…View arXiv page View PDF GitHub 10 Add to collection Community ICML2026 Get this paper in your agent: hf papers read 2605.11711 Don't have the latest CLI? curl -LsSf https…
…View arXiv page View PDF GitHub 40 Add to collection Community Standard policy gradients are fundamentally broken for proactive recommendation. ProRL fixes them with rectified gradient estimation. Proactive Recommender Systems aim to…
…View arXiv page View PDF GitHub 6 Add to collection Community Not just think! Agents need to explore the environment at test-time! Get this paper in your agent: hf papers read…
…View arXiv page View PDF Add to collection Community Get this paper in your agent: hf papers read 2605.13037 Don't have the latest CLI? curl -LsSf https://hf.co/cli…
…View arXiv page View PDF Project page Add to collection Community MemDreamer decouples perception and reasoning of long-video understanding via Hierachical Graph Memory and Agentic retrieval mechanism. This paradigm bypasses context…
…However, textual CoT forces this computation through a discrete, serial, and communication-oriented token stream: each reasoning step must be verbalized before the model can proceed, even when the underlying update is…
…View arXiv page View PDF Project page GitHub 46 Add to collection Community This paper introduces MoCam, a unified framework for novel view synthesis that addresses the fundamental conflict between geometric and…
…Gianluca Barmina , Federico Torrielli , , , , , , , , Abstract A psychologically-informed refusal framework called PsychoSafe is developed for large language models to improve harmful request handling through structured supportive communication, showing enhanced refusal quality and…
…We will release our benchmark, data, code, and models at https://github.com/microsoft/Phi-Ground.git View arXiv page View PDF GitHub 34 Add to collection Community Grounding anything any action…
…View arXiv page View PDF Project page GitHub 10 Add to collection Community With thousands of open-source models being released on HuggingFace, model selection is becoming a serious bottleneck. Our work…