , , Bo Li , , , , , , , , , , , Abstract RewardHarness is a self-evolving framework that…
…Concretely, we introduce DiGSeg ( Diffusion Models as a Generalist Segmentation Learner), which repurposes a pretrained diffusion model into a unified segmentation framework. Our approach encodes the input image and ground-truth mask…
…Joowon Kim , Seungho Shin , , Abstract A closed-loop framework collaboratively integrates vision-language models with video generation models at step level to improve visual reasoning by enabling real-time failure detection and…
…Rui Cai , , Xiaofei Wen , , , , , Abstract ModelLens is a unified framework that recommends models in real-world scenarios by learning from public leaderboard data to rank unseen models on unseen datasets without requiring…